diff options
67 files changed, 499 insertions, 281 deletions
@@ -3101,7 +3101,7 @@ S: Minto, NSW, 2566 S: Australia N: Stephen Smalley -E: sds@epoch.ncsc.mil +E: sds@tycho.nsa.gov D: portions of the Linux Security Module (LSM) framework and security modules N: Chris Smith diff --git a/MAINTAINERS b/MAINTAINERS index b6cbac5..11d44da 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2298,7 +2298,7 @@ S: Supported SELINUX SECURITY MODULE P: Stephen Smalley -M: sds@epoch.ncsc.mil +M: sds@tycho.nsa.gov P: James Morris M: jmorris@namei.org L: linux-kernel@vger.kernel.org (kernel issues) diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index d86c865..0afec85 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -442,6 +442,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" + depends on X86_CMPXCHG64 help Select this if you have a 32-bit processor and more than 4 gigabytes of physical RAM. diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c index 333578a..0810f81f 100644 --- a/arch/i386/kernel/cpu/amd.c +++ b/arch/i386/kernel/cpu/amd.c @@ -282,3 +282,11 @@ int __init amd_init_cpu(void) } //early_arch_initcall(amd_init_cpu); + +static int __init amd_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_AMD] = NULL; + return 0; +} + +late_initcall(amd_exit_cpu); diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c index 0dd92a2..f52669e 100644 --- a/arch/i386/kernel/cpu/centaur.c +++ b/arch/i386/kernel/cpu/centaur.c @@ -470,3 +470,11 @@ int __init centaur_init_cpu(void) } //early_arch_initcall(centaur_init_cpu); + +static int __init centaur_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CENTAUR] = NULL; + return 0; +} + +late_initcall(centaur_exit_cpu); diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 15aee26..7eb9213 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -44,6 +44,7 @@ static void default_init(struct cpuinfo_x86 * c) static struct cpu_dev default_cpu = { .c_init = default_init, + .c_vendor = "Unknown", }; static struct cpu_dev * this_cpu = &default_cpu; @@ -150,6 +151,7 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) { char *v = c->x86_vendor_id; int i; + static int printed; for (i = 0; i < X86_VENDOR_NUM; i++) { if (cpu_devs[i]) { @@ -159,10 +161,17 @@ static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) c->x86_vendor = i; if (!early) this_cpu = cpu_devs[i]; - break; + return; } } } + if (!printed) { + printed++; + printk(KERN_ERR "CPU: Vendor unknown, using generic init.\n"); + printk(KERN_ERR "CPU: Your system may be unstable.\n"); + } + c->x86_vendor = X86_VENDOR_UNKNOWN; + this_cpu = &default_cpu; } diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c index 7501597..00f2e05 100644 --- a/arch/i386/kernel/cpu/cyrix.c +++ b/arch/i386/kernel/cpu/cyrix.c @@ -345,7 +345,7 @@ static void __init init_cyrix(struct cpuinfo_x86 *c) /* * Handle National Semiconductor branded processors */ -static void __devinit init_nsc(struct cpuinfo_x86 *c) +static void __init init_nsc(struct cpuinfo_x86 *c) { /* There may be GX1 processors in the wild that are branded * NSC and not Cyrix. @@ -444,6 +444,14 @@ int __init cyrix_init_cpu(void) //early_arch_initcall(cyrix_init_cpu); +static int __init cyrix_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_CYRIX] = NULL; + return 0; +} + +late_initcall(cyrix_exit_cpu); + static struct cpu_dev nsc_cpu_dev __initdata = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, @@ -458,3 +466,11 @@ int __init nsc_init_cpu(void) } //early_arch_initcall(nsc_init_cpu); + +static int __init nsc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NSC] = NULL; + return 0; +} + +late_initcall(nsc_exit_cpu); diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index af591c7..ffe58ce 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -152,6 +152,7 @@ static int __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_le return 0; } +/* will only be called once; __init is safe here */ static int __init find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/i386/kernel/cpu/nexgen.c b/arch/i386/kernel/cpu/nexgen.c index 30898a2..ad87fa5 100644 --- a/arch/i386/kernel/cpu/nexgen.c +++ b/arch/i386/kernel/cpu/nexgen.c @@ -61,3 +61,11 @@ int __init nexgen_init_cpu(void) } //early_arch_initcall(nexgen_init_cpu); + +static int __init nexgen_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_NEXGEN] = NULL; + return 0; +} + +late_initcall(nexgen_exit_cpu); diff --git a/arch/i386/kernel/cpu/rise.c b/arch/i386/kernel/cpu/rise.c index 8602425..d08d5a2 100644 --- a/arch/i386/kernel/cpu/rise.c +++ b/arch/i386/kernel/cpu/rise.c @@ -51,3 +51,11 @@ int __init rise_init_cpu(void) } //early_arch_initcall(rise_init_cpu); + +static int __init rise_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_RISE] = NULL; + return 0; +} + +late_initcall(rise_exit_cpu); diff --git a/arch/i386/kernel/cpu/transmeta.c b/arch/i386/kernel/cpu/transmeta.c index fc42638..bdbeb77 100644 --- a/arch/i386/kernel/cpu/transmeta.c +++ b/arch/i386/kernel/cpu/transmeta.c @@ -84,7 +84,7 @@ static void __init init_transmeta(struct cpuinfo_x86 *c) #endif } -static void transmeta_identify(struct cpuinfo_x86 * c) +static void __init transmeta_identify(struct cpuinfo_x86 * c) { u32 xlvl; generic_identify(c); @@ -111,3 +111,11 @@ int __init transmeta_init_cpu(void) } //early_arch_initcall(transmeta_init_cpu); + +static int __init transmeta_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_TRANSMETA] = NULL; + return 0; +} + +late_initcall(transmeta_exit_cpu); diff --git a/arch/i386/kernel/cpu/umc.c b/arch/i386/kernel/cpu/umc.c index 264fcad..2cd988f 100644 --- a/arch/i386/kernel/cpu/umc.c +++ b/arch/i386/kernel/cpu/umc.c @@ -31,3 +31,11 @@ int __init umc_init_cpu(void) } //early_arch_initcall(umc_init_cpu); + +static int __init umc_exit_cpu(void) +{ + cpu_devs[X86_VENDOR_UMC] = NULL; + return 0; +} + +late_initcall(umc_exit_cpu); diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index d661703..63f39a7 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -138,7 +138,7 @@ static int __init check_nmi_watchdog(void) if (nmi_watchdog == NMI_LOCAL_APIC) smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); mdelay((10*1000)/nmi_hz); // wait 10 ticks diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 2185377..0480454 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -297,8 +297,10 @@ void show_regs(struct pt_regs * regs) if (user_mode(regs)) printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); - printk(" EFLAGS: %08lx %s (%s)\n", - regs->eflags, print_tainted(), system_utsname.release); + printk(" EFLAGS: %08lx %s (%s %.*s)\n", + regs->eflags, print_tainted(), system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->eax,regs->ebx,regs->ecx,regs->edx); printk("ESI: %08lx EDI: %08lx EBP: %08lx", diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 0aaebf3..b814dbd 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -166,7 +166,8 @@ static void show_trace_log_lvl(struct task_struct *task, stack = (unsigned long*)context->previous_esp; if (!stack) break; - printk(KERN_EMERG " =======================\n"); + printk(log_lvl); + printk(" =======================\n"); } } @@ -239,9 +240,11 @@ void show_registers(struct pt_regs *regs) } print_modules(); printk(KERN_EMERG "CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\n" - "EFLAGS: %08lx (%s) \n", + "EFLAGS: %08lx (%s %.