diff options
49 files changed, 816 insertions, 539 deletions
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index bec5a32e4095..4c1fc65a8b3d 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -1,7 +1,7 @@ /*P:100 This is the Launcher code, a simple program which lays out the - * "physical" memory for the new Guest by mapping the kernel image and the - * virtual devices, then reads repeatedly from /dev/lguest to run the Guest. -:*/ + * "physical" memory for the new Guest by mapping the kernel image and + * the virtual devices, then opens /dev/lguest to tell the kernel + * about the Guest and control it. :*/ #define _LARGEFILE64_SOURCE #define _GNU_SOURCE #include <stdio.h> @@ -43,7 +43,7 @@ #include "linux/virtio_console.h" #include "linux/virtio_ring.h" #include "asm-x86/bootparam.h" -/*L:110 We can ignore the 38 include files we need for this program, but I do +/*L:110 We can ignore the 39 include files we need for this program, but I do * want to draw attention to the use of kernel-style types. * * As Linus said, "C is a Spartan language, and so should your naming be." I @@ -320,7 +320,7 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) err(1, "Reading program headers"); /* Try all the headers: there are usually only three. A read-only one, - * a read-write one, and a "note" section which isn't loadable. */ + * a read-write one, and a "note" section which we don't load. */ for (i = 0; i < ehdr->e_phnum; i++) { /* If this isn't a loadable segment, we ignore it */ if (phdr[i].p_type != PT_LOAD) @@ -387,7 +387,7 @@ static unsigned long load_kernel(int fd) if (memcmp(hdr.e_ident, ELFMAG, SELFMAG) == 0) return map_elf(fd, &hdr); - /* Otherwise we assume it's a bzImage, and try to unpack it */ + /* Otherwise we assume it's a bzImage, and try to load it. */ return load_bzimage(fd); } @@ -433,12 +433,12 @@ static unsigned long load_initrd(const char *name, unsigned long mem) return len; } -/* Once we know how much memory we have, we can construct simple linear page +/* Once we know how much memory we have we can construct simple linear page * tables which set virtual == physical which will get the Guest far enough * into the boot to create its own. * * We lay them out of the way, just below the initrd (which is why we need to - * know its size). */ + * know its size here). */ static unsigned long setup_pagetables(unsigned long mem, unsigned long initrd_size) { @@ -850,7 +850,8 @@ static void handle_console_output(int fd, struct virtqueue *vq) * * Handling output for network is also simple: we get all the output buffers * and write them (ignoring the first element) to this device's file descriptor - * (stdout). */ + * (/dev/net/tun). + */ static void handle_net_output(int fd, struct virtqueue *vq) { unsigned int head, out, in; @@ -924,7 +925,7 @@ static void enable_fd(int fd, struct virtqueue *vq) write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd)); } -/* Resetting a device is fairly easy. */ +/* When the Guest asks us to reset a device, it's is fairly easy. */ static void reset_device(struct device *dev) { struct virtqueue *vq; @@ -1003,8 +1004,8 @@ static void handle_input(int fd) if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0) break; - /* Otherwise, call the device(s) which have readable - * file descriptors and a method of handling them. */ + /* Otherwise, call the device(s) which have readable file + * descriptors and a method of handling them. */ for (i = devices.dev; i; i = i->next) { if (i->handle_input && FD_ISSET(i->fd, &fds)) { int dev_fd; @@ -1015,8 +1016,7 @@ static void handle_input(int fd) * should no longer service it. Networking and * console do this when there's no input * buffers to deliver into. Console also uses - * it when it discovers that stdin is - * closed. */ + * it when it discovers that stdin is closed. */ FD_CLR(i->fd, &devices.infds); /* Tell waker to ignore it too, by sending a * negative fd number (-1, since 0 is a valid @@ -1033,7 +1033,8 @@ static void handle_input(int fd) * * All devices need a descriptor so the Guest knows it exists, and a "struct * device" so the Launcher can keep track of it. We have common helper - * routines to allocate and manage them. */ + * routines to allocate and manage them. + */ /* The layout of the device page is a "struct lguest_device_desc" followed by a * number of virtqueue descriptors, then two sets of feature bits, then an @@ -1078,7 +1079,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, struct virtqueue **i, *vq = malloc(sizeof(*vq)); void *p; - /* First we need some pages for this virtqueue. */ + /* First we need some memory for this virtqueue. */ pages = (vring_size(num_descs, getpagesize()) + getpagesize() - 1) / getpagesize(); p = get_pages(pages); @@ -1122,7 +1123,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, } /* The first half of the feature bitmask is for us to advertise features. The - * second half if for the Guest to accept features. */ + * second half is for the Guest to accept features. */ static void add_feature(struct device *dev, unsigned bit) { u8 *features = get_feature_bits(dev); @@ -1151,7 +1152,9 @@ static void set_config(struct device *dev, unsigned len, const void *conf) } /* This routine does all the creation and setup of a new device, including - * calling new_dev_desc() to allocate the descriptor and device memory. */ + * calling new_dev_desc() to allocate the descriptor and device memory. + * + * See what I mean about userspace being boring? */ static struct device *new_device(const char *name, u16 type, int fd, bool (*handle_input)(int, struct device *)) { @@ -1383,7 +1386,6 @@ struct vblk_info * Launcher triggers interrupt to Guest. */ int done_fd; }; -/*:*/ /*L:210 * The Disk @@ -1493,7 +1495,10 @@ static int io_thread(void *_dev) while (read(vblk->workpipe[0], &c, 1) == 1) { /* We acknowledge each request immediately to reduce latency, * rather than waiting until we've done them all. I haven't - * measured to see if it makes any difference. */ + * measured to see if it makes any difference. + * + * That would be an interesting test, wouldn't it? You could + * also try having more than one I/O thread. */ while (service_io(dev)) write(vblk->done_fd, &c, 1); } @@ -1501,7 +1506,7 @@ static int io_thread(void *_dev) } /* Now we've