*s) \n", smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, system_utsname.release); + print_tainted(), regs->eflags, system_utsname.release, + (int)strcspn(system_utsname.version, " "), + system_utsname.version); print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip); printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", regs->eax, regs->ebx, regs->ecx, regs->edx); diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index 67e4e28..a28756e 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -59,7 +59,6 @@ #include <asm/nmi.h> #include <asm/irq.h> #include <asm/hw_irq.h> -#include <asm/numa.h> /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -891,7 +890,6 @@ do_rest: if (boot_error) { cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */ - clear_node_cpumask(cpu); /* was set by numa_add_cpu */ cpu_clear(cpu, cpu_present_map); cpu_clear(cpu, cpu_possible_map); x86_cpu_to_apicid[cpu] = BAD_APICID; @@ -1189,7 +1187,6 @@ void remove_cpu_from_maps(void) cpu_clear(cpu, cpu_callout_map); cpu_clear(cpu, cpu_callin_map); clear_bit(cpu, &cpu_initialized); /* was set by cpu_init() */ - clear_node_cpumask(cpu); } int __cpu_disable(void) diff --git a/block/elevator.c b/block/elevator.c index 96a61e0..2fc269f 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -323,7 +323,8 @@ void __elv_add_request(request_queue_t *q, struct request *rq, int where, /* * toggle ordered color */ - q->ordcolor ^= 1; + if (blk_barrier_rq(rq)) + q->ordcolor ^= 1; /* * barriers implicitly indicate back insertion diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c index f9fc07e..ee5ed98 100644 --- a/block/ll_rw_blk.c +++ b/block/ll_rw_blk.c @@ -508,7 +508,7 @@ static inline struct request *start_ordered(request_queue_t *q, int blk_do_ordered(request_queue_t *q, struct request **rqp) { - struct request *rq = *rqp, *allowed_rq; + struct request *rq = *rqp; int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq); if (!q->ordseq) { @@ -532,32 +532,26 @@ int blk_do_ordered(request_queue_t *q, struct request **rqp) } } + /* + * Ordered sequence in progress + */ + + /* Special requests are not subject to ordering rules. */ + if (!blk_fs_request(rq) && + rq != &q->pre_flush_rq && rq != &q->post_flush_rq) + return 1; + if (q->ordered & QUEUE_ORDERED_TAG) { + /* Ordered by tag. Blocking the next barrier is enough. */ if (is_barrier && rq != &q->bar_rq) *rqp = NULL; - return 1; - } - - switch (blk_ordered_cur_seq(q)) { - case QUEUE_ORDSEQ_PREFLUSH: - allowed_rq = &q->pre_flush_rq; - break; - case QUEUE_ORDSEQ_BAR: - allowed_rq = &q->bar_rq; - break; - case QUEUE_ORDSEQ_POSTFLUSH: - allowed_rq = &q->post_flush_rq; - break; - default: - allowed_rq = NULL; - break; + } else { + /* Ordered by draining. Wait for turn. */ + WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q)); + if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q)) + *rqp = NULL; } - if (rq != allowed_rq && - (blk_fs_request(rq) || rq == &q->pre_flush_rq || - rq == &q->post_flush_rq)) - *rqp = NULL; - return 1; } @@ -3453,7 +3447,7 @@ int __init blk_dev_init(void) iocontext_cachep = kmem_cache_create("blkdev_ioc", sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL); - for (i = 0; i < NR_CPUS; i++) + for_each_cpu(i) INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i)); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL); diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 139cbba..8b13316 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -433,12 +433,12 @@ config CDROM_PKTCDVD_BUFFERS This controls the maximum number of active concurrent packets. More concurrent packets can increase write performance, but also require more memory. Each concurrent packet will require approximately 64Kb - of non-swappable kernel memory, memory which will be allocated at - pktsetup time. + of non-swappable kernel memory, memory which will be allocated when + a disc is opened for writing. config CDROM_PKTCDVD_WCACHE - bool "Enable write caching" - depends on CDROM_PKTCDVD + bool "Enable write caching (EXPERIMENTAL)" + depends on CDROM_PKTCDVD && EXPERIMENTAL help If enabled, write caching will be set for the CD-R/W device. For now this option is dangerous unless the CD-RW media is known good, as we diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 93affee..4e7dbcc 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -43,8 +43,6 @@ * *************************************************************************/ -#define VERSION_CODE "v0.2.0a 2004-07-14 Jens Axboe (axboe@suse.de) and petero2@telia.com" - #include <linux/pktcdvd.h> #include <linux/config.h> #include <linux/module.h> @@ -131,7 +129,7 @@ static struct bio *pkt_bio_alloc(int nr_iovecs) /* * Allocate a packet_data struct */ -static struct packet_data *pkt_alloc_packet_data(void) +static struct packet_data *pkt_alloc_packet_data(int frames) { int i; struct packet_data *pkt; @@ -140,11 +138,12 @@ static struct packet_data *pkt_alloc_packet_data(void) if (!pkt) goto no_pkt; - pkt->w_bio = pkt_bio_alloc(PACKET_MAX_SIZE); + pkt->frames = frames; + pkt->w_bio = pkt_bio_alloc(frames); if (!pkt->w_bio) goto no_bio; - for (i = 0; i < PAGES_PER_PACKET; i++) { + for (i = 0; i < frames / FRAMES_PER_PAGE; i++) { pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO); if (!pkt->pages[i]) goto no_page; @@ -152,7 +151,7 @@ static struct packet_data *pkt_alloc_packet_data(void) spin_lock_init(&pkt->lock); - for (i = 0; i < PACKET_MAX_SIZE; i++) { + for (i = 0; i < frames; i++) { struct bio *bio = pkt_bio_alloc(1); if (!bio) goto no_rd_bio; @@ -162,14 +161,14 @@ static struct packet_data *pkt_alloc_packet_data(void) return pkt; no_rd_bio: - for (i = 0; i < PACKET_MAX_SIZE; i++) { + for (i = 0; i < frames; i++) { struct bio *bio = pkt->r_bios[i]; if (bio) bio_put(bio); } no_page: - for (i = 0; i < PAGES_PER_PACKET; i++) + for (i = 0; i < frames / FRAMES_PER_PAGE; i++) if (pkt->pages[i]) __free_page(pkt->pages[i]); bio_put(pkt->w_bio); @@ -186,12 +185,12 @@ static void pkt_free_packet_data(struct packet_data *pkt) { int i; - for (i = 0; i < PACKET_MAX_SIZE; i++) { + for (i = 0; i < pkt->frames; i++) { struct bio *bio = pkt->r_bios[i]; if (bio) bio_put(bio); } - for (i = 0; i < PAGES_PER_PACKET; i++) + for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) __free_page(pkt->pages[i]); bio_put(pkt->w_bio); kfree(pkt); @@ -206,17 +205,17 @@ static void pkt_shrink_pktlist(struct pktcdvd_device *pd) list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) { pkt_free_packet_data(pkt); } + INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); } static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets) { struct packet_data *pkt; - INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); - INIT_LIST_HEAD(&pd->cdrw.pkt_active_list); - spin_lock_init(&pd->cdrw.active_list_lock); + BUG_ON(!list_empty(&pd->cdrw.pkt_free_list)); + while (nr_packets > 0) { - pkt = pkt_alloc_packet_data(); + pkt = pkt_alloc_packet_data(pd->settings.size >> 2); if (!pkt) { pkt_shrink_pktlist(pd); return 0; @@ -951,7 +950,7 @@ try_next_bio: pd->current_sector = zone + pd->settings.size; pkt->sector = zone; - pkt->frames = pd->settings.size >> 2; + BUG_ON(pkt->frames != pd->settings.size >> 2); pkt->write_size = 0; /* @@ -1639,7 +1638,7 @@ static int pkt_probe_settings(struct pktcdvd_device *pd) pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; if (pd->settings.size == 0) { printk("pktcdvd: detected zero packet size!