seen the I/O thread, we return to the Launcher to see what happens - * when the thread tells us it's completed some I/O. */ + * when that thread tells us it's completed some I/O. */ static bool handle_io_finish(int fd, struct device *dev) { char c; @@ -1573,11 +1578,12 @@ static void setup_block_file(const char *filename) * more work. */ pipe(vblk->workpipe); - /* Create stack for thread and run it */ + /* Create stack for thread and run it. Since stack grows upwards, we + * point the stack pointer to the end of this region. */ stack = malloc(32768); /* SIGCHLD - We dont "wait" for our cloned thread, so prevent it from * becoming a zombie. */ - if (clone(io_thread, stack + 32768, CLONE_VM | SIGCHLD, dev) == -1) + if (clone(io_thread, stack + 32768, CLONE_VM | SIGCHLD, dev) == -1) err(1, "Creating clone"); /* We don't need to keep the I/O thread's end of the pipes open. */ @@ -1587,14 +1593,14 @@ static void setup_block_file(const char *filename) verbose("device %u: virtblock %llu sectors\n", devices.device_num, le64_to_cpu(conf.capacity)); } -/* That's the end of device setup. :*/ +/* That's the end of device setup. */ -/* Reboot */ +/*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */ static void __attribute__((noreturn)) restart_guest(void) { unsigned int i; - /* Closing pipes causes the waker thread and io_threads to die, and + /* Closing pipes causes the Waker thread and io_threads to die, and * closing /dev/lguest cleans up the Guest. Since we don't track all * open fds, we simply close everything beyond stderr. */ for (i = 3; i < FD_SETSIZE; i++) @@ -1603,7 +1609,7 @@ static void __attribute__((noreturn)) restart_guest(void) err(1, "Could not exec %s", main_args[0]); } -/*L:220 Finally we reach the core of the Launcher, which runs the Guest, serves +/*L:220 Finally we reach the core of the Launcher which runs the Guest, serves * its input and output, and finally, lays it to rest. */ static void __attribute__((noreturn)) run_guest(int lguest_fd) { @@ -1644,7 +1650,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd) err(1, "Resetting break"); } } -/* +/*L:240 * This is the end of the Launcher. The good news: we are over halfway * through! The bad news: the most fiendish part of the code still lies ahead * of us. @@ -1691,8 +1697,8 @@ int main(int argc, char *argv[]) * device receive input from a file descriptor, we keep an fdset * (infds) and the maximum fd number (max_infd) with the head of the * list. We also keep a pointer to the last device. Finally, we keep - * the next interrupt number to hand out (1: remember that 0 is used by - * the timer). */ + * the next interrupt number to use for devices (1: remember that 0 is + * used by the timer). */ FD_ZERO(&devices.infds); devices.max_infd = -1; devices.lastdev = NULL; @@ -1793,8 +1799,8 @@ int main(int argc, char *argv[]) lguest_fd = tell_kernel(pgdir, start); /* We fork off a child process, which wakes the Launcher whenever one - * of the input file descriptors needs attention. Otherwise we would - * run the Guest until it tries to output something. */ + * of the input file descriptors needs attention. We call this the + * Waker, and we'll cover it in a moment. */ waker_fd = setup_waker(lguest_fd); /* Finally, run the Guest. This doesn't return. */ diff --git a/Documentation/lguest/lguest.txt b/Documentation/lguest/lguest.txt index 722d4e7fbebe..29510dc51510 100644 --- a/Documentation/lguest/lguest.txt +++ b/Documentation/lguest/lguest.txt @@ -1,6 +1,7 @@ -Rusty's Remarkably Unreliable Guide to Lguest - - or, A Young Coder's Illustrated Hypervisor -http://lguest.ozlabs.org + __ + (___()'`; Rusty's Remarkably Unreliable Guide to Lguest + /, /` - or, A Young Coder's Illustrated Hypervisor + \\"--\\ http://lguest.ozlabs.org Lguest is designed to be a minimal hypervisor for the Linux kernel, for Linux developers and users to experiment with virtualization with the @@ -41,12 +42,16 @@ Running Lguest: CONFIG_PHYSICAL_ALIGN=0x100000) "Device Drivers": + "Block devices" + "Virtio block driver (EXPERIMENTAL)" = M/Y "Network device support" "Universal TUN/TAP device driver support" = M/Y - (CONFIG_TUN=m) - "Virtualization" - "Linux hypervisor example code" = M/Y - (CONFIG_LGUEST=m) + "Virtio network driver (EXPERIMENTAL)" = M/Y + (CONFIG_VIRTIO_BLK=m, CONFIG_VIRTIO_NET=m and CONFIG_TUN=m) + + "Virtualization" + "Linux hypervisor example code" = M/Y + (CONFIG_LGUEST=m) - A tool called "lguest" is available in this directory: type "make" to build it. If you didn't build your kernel in-tree, use "make diff --git a/MAINTAINERS b/MAINTAINERS index f1ed75cef6a4..90dcbbcad91c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -163,6 +163,12 @@ M: A2232@gmx.net L: linux-m68k@lists.linux-m68k.org S: Maintained +AFS FILESYSTEM & AF_RXRPC SOCKET DOMAIN +P: David Howells +M: dhowells@redhat.com +L: linux-afs@lists.infradead.org +S: Supported + AIO P: Benjamin LaHaise M: bcrl@kvack.org @@ -2314,8 +2320,6 @@ L: kexec@lists.infradead.org S: Maintained KPROBES -P: Prasanna S Panchamukhi -M: prasanna@in.ibm.com P: Ananth N Mavinakayanahalli M: ananth@in.ibm.com P: Anil S Keshavamurthy diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 797f0dfebde2..09f306248f2e 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.24-rc6 -# Tue Jan 15 10:26:10 2008 +# Linux kernel version: 2.6.25-rc6 +# Tue Mar 25 10:25:48 2008 # CONFIG_PPC64=y @@ -27,6 +27,7 @@ CONFIG_GENERIC_TIME=y CONFIG_GENERIC_TIME_VSYSCALL=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_GENERIC_HARDIRQS=y +CONFIG_HAVE_SETUP_PER_CPU_AREA=y CONFIG_IRQ_PER_CPU=y CONFIG_RWSEM_XCHGADD_ALGORITHM=y CONFIG_ARCH_HAS_ILOG2_U32=y @@ -67,17 +68,19 @@ CONFIG_SYSVIPC_SYSCTL=y # CONFIG_POSIX_MQUEUE is not set # CONFIG_BSD_PROCESS_ACCT is not set # CONFIG_TASKSTATS is not set -# CONFIG_USER_NS is not set -# CONFIG_PID_NS is not set # CONFIG_AUDIT is not set # CONFIG_IKCONFIG is not set CONFIG_LOG_BUF_SHIFT=17 # CONFIG_CGROUPS is not set -CONFIG_FAIR_GROUP_SCHED=y -CONFIG_FAIR_USER_SCHED=y -# CONFIG_FAIR_CGROUP_SCHED is not set +# CONFIG_GROUP_SCHED is not set CONFIG_SYSFS_DEPRECATED=y +CONFIG_SYSFS_DEPRECATED_V2=y # CONFIG_RELAY is not set +CONFIG_NAMESPACES=y +# CONFIG_UTS_NS is not set +# CONFIG_IPC_NS is not set +# CONFIG_USER_NS is not set +# CONFIG_PID_NS is not set