\n"); - pd->settings.size = 128; + return -ENXIO; } if (pd->settings.size > PACKET_MAX_SECTORS) { printk("pktcdvd: packet size is too big\n"); @@ -1987,8 +1986,14 @@ static int pkt_open_dev(struct pktcdvd_device *pd, int write) if ((ret = pkt_set_segment_merging(pd, q))) goto out_unclaim; - if (write) + if (write) { + if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { + printk("pktcdvd: not enough memory for buffers\n"); + ret = -ENOMEM; + goto out_unclaim; + } printk("pktcdvd: %lukB available on disc\n", lba << 1); + } return 0; @@ -2014,6 +2019,8 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); bd_release(pd->bdev); blkdev_put(pd->bdev); + + pkt_shrink_pktlist(pd); } static struct pktcdvd_device *pkt_find_dev_from_minor(int dev_minor) @@ -2379,12 +2386,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); - if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { - printk("pktcdvd: not enough memory for buffers\n"); - ret = -ENOMEM; - goto out_mem; - } - pd->bdev = bdev; set_blocksize(bdev, CD_FRAMESIZE); @@ -2395,7 +2396,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) if (IS_ERR(pd->cdrw.thread)) { printk("pktcdvd: can't start kernel thread\n"); ret = -ENOMEM; - goto out_thread; + goto out_mem; } proc = create_proc_entry(pd->name, 0, pkt_proc); @@ -2406,8 +2407,6 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) DPRINTK("pktcdvd: writer %s mapped to %s\n", pd->name, bdevname(bdev, b)); return 0; -out_thread: - pkt_shrink_pktlist(pd); out_mem: blkdev_put(bdev); /* This is safe: open() is still holding a reference. */ @@ -2503,6 +2502,10 @@ static int pkt_setup_dev(struct pkt_ctrl_command *ctrl_cmd) goto out_mem; pd->disk = disk; + INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); + INIT_LIST_HEAD(&pd->cdrw.pkt_active_list); + spin_lock_init(&pd->cdrw.active_list_lock); + spin_lock_init(&pd->lock); spin_lock_init(&pd->iosched.lock); sprintf(pd->name, "pktcdvd%d", idx); @@ -2567,8 +2570,6 @@ static int pkt_remove_dev(struct pkt_ctrl_command *ctrl_cmd) blkdev_put(pd->bdev); - pkt_shrink_pktlist(pd); - remove_proc_entry(pd->name, pkt_proc); DPRINTK("pktcdvd: writer %s unmapped\n", pd->name); @@ -2678,7 +2679,6 @@ static int __init pkt_init(void) pkt_proc = proc_mkdir("pktcdvd", proc_root_driver); - DPRINTK("pktcdvd: %s\n", VERSION_CODE); return 0; out: diff --git a/drivers/message/i2o/i2o_scsi.c b/drivers/message/i2o/i2o_scsi.c index f9e5a23..c08ddac 100644 --- a/drivers/message/i2o/i2o_scsi.c +++ b/drivers/message/i2o/i2o_scsi.c @@ -732,7 +732,7 @@ static int i2o_scsi_abort(struct scsi_cmnd *SCpnt) cpu_to_le32(I2O_CMD_SCSI_ABORT << 24 | HOST_TID << 12 | tid); msg->body[0] = cpu_to_le32(i2o_cntxt_list_get_ptr(c, SCpnt)); - if (i2o_msg_post_wait(c, msg, I2O_TIMEOUT_SCSI_SCB_ABORT)) + if (!i2o_msg_post_wait(c, msg, I2O_TIMEOUT_SCSI_SCB_ABORT)) status = SUCCESS; return status; diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 245ca99..c551bb8 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -1245,7 +1245,7 @@ static int __init init_scsi(void) if (error) goto cleanup_sysctl; - for (i = 0; i < NR_CPUS; i++) + for_each_cpu(i) INIT_LIST_HEAD(&per_cpu(scsi_done_q, i)); devfs_mk_dir("scsi"); @@ -379,7 +379,6 @@ static void __devinit fdtable_defer_list_init(int cpu) void __init files_defer_init(void) { int i; - /* Really early - can't use for_each_cpu */ - for (i = 0; i < NR_CPUS; i++) + for_each_cpu(i) fdtable_defer_list_init(i); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 4526da8..f556a0d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -120,9 +120,9 @@ struct fuse_req *fuse_get_request(struct fuse_conn *fc) return do_get_request(fc); } +/* Must be called with fuse_lock held */ static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) { - spin_lock(&fuse_lock); if (req->preallocated) { atomic_dec(&fc->num_waiting); list_add(&req->list, &fc->unused_list); @@ -134,11 +134,19 @@ static void fuse_putback_request(struct fuse_conn *fc, struct fuse_req *req) fc->outstanding_debt--; else up(&fc->outstanding_sem); - spin_unlock(&fuse_lock); } void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req) { + if (atomic_dec_and_test(&req->count)) { + spin_lock(&fuse_lock); + fuse_putback_request(fc, req); + spin_unlock(&fuse_lock); + } +} + +static void fuse_put_request_locked(struct fuse_conn *fc, struct fuse_req *req) +{ if (atomic_dec_and_test(&req->count)) fuse_putback_request(fc, req); } @@ -163,26 +171,36 @@ void fuse_release_background(struct fuse_req *req) * still waiting), the 'end' callback is called if given, else the * reference to the request is released * + * Releasing extra reference for foreground requests must be done + * within the same locked region as setting state to finished. This + * is because fuse_reset_request() may be called after request is + * finished and it must be the sole possessor. If request is + * interrupted and put in the background, it will return with an error + * and hence never be reset and reused. + * * Called with fuse_lock, unlocks it */ static void request_end(struct fuse_conn *fc, struct fuse_req *req) { - void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; - req->end = NULL; list_del(&req->list); req->state = FUSE_REQ_FINISHED; - spin_unlock(&fuse_lock); - if (req->background) { + if (!req->background) { + wake_up(&req->waitq); + fuse_put_request_locked(fc, req); + spin_unlock(&fuse_lock); + } else { + void (*end) (struct fuse_conn *, struct fuse_req *) = req->end; + req->end = NULL; + spin_unlock(&fuse_lock); down_read(&fc->sbput_sem); if (fc->mounted) fuse_release_background(req); up_read(&fc->sbput_sem); + if (end) + end(fc, req); + else + fuse_put_request(fc, req); } - wake_up(&req->waitq); - if (end) - end(fc, req); - else - fuse_put_request(fc, req); } /* diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 429f4b2..ca91797 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1308,6 +1308,7 @@ int journal_stop(handle_t *handle) transaction_t *transaction = handle->h_transaction; journal_t *journal = transaction->t_journal; int old_handle_count, err; + pid_t pid; J_ASSERT(transaction->t_updates > 0); J_ASSERT(journal_current_handle() == handle); @@ -1333,8 +1334,15 @@ int journal_stop(handle_t *handle) * It doesn't cost much - we're about to run a commit and sleep * on IO anyway. Speeds up many-threaded, many-dir operations * by 30x or more... + * + * But don't do this if this process was the most recent one to + * perform a synchronous write. We do this to detect the case where a + * single process is doing a stream of sync writes. No point in waiting + * for joiners in that case. */ - if (handle->h_sync) { + pid = current->pid; + if (handle->h_sync && journal->j_last_sync_writer != pid) { + journal->j_last_sync_writer = pid; do { old_handle_count = transaction->t_handle_count; schedule_timeout_uninterruptible(1); @@ -790,7 +790,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) inode = nd->dentry->d_inode; if (nd->depth) - lookup_flags = LOOKUP_FOLLOW; + lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); /* At this point we know we have a real path component. */ for(;;) { @@ -885,7 +885,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) last_with_slashes: lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; last_component: - nd->flags &= ~LOOKUP_CONTINUE; + /* Clear LOOKUP_CONTINUE iff it was previously unset */ + nd->flags &= lookup_flags | ~LOOKUP_CONTINUE; if (lookup_flags & LOOKUP_PARENT) goto lookup_parent; if (this.name[0] == '.') switch (this.len) { @@ -1069,6 +1070,8 @@ static int fastcall do_path_lookup(int dfd, const char *name, unsigned int flags, struct nameidata *nd) { int retval = 0; + int fput_needed; + struct file *file; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags; @@ -1090,29 +1093,22 @@ static int fastcall do_path_lookup(int dfd, const char *name, nd->mnt = mntget(current->fs->pwdmnt); nd->dentry = dget(current->fs->pwd); } else { - struct file *file; - int fput_needed; struct dentry *dentry; file = fget_light(dfd, &fput_needed); - if (!file) { - retval = -EBADF; - goto out_fail; - } + retval = -EBADF; + if (!file) + goto unlock_fail; dentry = file->f_dentry; - if (!S_ISDIR(dentry->d_inode->i_mode)) { - retval = -ENOTDIR; - fput_light(file, fput_needed); - goto out_fail; - } + retval = -ENOTDIR; + if (!S_ISDIR(dentry->d_inode->i_mode)) + goto fput_unlock_fail; retval = file_permission(file, MAY_EXEC); - if (retval) { - fput_light(file, fput_needed); - goto out_fail; - } + if (retval) + goto fput_unlock_fail; nd->mnt = mntget(file->f_vfsmnt); nd->dentry = dget(dentry); @@ -1126,7 +1122,12 @@ out: if (unlikely(current->audit_context && nd && nd->dentry && nd->dentry->d_inode)) audit_inode(name, nd->dentry->d_inode, flags); -out_fail: + return retval; + +fput_unlock_fail: + fput_light(file, fput_needed); +unlock_fail: + read_unlock(¤t->fs->lock); return retval; } diff --git a/include/asm-i386/system.h b/include/asm-i386/system.h index 36a92ed..399145a 100644 --- a/include/asm-i386/system.h +++ b/include/asm-i386/system.h @@ -507,7 +507,7 @@ struct alt_instr { #define smp_rmb() rmb() #define smp_wmb() wmb() #define smp_read_barrier_depends() read_barrier_depends() -#define set_mb(var, value) do { xchg(&var, value); } while (0) +#define set_mb(var, value) do { (void) xchg(&var, value); } while (0) #else #define smp_mb() barrier() #define smp_rmb() barrier() diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h index dffe276..34e434c 100644 --- a/include/asm-x86_64/numa.h +++ b/include/asm-x86_64/numa.h @@ -22,15 +22,8 @@ extern void numa_set_node(int cpu, int node); extern unsigned char apicid_to_node[256]; #ifdef CONFIG_NUMA extern void __init init_cpu_to_node(void); - -static inline void clear_node_cpumask(int cpu) -{ - clear_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]); -} - #else #define init_cpu_to_node() do {} while (0) -#define clear_node_cpumask(cpu) do {} while (0) #endif #define NUMA_NO_NODE 0xff diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h index a73f0c7..b7f6603 100644 --- a/include/asm-x86_64/system.h +++ b/include/asm-x86_64/system.h @@ -327,7 +327,7 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, #define wmb() asm volatile("" ::: "memory") #endif #define read_barrier_depends() do {} while(0) -#define set_mb(var, value) do { xchg(&var, value); } while (0) +#define set_mb(var, value) do { (void) xchg(&var, value); } while (0) #define set_wmb(var, value) do { var = value; wmb(); } while (0) #define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); } while (0) diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 558cb4c..751bb38 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -23,6 +23,7 @@ #define jfs_debug jbd_debug #else +#include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> @@ -618,6 +619,7 @@ struct transaction_s * @j_wbuf: array of buffer_heads for journal_commit_transaction * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the * number that will fit in j_blocksize + * @j_last_sync_writer: most recent pid which did a synchronous write * @j_private: An opaque pointer to fs-private information. */ @@ -807,6 +809,8 @@ struct journal_s struct buffer_head **j_wbuf; int j_wbufsize; + pid_t j_last_sync_writer; + /* * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h index b04dfa3..f63e6ee 100644 --- a/include/linux/netfilter_ipv4/ipt_connbytes.h +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -1,10 +1,10 @@ #ifndef _IPT_CONNBYTES_H #define _IPT_CONNBYTES_H -#include <net/netfilter/xt_connbytes.h> +#include <linux/netfilter/xt_connbytes.h> #define ipt_connbytes_what xt_connbytes_what -#define IPT_CONNBYTES_PKTS XT_CONNBYTES_PACKETS +#define IPT_CONNBYTES_PKTS XT_CONNBYTES_PKTS #define IPT_CONNBYTES_BYTES XT_CONNBYTES_BYTES #define IPT_CONNBYTES_AVGPKT XT_CONNBYTES_AVGPKT diff --git a/include/linux/netfilter_ipv4/ipt_policy.h b/include/linux/netfilter_ipv4/ipt_policy.h index 7fd1bec..a3f6eff 100644 --- a/include/linux/netfilter_ipv4/ipt_policy.h +++ b/include/linux/netfilter_ipv4/ipt_policy.h @@ -27,16 +27,22 @@ struct ipt_policy_spec reqid:1; }; +union ipt_policy_addr +{ + struct in_addr a4; + struct in6_addr a6; +}; + struct ipt_policy_elem { - u_int32_t saddr; - u_int32_t smask; - u_int32_t daddr; - u_int32_t dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; + union ipt_policy_addr saddr; + union ipt_policy_addr smask; + union ipt_policy_addr daddr; + union ipt_policy_addr dmask; + u_int32_t spi; + u_int32_t reqid; + u_int8_t proto; + u_int8_t mode; struct ipt_policy_spec match; struct ipt_policy_spec invert; diff --git a/include/linux/netfilter_ipv6/ip6t_policy.h b/include/linux/netfilter_ipv6/ip6t_policy.h index 5a93afc..671bd81 100644 --- a/include/linux/netfilter_ipv6/ip6t_policy.h +++ b/include/linux/netfilter_ipv6/ip6t_policy.h @@ -27,16 +27,22 @@ struct ip6t_policy_spec reqid:1; }; +union ip6t_policy_addr +{ + struct in_addr a4; + struct in6_addr a6; +}; + struct ip6t_policy_elem { - struct in6_addr saddr; - struct in6_addr smask; - struct in6_addr daddr; - struct in6_addr dmask; - u_int32_t spi; - u_int32_t reqid; - u_int8_t proto; - u_int8_t mode; + union ip6t_policy_addr saddr; + union ip6t_policy_addr smask; + union ip6t_policy_addr daddr; + union ip6t_policy_addr dmask; + u_int32_t spi; + u_int32_t reqid; + u_int8_t proto; + u_int8_t mode; struct ip6t_policy_spec match; struct ip6t_policy_spec invert; diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 2c177e4..8a94c71 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -114,7 +114,7 @@ struct pkt_ctrl_command { struct packet_settings { - __u8 size; /* packet size in (512 byte) sectors */ + __u32 size; /* packet size in (512 byte) sectors */ __u8 fp; /* fixed packets */ __u8 link_loss; /* the rest is specified * as per Mt Fuji */ @@ -169,8 +169,8 @@ struct packet_iosched #if (PAGE_SIZE % CD_FRAMESIZE) != 0 #error "PAGE_SIZE must be a multiple of CD_FRAMESIZE" #endif -#define PACKET_MAX_SIZE 32 -#define PAGES_PER_PACKET (PACKET_MAX_SIZE * CD_FRAMESIZE / PAGE_SIZE) +#define PACKET_MAX_SIZE 128 +#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE) #define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) enum packet_data_state { @@ -219,7 +219,7 @@ struct packet_data atomic_t io_errors; /* Number of read/write errors during IO */ struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */ - struct page *pages[PAGES_PER_PACKET]; + struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE]; int cache_valid; /* If non-zero, the data for the zone defined */ /* by the sector variable is completely cached */ diff --git a/include/linux/reiserfs_acl.h b/include/linux/reiserfs_acl.h