CONFIG_BLK_DEV_INITRD=y CONFIG_INITRAMFS_SOURCE="" # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set @@ -91,11 +94,13 @@ CONFIG_HOTPLUG=y CONFIG_PRINTK=y CONFIG_BUG=y CONFIG_ELF_CORE=y +CONFIG_COMPAT_BRK=y CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_ANON_INODES=y CONFIG_EPOLL=y CONFIG_SIGNALFD=y +CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_VM_EVENT_COUNTERS=y @@ -103,6 +108,15 @@ CONFIG_SLUB_DEBUG=y # CONFIG_SLAB is not set CONFIG_SLUB=y # CONFIG_SLOB is not set +CONFIG_PROFILING=y +# CONFIG_MARKERS is not set +CONFIG_OPROFILE=y +CONFIG_HAVE_OPROFILE=y +# CONFIG_KPROBES is not set +CONFIG_HAVE_KPROBES=y +CONFIG_HAVE_KRETPROBES=y +CONFIG_PROC_PAGE_MONITOR=y +CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -130,6 +144,7 @@ CONFIG_DEFAULT_AS=y # CONFIG_DEFAULT_CFQ is not set # CONFIG_DEFAULT_NOOP is not set CONFIG_DEFAULT_IOSCHED="anticipatory" +CONFIG_CLASSIC_RCU=y # # Platform support @@ -140,8 +155,8 @@ CONFIG_PPC_MULTIPLATFORM=y # CONFIG_PPC_86xx is not set # CONFIG_PPC_PSERIES is not set # CONFIG_PPC_ISERIES is not set -# CONFIG_PPC_MPC52xx is not set -# CONFIG_PPC_MPC5200 is not set +# CONFIG_PPC_MPC512x is not set +# CONFIG_PPC_MPC5121 is not set # CONFIG_PPC_PMAC is not set # CONFIG_PPC_MAPLE is not set CONFIG_PPC_PASEMI=y @@ -159,6 +174,7 @@ CONFIG_PPC_PASEMI_MDIO=y # CONFIG_PPC_IBM_CELL_BLADE is not set # CONFIG_PQ2ADS is not set CONFIG_PPC_NATIVE=y +# CONFIG_IPIC is not set CONFIG_MPIC=y # CONFIG_MPIC_WEIRD is not set # CONFIG_PPC_I8259 is not set @@ -189,7 +205,6 @@ CONFIG_CPU_FREQ_GOV_ONDEMAND=y # CPU Frequency drivers # CONFIG_PPC_PASEMI_CPUFREQ=y -# CONFIG_CPM2 is not set # CONFIG_FSL_ULI1575 is not set # @@ -204,16 +219,20 @@ CONFIG_GENERIC_CLOCKEVENTS_BUILD=y # CONFIG_HZ_300 is not set CONFIG_HZ_1000=y CONFIG_HZ=1000 +# CONFIG_SCHED_HRTICK is not set CONFIG_PREEMPT_NONE=y # CONFIG_PREEMPT_VOLUNTARY is not set # CONFIG_PREEMPT is not set -# CONFIG_PREEMPT_BKL is not set CONFIG_BINFMT_ELF=y +CONFIG_COMPAT_BINFMT_ELF=y # CONFIG_BINFMT_MISC is not set CONFIG_FORCE_MAX_ZONEORDER=9 CONFIG_HUGETLB_PAGE_SIZE_VARIABLE=y CONFIG_IOMMU_VMERGE=y +CONFIG_IOMMU_HELPER=y CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y +CONFIG_ARCH_HAS_WALK_MEMORY=y +CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y # CONFIG_KEXEC is not set # CONFIG_CRASH_DUMP is not set # CONFIG_IRQ_ALL_CPUS is not set @@ -236,12 +255,12 @@ CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_PPC_HAS_HASH_64K=y CONFIG_PPC_64K_PAGES=y +# CONFIG_PPC_SUBPAGE_PROT is not set # CONFIG_SCHED_SMT is not set CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set # CONFIG_PM is not set # CONFIG_SECCOMP is not set -# CONFIG_WANT_DEVICE_TREE is not set CONFIG_ISA_DMA_API=y # @@ -290,6 +309,7 @@ CONFIG_XFRM=y CONFIG_XFRM_USER=y # CONFIG_XFRM_SUB_POLICY is not set # CONFIG_XFRM_MIGRATE is not set +# CONFIG_XFRM_STATISTICS is not set CONFIG_NET_KEY=y # CONFIG_NET_KEY_MIGRATE is not set CONFIG_INET=y @@ -346,6 +366,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # # CONFIG_NET_PKTGEN is not set # CONFIG_HAMRADIO is not set +# CONFIG_CAN is not set # CONFIG_IRDA is not set # CONFIG_BT is