index 0a36050..806ec5b 100644 --- a/include/linux/reiserfs_acl.h +++ b/include/linux/reiserfs_acl.h @@ -58,9 +58,13 @@ extern struct reiserfs_xattr_handler posix_acl_default_handler; extern struct reiserfs_xattr_handler posix_acl_access_handler; #else -#define reiserfs_get_acl NULL #define reiserfs_cache_default_acl(inode) 0 +static inline struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) +{ + return NULL; +} + static inline int reiserfs_xattr_posix_acl_init(void) { return 0; diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index 67856eb..dac43b1 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -88,12 +88,6 @@ extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); extern void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto); -static inline struct nf_conntrack_l3proto * -__nf_ct_l3proto_find(u_int16_t l3proto) -{ - return nf_ct_l3protos[l3proto]; -} - extern struct nf_conntrack_l3proto * nf_ct_l3proto_find_get(u_int16_t l3proto); @@ -103,4 +97,13 @@ extern void nf_ct_l3proto_put(struct nf_conntrack_l3proto *p); extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4; extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6; extern struct nf_conntrack_l3proto nf_conntrack_generic_l3proto; + +static inline struct nf_conntrack_l3proto * +__nf_ct_l3proto_find(u_int16_t l3proto) +{ + if (unlikely(l3proto >= AF_MAX)) + return &nf_conntrack_generic_l3proto; + return nf_ct_l3protos[l3proto]; +} + #endif /*_NF_CONNTRACK_L3PROTO_H*/ diff --git a/kernel/intermodule.c b/kernel/intermodule.c index 0cbe633..55b1e5b 100644 --- a/kernel/intermodule.c +++ b/kernel/intermodule.c @@ -179,3 +179,6 @@ EXPORT_SYMBOL(inter_module_register); EXPORT_SYMBOL(inter_module_unregister); EXPORT_SYMBOL(inter_module_get_request); EXPORT_SYMBOL(inter_module_put); + +MODULE_LICENSE("GPL"); + diff --git a/kernel/sched.c b/kernel/sched.c index f77f23f..bc38804 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5551,13 +5551,15 @@ static void calibrate_migration_costs(const cpumask_t *cpu_map) -1 #endif ); - printk("migration_cost="); - for (distance = 0; distance <= max_distance; distance++) { - if (distance) - printk(","); - printk("%ld", (long)migration_cost[distance] / 1000); + if (system_state == SYSTEM_BOOTING) { + printk("migration_cost="); + for (distance = 0; distance <= max_distance; distance++) { + if (distance) + printk(","); + printk("%ld", (long)migration_cost[distance] / 1000); + } + printk("\n"); } - printk("\n"); j1 = jiffies; if (migration_debug) printk("migration: %ld seconds\n", (j1-j0)/HZ); @@ -6109,7 +6111,7 @@ void __init sched_init(void) runqueue_t *rq; int i, j, k; - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { prio_array_t *array; rq = cpu_rq(i); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b21d78c..ceb3ebb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -444,6 +444,15 @@ retry: page = alloc_huge_page(vma, address); if (!page) { hugetlb_put_quota(mapping); + /* + * No huge pages available. So this is an OOM + * condition but we do not want to trigger the OOM + * killer, so we return VM_FAULT_SIGBUS. + * + * A program using hugepages may fault with Bus Error + * because no huge pages are available in the cpuset, per + * memory policy or because all are in use! + */ goto out; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 44b4eb4..dde04ff 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1213,18 +1213,21 @@ static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask) { int cpu = 0; - memset(ret, 0, sizeof(*ret)); + memset(ret, 0, nr * sizeof(unsigned long)); cpus_and(*cpumask, *cpumask, cpu_online_map); cpu = first_cpu(*cpumask); while (cpu < NR_CPUS) { unsigned long *in, *out, off; + if (!cpu_isset(cpu, *cpumask)) + continue; + in = (unsigned long *)&per_cpu(page_states, cpu); cpu = next_cpu(cpu, *cpumask); - if (cpu < NR_CPUS) + if (likely(cpu < NR_CPUS)) prefetch(&per_cpu(page_states, cpu)); out = (unsigned long *)ret; @@ -1886,8 +1889,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p, * not check if the processor is online before following the pageset pointer. * Other parts of the kernel may not check if the zone is available. */ -static struct per_cpu_pageset - boot_pageset[NR_CPUS]; +static struct per_cpu_pageset boot_pageset[NR_CPUS]; /* * Dynamically allocate memory for the @@ -294,6 +294,7 @@ struct kmem_list3 { unsigned long next_reap; int free_touched; unsigned int free_limit; + unsigned int colour_next; /* Per-node cache coloring */ spinlock_t list_lock; struct array_cache *shared; /* shared per node */ struct array_cache **alien; /* on other nodes */ @@ -344,6 +345,7 @@ static void kmem_list3_init(struct kmem_list3 *parent) INIT_LIST_HEAD(&parent->slabs_free); parent->shared = NULL; parent->alien = NULL; + parent->colour_next = 0; spin_lock_init(&parent->list_lock); parent->free_objects = 0; parent->free_touched = 0; @@ -390,7 +392,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - unsigned int colour_next; /* cache colouring */ struct kmem_cache *slabp_cache; unsigned int slab_size; unsigned int dflags; /* dynamic flags */ @@ -883,14 +884,14 @@ static void __drain_alien_cache(struct kmem_cache *cachep, } } -static void drain_alien_cache(struct kmem_cache *cachep, struct kmem_list3 *l3) +static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien) { int i = 0; struct array_cache *ac; unsigned long flags; for_each_online_node(i) { - ac = l3->alien[i]; + ac = alien[i]; if (ac) { spin_lock_irqsave(&ac->lock, flags); __drain_alien_cache(cachep, ac, i); @@ -900,8 +901,11 @@ static void drain_alien_cache(struct kmem_cache *cachep, struct kmem_list3 *l3) } #else #define alloc_alien_cache(node, limit) do { } while (0) -#define free_alien_cache(ac_ptr) do { } while (0) -#define drain_alien_cache(cachep, l3) do { } while (0) +#define drain_alien_cache(cachep, alien) do { } while (0) + +static inline void free_alien_cache(struct array_cache **ac_ptr) +{ +} #endif static int __devinit cpuup_callback(struct notifier_block *nfb, @@ -935,6 +939,11 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, l3->next_reap = jiffies + REAPTIMEOUT_LIST3 + ((unsigned long)cachep) % REAPTIMEOUT_LIST3; + /* + * The l3s don't come and go as CPUs come and + * go. cache_chain_mutex is sufficient + * protection here. + */ cachep->nodelists[node] = l3; } @@ -949,26 +958,47 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, & array cache's */ list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; + struct array_cache *shared; + struct array_cache **alien; nc = alloc_arraycache(node, cachep->limit, - cachep->batchcount); + cachep->batchcount); if (!nc) goto bad; + shared = alloc_arraycache(node, + cachep->shared * cachep->batchcount, + 0xbaadf00d); + if (!shared) + goto bad; +#ifdef CONFIG_NUMA + alien = alloc_alien_cache(node, cachep->limit); + if (!alien) + goto bad; +#endif cachep->array[cpu] = nc; l3 = cachep->nodelists[node]; BUG_ON(!l3); - if (!l3->shared) { - if (!(nc = alloc_arraycache(node, - cachep->shared * - cachep->batchcount, - 0xbaadf00d))) - goto bad; - /* we are serialised from CPU_DEAD or - CPU_UP_CANCELLED by the cpucontrol lock */ - l3->shared = nc; + spin_lock_irq(&l3->list_lock); + if (!l3->shared) { + /* + * We are serialised from CPU_DEAD or + * CPU_UP_CANCELLED by the cpucontrol lock + */ + l3->shared = shared; + shared = NULL; + } +#ifdef CONFIG_NUMA + if (!l3->alien) { + l3->alien = alien; + alien = NULL; } +#endif + spin_unlock_irq(&l3->list_lock); + + kfree(shared); + free_alien_cache(alien); } mutex_unlock(&cache_chain_mutex); break; @@ -977,25 +1007,34 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: + /* + * Even if all the cpus of a node are down, we don't free the + * kmem_list3 of any cache. This to avoid a race between + * cpu_down, and a kmalloc allocation from another cpu for + * memory from the node of the cpu going down. The list3 + * structure is usually allocated from kmem_cache_create() and + * gets destroyed at kmem_cache_destroy(). + */ /* fall thru */ case CPU_UP_CANCELED: mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; + struct array_cache *shared; + struct array_cache **alien; cpumask_t mask; mask = node_to_cpumask(node); - spin_lock_irq(&cachep->spinlock); /* cpu is dead; no one can alloc from it. */ nc = cachep->array[cpu]; cachep->array[cpu] = NULL; l3 = cachep->nodelists[node]; if (!l3) - goto unlock_cache; + goto free_array_cache; - spin_lock(&l3->list_lock); + spin_lock_irq(&l3->list_lock); /* Free limit for this kmem_list3 */ l3->free_limit -= cachep->batchcount; @@ -1003,34 +1042,44 @@ static int __devinit cpuup_callback(struct notifier_block *nfb, free_block(cachep, nc->entry, nc->avail, node); if (!cpus_empty(mask)) { - spin_unlock(&l3->list_lock); - goto unlock_cache; + spin_unlock_irq(&l3->list_lock); + goto free_array_cache; } - if (l3->shared) { + shared = l3->shared; + if (shared) { free_block(cachep, l3->shared->entry, l3->shared->avail, node); - kfree(l3->shared); l3->shared = NULL; } - if (l3->alien) { - drain_alien_cache(cachep, l3); - free_alien_cache(l3->alien); - l3->alien = NULL; - } - /* free slabs belonging to this node */ - if (__node_shrink(cachep, node)) { - cachep->nodelists[node] = NULL; - spin_unlock(&l3->list_lock); - kfree(l3); - } else { - spin_unlock(&l3->list_lock); + alien = l3->alien; + l3->alien = NULL; + + spin_unlock_irq(&l3->list_lock); + + kfree(shared); + if (alien) { + drain_alien_cache(cachep, alien); + free_alien_cache(alien); } - unlock_cache: - spin_unlock_irq(&cachep->spinlock); +free_array_cache: kfree(nc); } + /* + * In the previous loop, all the objects were freed to + * the respective cache's slabs, now we can go ahead and + * shrink each nodelist to its limit. + */ + list_for_each_entry(cachep, &cache_chain, next) { + l3 = cachep->nodelists[node]; + if (!l3) + continue; + spin_lock_irq(&l3->list_lock); + /* free slabs belonging to this node */ + __node_shrink(cachep, node); + spin_unlock_irq(&l3->list_lock); + } mutex_unlock(&cache_chain_mutex); break; #endif @@ -1119,7 +1168,6 @@ void __init kmem_cache_init(void) BUG(); cache_cache.colour = left_over / cache_cache.colour_off; - cache_cache.colour_next = 0; cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) + sizeof(struct slab), cache_line_size()); @@ -2011,18 +2059,16 @@ static void drain_cpu_caches(struct kmem_cache *cachep) smp_call_function_all_cpus(do_drain, cachep); check_irq_on(); - spin_lock_irq(&cachep->spinlock); for_each_online_node(node) { l3 = cachep->nodelists[node]; if (l3) { - spin_lock(&l3->list_lock); + spin_lock_irq(&l3->list_lock); drain_array_locked(cachep, l3->shared, 1, node); - spin_unlock(&l3->list_lock); + spin_unlock_irq(&l3->list_lock); if (l3->alien) - drain_alien_cache(cachep, l3); + drain_alien_cache(cachep, l3->alien); } } - spin_unlock_irq(&cachep->spinlock); } static int __node_shrink(struct kmem_cache *cachep, int node) @@ -2324,20 +2370,20 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) */ ctor_flags |= SLAB_CTOR_ATOMIC; - /* About to mess with non-constant members - lock. */ + /* Take the l3 list lock to change the colour_next on this node */ check_irq_off(); - spin_lock(&cachep->spinlock); + l3 = cachep->nodelists[nodeid]; + spin_lock(&l3->list_lock); /* Get colour for the slab, and cal the next value. */ - offset = cachep->colour_next; - cachep->colour_next++; - if (cachep->colour_next >= cachep->colour) - cachep->colour_next = 0; - offset *= cachep->colour_off; + offset = l3->colour_next; + l3->colour_next++; + if (l3->colour_next >= cachep->colour) + l3->colour_next = 0; + spin_unlock(&l3->list_lock); - spin_unlock(&cachep->spinlock); + offset *= cachep->colour_off; - check_irq_off(); if (local_flags & __GFP_WAIT) local_irq_enable(); @@ -2367,7 +2413,6 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) if (local_flags & __GFP_WAIT) local_irq_disable(); check_irq_off(); - l3 = cachep->nodelists[nodeid]; spin_lock(&l3->list_lock); /* Make slab active. */ @@ -2725,6 +2770,7 @@ static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int node BUG_ON(!l3); retry: + check_irq_off(); spin_lock(&l3->list_lock); entry = l3->slabs_partial.next; if (entry == &l3->slabs_partial) { @@ -3304,11 +3350,11 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount smp_call_function_all_cpus(do_ccupdate_local, (void *)&new); check_irq_on(); - spin_lock_irq(&cachep->spinlock); + spin_lock(&cachep->spinlock); cachep->batchcount = batchcount; cachep->limit = limit; cachep->shared = shared; - spin_unlock_irq(&cachep->spinlock); + spin_unlock(&cachep->spinlock); for_each_online_cpu(i) { struct array_cache *ccold = new.new[i]; @@ -3440,7 +3486,7 @@ static void cache_reap(void *unused) l3 = searchp->nodelists[numa_node_id()]; if (l3->alien) - drain_alien_cache(searchp, l3); + drain_alien_cache(searchp, l3->alien); spin_lock_irq(&l3->list_lock); drain_array_locked(searchp, cpu_cache_get(searchp), 0, @@ -3564,8 +3610,7 @@ static int s_show(struct seq_file *m, void *p) int node; struct kmem_list3 *l3; - check_irq_on(); - spin_lock_irq(&cachep->spinlock); + spin_lock(&cachep->spinlock); active_objs = 0; num_slabs = 0; for_each_online_node(node) { @@ -3573,7 +3618,8 @@ static int s_show(struct seq_file *m, void *p) if (!l3) continue; - spin_lock(&l3->list_lock); + check_irq_on(); + spin_lock_irq(&l3->list_lock); list_for_each(q, &l3->slabs_full) { slabp = list_entry(q, struct slab, list); @@ -3598,9 +3644,10 @@ static int s_show(struct seq_file *m, void *p) num_slabs++; } free_objects += l3->free_objects; - shared_avail += l3->shared->avail; + if (l3->shared) + shared_avail += l3->shared->avail; - spin_unlock(&l3->list_lock); + spin_unlock_irq(&l3->list_lock); } num_slabs += active_slabs; num_objs = num_slabs * cachep->num; @@ -3644,7 +3691,7 @@ static int s_show(struct seq_file *m, void *p) } #endif seq_putc(m, '\n'); - spin_unlock_irq(&cachep->spinlock); + spin_unlock(&cachep->spinlock); return 0; } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index ce617b3..802baf7 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -46,7 +46,7 @@ #define PRINTR(format, args...) do { if (net_ratelimit()) \ printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0600); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size (number of bytes) " "(defaults to 4096)"); @@ -98,12 +98,14 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR(KERN_ERR "ebt_ulog: can't alloc whole buffer " - "of size %ub!\n", nlbufsiz); - if (size < nlbufsiz) { + "of size %ub!