not set # CONFIG_AF_RXRPC is not set @@ -441,8 +462,10 @@ CONFIG_MTD_NAND=y CONFIG_MTD_NAND_IDS=y # CONFIG_MTD_NAND_DISKONCHIP is not set # CONFIG_MTD_NAND_CAFE is not set +CONFIG_MTD_NAND_PASEMI=y # CONFIG_MTD_NAND_PLATFORM is not set # CONFIG_MTD_ALAUDA is not set +# CONFIG_MTD_NAND_FSL_ELBC is not set # CONFIG_MTD_ONENAND is not set # @@ -465,7 +488,7 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=16 CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024 +# CONFIG_BLK_DEV_XIP is not set # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set CONFIG_MISC_DEVICES=y @@ -473,11 +496,13 @@ CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ENCLOSURE_SERVICES is not set +CONFIG_HAVE_IDE=y CONFIG_IDE=y CONFIG_BLK_DEV_IDE=y # -# Please see Documentation/ide.txt for help/info on IDE drives +# Please see Documentation/ide/ide.txt for help/info on IDE drives # # CONFIG_BLK_DEV_IDE_SATA is not set CONFIG_BLK_DEV_IDEDISK=y @@ -485,6 +510,7 @@ CONFIG_IDEDISK_MULTI_MODE=y # CONFIG_BLK_DEV_IDECS is not set # CONFIG_BLK_DEV_DELKIN is not set CONFIG_BLK_DEV_IDECD=y +CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y # CONFIG_BLK_DEV_IDETAPE is not set # CONFIG_BLK_DEV_IDEFLOPPY is not set CONFIG_BLK_DEV_IDESCSI=y @@ -500,7 +526,6 @@ CONFIG_IDE_PROC_FS=y # # PCI IDE chipsets support # -# CONFIG_IDEPCI_PCIBUS_ORDER is not set # CONFIG_BLK_DEV_GENERIC is not set # CONFIG_BLK_DEV_OPTI621 is not set # CONFIG_BLK_DEV_AEC62XX is not set @@ -528,7 +553,6 @@ CONFIG_IDE_PROC_FS=y # CONFIG_BLK_DEV_TRM290 is not set # CONFIG_BLK_DEV_VIA82CXXX is not set # CONFIG_BLK_DEV_TC86C001 is not set -# CONFIG_IDE_ARM is not set # CONFIG_BLK_DEV_IDEDMA is not set CONFIG_IDE_ARCH_OBSOLETE_INIT=y # CONFIG_BLK_DEV_HD is not set @@ -593,6 +617,7 @@ CONFIG_SCSI_LOWLEVEL=y # CONFIG_SCSI_IPS is not set # CONFIG_SCSI_INITIO is not set # CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_MVSAS is not set # CONFIG_SCSI_STEX is not set # CONFIG_SCSI_SYM53C8XX_2 is not set # CONFIG_SCSI_IPR is not set @@ -646,6 +671,7 @@ CONFIG_ATA_GENERIC=y # CONFIG_PATA_MPIIX is not set # CONFIG_PATA_OLDPIIX is not set # CONFIG_PATA_NETCELL is not set +# CONFIG_PATA_NINJA32 is not set # CONFIG_PATA_NS87410 is not set # CONFIG_PATA_NS87415 is not set # CONFIG_PATA_OPTI is not set @@ -699,7 +725,6 @@ CONFIG_DUMMY=y # CONFIG_EQUALIZER is not set # CONFIG_TUN is not set # CONFIG_VETH is not set -# CONFIG_IP1000 is not set # CONFIG_ARCNET is not set CONFIG_PHYLIB=y @@ -715,6 +740,7 @@ CONFIG_MARVELL_PHY=y # CONFIG_SMSC_PHY is not set # CONFIG_BROADCOM_PHY is not set # CONFIG_ICPLUS_PHY is not set +# CONFIG_REALTEK_PHY is not set # CONFIG_FIXED_PHY is not set # CONFIG_MDIO_BITBANG is not set CONFIG_NET_ETHERNET=y @@ -742,6 +768,7 @@ CONFIG_NET_PCI=y # CONFIG_NE2K_PCI is not set # CONFIG_8139CP is not set # CONFIG_8139TOO is not set +# CONFIG_R6040 is not set # CONFIG_SIS900 is not set # CONFIG_EPIC100 is not set # CONFIG_SUNDANCE is not set @@ -754,6 +781,9 @@ CONFIG_E1000=y CONFIG_E1000_NAPI=y # CONFIG_E1000_DISABLE_PACKET_SPLIT is not set # CONFIG_E1000E is not set +# CONFIG_E1000E_ENABLED is not set +# CONFIG_IP1000 is not set +# CONFIG_IGB is not set # CONFIG_NS83820 is not set # CONFIG_HAMACHI is not set # CONFIG_YELLOWFIN is not set @@ -779,6 +809,7 @@ CONFIG_NETDEV_10000=y CONFIG_PASEMI_MAC=y # CONFIG_MLX4_CORE is not set # CONFIG_TEHUTI is not set +# CONFIG_BNX2X is not set # CONFIG_TR is not set # @@ -802,7 +833,6 @@ CONFIG_PASEMI_MAC=y # CONFIG_PPP is not set # CONFIG_SLIP is not set # CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set # CONFIG_NETCONSOLE is not set # CONFIG_NETPOLL is not set # CONFIG_NET_POLL_CONTROLLER is not set @@ -861,6 +891,7 @@ CONFIG_VT_CONSOLE=y CONFIG_HW_CONSOLE=y # CONFIG_VT_HW_CONSOLE_BINDING is not set # CONFIG_SERIAL_NONSTANDARD is not set +# CONFIG_NOZOMI is not set # # Serial drivers @@ -886,8 +917,7 @@ CONFIG_LEGACY_PTY_COUNT=4 # CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_PASEMI=y -CONFIG_GEN_RTC=y -CONFIG_GEN_RTC_X=y +# CONFIG_GEN_RTC is not set # CONFIG_R3964 is not set # CONFIG_APPLICOM is not set @@ -897,6 +927,7 @@ CONFIG_GEN_RTC_X=y # CONFIG_SYNCLINK_CS is not set # CONFIG_CARDMAN_4000 is not set # CONFIG_CARDMAN_4040 is not set +# CONFIG_IPWIRELESS is not set CONFIG_RAW_DRIVER=y CONFIG_MAX_RAW_DEVS=256 # CONFIG_HANGCHECK_TIMER is not set @@ -944,13 +975,12 @@ CONFIG_I2C_PASEMI=y # # Miscellaneous I2C Chip support # -# CONFIG_SENSORS_DS1337 is not set -# CONFIG_SENSORS_DS1374 is not set # CONFIG_DS1682 is not set CONFIG_SENSORS_EEPROM=y # CONFIG_SENSORS_PCF8574 is not set -# CONFIG_SENSORS_PCA9539 is not set +# CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCF8591 is not set +# CONFIG_TPS65010 is not set # CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set @@ -975,6 +1005,7 @@ CONFIG_HWMON_VID=y # CONFIG_SENSORS_ADM1031 is not set # CONFIG_SENSORS_ADM9240 is not set # CONFIG_SENSORS_ADT7470 is not set +# CONFIG_SENSORS_ADT7473 is not set # CONFIG_SENSORS_ATXP1 is not set # CONFIG_SENSORS_DS1621 is not set # CONFIG_SENSORS_I5K_AMB is not set @@ -1004,6 +1035,7 @@ CONFIG_SENSORS_LM90=y # CONFIG_SENSORS_SMSC47M1 is not set # CONFIG_SENSORS_SMSC47M192 is not set # CONFIG_SENSORS_SMSC47B397 is not set +# CONFIG_SENSORS_ADS7828 is not set # CONFIG_SENSORS_THMC50 is not set # CONFIG_SENSORS_VIA686A is not set # CONFIG_SENSORS_VT1211 is not set @@ -1013,9 +1045,11 @@ CONFIG_SENSORS_LM90=y # CONFIG_SENSORS_W83792D is not set # CONFIG_SENSORS_W83793 is not set # CONFIG_SENSORS_W83L785TS is not set +# CONFIG_SENSORS_W83L786NG is not set # CONFIG_SENSORS_W83627HF is not set # CONFIG_SENSORS_W83627EHF is not set # CONFIG_HWMON_DEBUG_CHIP is not set +# CONFIG_THERMAL is not set # CONFIG_WATCHDOG is not set # @@ -1183,6 +1217,7 @@ CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_BT87X is not set # CONFIG_SND_CA0106 is not set # CONFIG_SND_CMIPCI is not set +# CONFIG_SND_OXYGEN is not set # CONFIG_SND_CS4281 is not set # CONFIG_SND_CS46XX is not set # CONFIG_SND_CS5530 is not set @@ -1208,6 +1243,7 @@ CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_HDA_INTEL is not set # CONFIG_SND_HDSP is not set # CONFIG_SND_HDSPM is not set +# CONFIG_SND_HIFIER is not set # CONFIG_SND_ICE1712 is not set # CONFIG_SND_ICE1724 is not set # CONFIG_SND_INTEL8X0 