\n", n); + if (n > size) { /* try to allocate only as much as we need for * current packet */ skb = alloc_skb(size, GFP_ATOMIC); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 00729b3..cbd4020 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -934,6 +934,13 @@ static int do_replace(void __user *user, unsigned int len) BUGPRINT("Entries_size never zero\n"); return -EINVAL; } + /* overflow check */ + if (tmp.nentries >= ((INT_MAX - sizeof(struct ebt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) / sizeof(struct ebt_counter)) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) + return -ENOMEM; + countersize = COUNTER_OFFSET(tmp.nentries) * (highest_possible_processor_id()+1); newinfo = (struct ebt_table_info *) diff --git a/net/core/dev.c b/net/core/dev.c index ffb8207..2afb0de 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3237,7 +3237,7 @@ static int __init net_dev_init(void) * Initialise the packet receive queues. */ - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct softnet_data *queue; queue = &per_cpu(softnet_data, i); diff --git a/net/core/utils.c b/net/core/utils.c index ac1d1fc..fdc4f38 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -121,7 +121,7 @@ void __init net_random_init(void) { int i; - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, i+jiffies); } @@ -133,7 +133,7 @@ static int net_random_reseed(void) unsigned long seed[NR_CPUS]; get_random_bytes(seed, sizeof(seed)); - for (i = 0; i < NR_CPUS; i++) { + for_each_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); __net_srandom(state, seed[i]); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 6bc0887..4d1c409 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -524,7 +524,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) iph->tos; if (ip_options_echo(&icmp_param.replyopts, skb_in)) - goto ende; + goto out_unlock; /* diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index afe3d8f..dd1048b 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -807,6 +807,13 @@ static int do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c index c9ebbe0..e0b5926 100644 --- a/net/ipv4/netfilter/ip_conntrack_netlink.c +++ b/net/ipv4/netfilter/ip_conntrack_netlink.c @@ -1216,7 +1216,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1567,6 +1567,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/ipv4/netfilter/ip_conntrack_tftp.c b/net/ipv4/netfilter/ip_conntrack_tftp.c index d3c5a37..4ba4463 100644 --- a/net/ipv4/netfilter/ip_conntrack_tftp.c +++ b/net/ipv4/netfilter/ip_conntrack_tftp.c @@ -71,6 +71,7 @@ static int tftp_help(struct sk_buff **pskb, exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; exp->mask.src.ip = 0xffffffff; + exp->mask.src.u.udp.port = 0; exp->mask.dst.ip = 0xffffffff; exp->mask.dst.u.udp.port = 0xffff; exp->mask.dst.protonum = 0xff; diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index ad438fb..92c5499 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -209,8 +209,8 @@ ip_nat_in(unsigned int hooknum, && (ct = ip_conntrack_get(*pskb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - if (ct->tuplehash[dir].tuple.src.ip != - ct->tuplehash[!dir].tuple.dst.ip) { + if (ct->tuplehash[dir].tuple.dst.ip != + ct->tuplehash[!dir].tuple.src.ip) { dst_release((*pskb)->dst); (*pskb)->dst = NULL; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2371b20..16f47c6 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -921,6 +921,13 @@ do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 641dbc4..180a9ea 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -35,6 +35,10 @@ * each nlgroup you are using, so the total kernel memory usage increases * by that factor. * + * Actually you should use nlbufsiz a bit smaller than PAGE_SIZE, since + * nlbufsiz is used with alloc_skb, which adds another + * sizeof(struct skb_shared_info). Use NLMSG_GOODSIZE instead. + * * flushtimeout: * Specify, after how many hundredths of a second the queue should be * flushed even if it is not full yet. @@ -76,7 +80,7 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NFLOG); #define PRINTR(format, args...) do { if (net_ratelimit()) printk(format , ## args); } while (0) -static unsigned int nlbufsiz = 4096; +static unsigned int nlbufsiz = NLMSG_GOODSIZE; module_param(nlbufsiz, uint, 0400); MODULE_PARM_DESC(nlbufsiz, "netlink buffer size"); @@ -143,22 +147,26 @@ static void ulog_timer(unsigned long data) static struct sk_buff *ulog_alloc_skb(unsigned int size) { struct sk_buff *skb; + unsigned int n; /* alloc skb which should be big enough for a whole * multipart message. WARNING: has to be <= 131000 * due to slab allocator restrictions */ - skb = alloc_skb(nlbufsiz, GFP_ATOMIC); + n = max(size, nlbufsiz); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { - PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", - nlbufsiz); + PRINTR("ipt_ULOG: can't alloc whole buffer %ub!\n", n); - /* try to allocate only as much as we need for - * current packet */ + if (n > size) { + /* try to allocate only as much as we need for + * current packet */ - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - PRINTR("ipt_ULOG: can't even allocate %ub\n", size); + skb = alloc_skb(size, GFP_ATOMIC); + if (!skb) + PRINTR("ipt_ULOG: can't even allocate %ub\n", + size); + } } return skb; diff --git a/net/ipv4/netfilter/ipt_policy.c b/net/ipv4/netfilter/ipt_policy.c index 18ca825..5a7a265 100644 --- a/net/ipv4/netfilter/ipt_policy.c +++ b/net/ipv4/netfilter/ipt_policy.c @@ -26,10 +26,13 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ipt_policy_elem *e) { -#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((e->x.a4.s_addr == (e->y.a4.s_addr & (z))) \ + ^ e->invert.x)) +#define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) - return MATCH(saddr, x->props.saddr.a4 & e->smask) && - MATCH(daddr, x->id.daddr.a4 & e->dmask) && + return MATCH_ADDR(saddr, smask, x->props.saddr.a4) && + MATCH_ADDR(daddr, dmask, x->id.daddr.a4) && MATCH(proto, x->id.proto) && MATCH(mode, x->props.mode) && MATCH(spi, x->id.spi) && @@ -89,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ipt_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 39d49dc..1b167c4b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -49,7 +49,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 847068f..74ff56c 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -978,6 +978,13 @@ do_replace(void __user *user, unsigned int len) if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; + /* overflow check */ + if (tmp.size >= (INT_MAX - sizeof(struct xt_table_info)) / NR_CPUS - + SMP_CACHE_BYTES) + return -ENOMEM; + if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) + return -ENOMEM; + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; diff --git a/net/ipv6/netfilter/ip6t_policy.c b/net/ipv6/netfilter/ip6t_policy.c index afe1cc4..3d39ec9 100644 --- a/net/ipv6/netfilter/ip6t_policy.c +++ b/net/ipv6/netfilter/ip6t_policy.c @@ -26,8 +26,9 @@ MODULE_LICENSE("GPL"); static inline int match_xfrm_state(struct xfrm_state *x, const struct ip6t_policy_elem *e) { -#define MATCH_ADDR(x,y,z) (!e->match.x || \ - ((ip6_masked_addrcmp((z), &e->x, &e->y)) == 0) ^ e->invert.x) +#define MATCH_ADDR(x,y,z) (!e->match.x || \ + ((!ip6_masked_addrcmp(&e->x.a6, &e->y.a6, z)) \ + ^ e->invert.x)) #define MATCH(x,y) (!e->match.x || ((e->x == (y)) ^ e->invert.x)) return MATCH_ADDR(saddr, smask, (struct in6_addr *)&x->props.saddr.a6) && @@ -91,7 +92,7 @@ match_policy_out(const struct sk_buff *skb, const struct ip6t_policy_info *info) return 0; } - return strict ? 1 : 0; + return strict ? i == info->len : 0; } static int match(const struct sk_buff *skb, diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 50a13e7..4238b1e 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -38,7 +38,7 @@ static int fold_prot_inuse(struct proto *proto) int res = 0; int cpu; - for (cpu=0; cpu<NR_CPUS; cpu++) + for_each_cpu(cpu) res += proto->stats[cpu].inuse; return res; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 62bb509..0ce337a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -188,7 +188,7 @@ extern struct nf_conntrack_protocol nf_conntrack_generic_protocol; struct nf_conntrack_protocol * __nf_ct_proto_find(u_int16_t l3proto, u_int8_t protocol) { - if (unlikely(nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_generic_protocol; return nf_ct_protos[l3proto][protocol]; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index ab0c920..6f210f3 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -657,8 +657,6 @@ static int __init init(void) /* FIXME should be configurable whether IPv4 and IPv6 FTP connections are tracked or not - YK */ for (i = 0; i < ports_c; i++) { - memset(&ftp[i], 0, sizeof(struct nf_conntrack_helper)); - ftp[i][0].tuple.src.l3num = PF_INET; ftp[i][1].tuple.src.l3num = PF_INET6; for (j = 0; j < 2; j++) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 73ab16b..9ff34630 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1232,7 +1232,7 @@ static int ctnetlink_expect_event(struct notifier_block *this, b = skb->tail; - type |= NFNL_SUBSYS_CTNETLINK << 8; + type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(struct nfgenmsg)); nfmsg = NLMSG_DATA(nlh); @@ -1589,6 +1589,7 @@ static struct nfnetlink_subsystem ctnl_exp_subsys = { }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __init ctnetlink_init(void) { diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e10512e..3b3c781 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -37,7 +37,7 @@ #include "../bridge/br_private.h" #endif -#define NFULNL_NLBUFSIZ_DEFAULT 4096 +#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ @@ -314,24 +314,28 @@ static struct sk_buff *nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; + unsigned int n; UDEBUG("entered (%u, %u)\n", inst_size, pkt_size); /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ - skb = alloc_skb(inst_size, GFP_ATOMIC); + n = max(inst_size, pkt_size); + skb = alloc_skb(n, GFP_ATOMIC); if (!skb) { PRINTR("nfnetlink_log: can't alloc whole buffer (%u bytes)\n", inst_size); - /* try to allocate only as much as we need for current - * packet */ + if (n > pkt_size) { + /* try to allocate only as much as we need for current + * packet */ - skb = alloc_skb(pkt_size, GFP_ATOMIC); - if (!skb) - PRINTR("nfnetlink_log: can't even alloc %u bytes\n", - pkt_size); + skb = alloc_skb(pkt_size, GFP_ATOMIC); + if (!skb) + PRINTR("nfnetlink_log: can't even alloc %u " + "bytes\n", pkt_size); + } } return skb; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 18ed9c5..cac38b2e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -825,7 +825,8 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, } if (nfqa[NFQA_MARK-1]) - skb->nfmark = ntohl(*(u_int32_t *)NFA_DATA(nfqa[NFQA_MARK-1])); + entry->skb->nfmark = ntohl(*(u_int32_t *) + NFA_DATA(nfqa[NFQA_MARK-1])); issue_verdict(entry, verdict); instance_put(queue); diff --git a/net/socket.c b/net/socket.c index b38a263..a00851f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2078,7 +2078,7 @@ void socket_seq_show(struct seq_file *seq) int cpu; int counter = 0; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_cpu(cpu) counter += per_cpu(sockets_in_use, cpu); /* It can be negative, by the way. 8) */ diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 5760e05..d64aae8 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -123,7 +123,17 @@ KBUILD_HAVE_NLS := $(shell \ then echo yes ; \ else echo no ; fi) ifeq ($(KBUILD_HAVE_NLS),no) -HOSTCFLAGS += -DKBUILD_NO_NLS + HOSTCFLAGS += -DKBUILD_NO_NLS +else + KBUILD_NEED_LINTL := $(shell \ + if echo -e "\#include <libintl.h>\nint main(int a, char** b) { gettext(\"\"); return 0; }\n" | \ + $(HOSTCC) $(HOSTCFLAGS) -x c - -o /dev/null> /dev/null 2>&1 ; \ + then echo no ; \ + else echo yes ; fi) + ifeq ($(KBUILD_NEED_LINTL),yes) + HOSTLOADLIBES_conf += -lintl + HOSTLOADLIBES_mconf += -lintl + endif endif # generated files seem to need this to find local include files diff --git a/security/selinux/Kconfig b/security/selinux/Kconfig index b59582b..502f78f 100644 --- a/security/selinux/Kconfig +++ b/security/selinux/Kconfig @@ -1,6 +1,6 @@ config SECURITY_SELINUX bool "NSA SELinux Support" - depends on SECURITY && NET && INET + depends on SECURITY_NETWORK && NET && INET default n help This selects NSA Security-Enhanced Linux (SELinux). diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 06d54d9..688c0a2 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -4,9 +4,7 @@ obj-$(CONFIG_SECURITY_SELINUX) := selinux.o ss/ -selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o - -selinux-$(CONFIG_SECURITY_NETWORK) += netif.o +selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4ae834d..b7773bf 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -232,7 +232,6 @@ static void superblock_free_security(struct super_block *sb) kfree(sbsec); } -#ifdef CONFIG_SECURITY_NETWORK static int sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *ssec; @@ -261,7 +260,6 @@ static void sk_free_security(struct sock *sk) sk->sk_security = NULL; kfree(ssec); } -#endif /* CONFIG_SECURITY_NETWORK */ /* The security server must be initialized before any labeling or access decisions can be provided. */ @@ -2736,8 +2734,6 @@ static void selinux_task_to_inode(struct task_struct *p, return; } -#ifdef CONFIG_SECURITY_NETWORK - /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct avc_audit_data *ad) { @@ -3556,15 +3552,6 @@ static unsigned int selinux_ipv6_postroute_last(unsigned int hooknum, #endif /* CONFIG_NETFILTER */ -#else - -static inline int selinux_nlmsg_perm(struct sock *sk, struct sk_buff *skb) -{ - return 0; -} - -#endif /* CONFIG_SECURITY_NETWORK */ - static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { struct task_security_struct *tsec; @@ -4340,7 +4327,6 @@ static struct security_operations selinux_ops = { .getprocattr = selinux_getprocattr, .setprocattr = selinux_setprocattr, -#ifdef CONFIG_SECURITY_NETWORK .unix_stream_connect = selinux_socket_unix_stream_connect, .unix_may_send = selinux_socket_unix_may_send, @@ -4362,7 +4348,6 @@ static struct security_operations selinux_ops = { .sk_alloc_security = selinux_sk_alloc_security, .sk_free_security = selinux_sk_free_security, .sk_getsid = selinux_sk_getsid_security, -#endif #ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc, @@ -4440,7 +4425,7 @@ next_sb: all processes and objects when they are created. */ security_initcall(selinux_init); -#if defined(CONFIG_SECURITY_NETWORK) && defined(CONFIG_NETFILTER) +#if defined(CONFIG_NETFILTER) static struct nf_hook_ops selinux_ipv4_op = { .hook = selinux_ipv4_postroute_last, @@ -4501,13 +4486,13 @@ static void selinux_nf_ip_exit(void) } #endif -#else /* CONFIG_SECURITY_NETWORK && CONFIG_NETFILTER */ +#else /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE #define selinux_nf_ip_exit() #endif -#endif /* CONFIG_SECURITY_NETWORK && CONFIG_NETFILTER */ +#endif /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE int selinux_disable(void) |