is not set @@ -1225,6 +1261,7 @@ CONFIG_SND_VERBOSE_PROCFS=y # CONFIG_SND_TRIDENT is not set # CONFIG_SND_VIA82XX is not set # CONFIG_SND_VIA82XX_MODEM is not set +# CONFIG_SND_VIRTUOSO is not set # CONFIG_SND_VX222 is not set # CONFIG_SND_YMFPCI is not set @@ -1259,6 +1296,10 @@ CONFIG_SND_USB_USX2Y=y # # +# ALSA SoC audio for Freescale SOCs +# + +# # Open Sound System # # CONFIG_SOUND_PRIME is not set @@ -1280,6 +1321,7 @@ CONFIG_USB_ARCH_HAS_OHCI=y CONFIG_USB_ARCH_HAS_EHCI=y CONFIG_USB=y # CONFIG_USB_DEBUG is not set +# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set # # Miscellaneous USB options @@ -1293,17 +1335,14 @@ CONFIG_USB_DEVICEFS=y # USB Host Controller Drivers # CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_SPLIT_ISO is not set # CONFIG_USB_EHCI_ROOT_HUB_TT is not set # CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_EHCI_HCD_PPC_OF=y # CONFIG_USB_ISP116X_HCD is not set CONFIG_USB_OHCI_HCD=y -CONFIG_USB_OHCI_HCD_PPC_OF=y -CONFIG_USB_OHCI_HCD_PPC_OF_BE=y -# CONFIG_USB_OHCI_HCD_PPC_OF_LE is not set -CONFIG_USB_OHCI_HCD_PCI=y -CONFIG_USB_OHCI_BIG_ENDIAN_DESC=y -CONFIG_USB_OHCI_BIG_ENDIAN_MMIO=y +# CONFIG_USB_OHCI_HCD_PPC_OF is not set +# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set +# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set CONFIG_USB_OHCI_LITTLE_ENDIAN=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_SL811_HCD=y @@ -1348,10 +1387,6 @@ CONFIG_USB_LIBUSUAL=y # # USB port drivers # - -# -# USB Serial Converter support -# # CONFIG_USB_SERIAL is not set # @@ -1377,16 +1412,9 @@ CONFIG_USB_LIBUSUAL=y # CONFIG_USB_TRANCEVIBRATOR is not set # CONFIG_USB_IOWARRIOR is not set # CONFIG_USB_TEST is not set - -# -# USB DSL modem support -# - -# -# USB Gadget Support -# # CONFIG_USB_GADGET is not set # CONFIG_MMC is not set +# CONFIG_MEMSTICK is not set # CONFIG_NEW_LEDS is not set # CONFIG_INFINIBAND is not set CONFIG_EDAC=y @@ -1425,6 +1453,7 @@ CONFIG_RTC_DRV_DS1307=y # CONFIG_RTC_DRV_PCF8563 is not set # CONFIG_RTC_DRV_PCF8583 is not set # CONFIG_RTC_DRV_M41T80 is not set +# CONFIG_RTC_DRV_S35390A is not set # # SPI RTC drivers @@ -1434,9 +1463,10 @@ CONFIG_RTC_DRV_DS1307=y # Platform RTC drivers # # CONFIG_RTC_DRV_CMOS is not set +# CONFIG_RTC_DRV_DS1511 is not set # CONFIG_RTC_DRV_DS1553 is not set -# CONFIG_RTC_DRV_STK17TA8 is not set # CONFIG_RTC_DRV_DS1742 is not set +# CONFIG_RTC_DRV_STK17TA8 is not set # CONFIG_RTC_DRV_M48T86 is not set # CONFIG_RTC_DRV_M48T59 is not set # CONFIG_RTC_DRV_V3020 is not set @@ -1444,6 +1474,7 @@ CONFIG_RTC_DRV_DS1307=y # # on-CPU RTC drivers # +# CONFIG_DMADEVICES is not set # # Userspace I/O @@ -1471,12 +1502,10 @@ CONFIG_FS_POSIX_ACL=y # CONFIG_XFS_FS is not set # CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set +CONFIG_DNOTIFY=y CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y # CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y CONFIG_AUTOFS_FS=y CONFIG_AUTOFS4_FS=y # CONFIG_FUSE_FS is not set @@ -1536,8 +1565,10 @@ CONFIG_JFFS2_RTIME=y # CONFIG_JFFS2_RUBIN is not set # CONFIG_CRAMFS is not set # CONFIG_VXFS_FS is not set +# CONFIG_MINIX_FS is not set # CONFIG_HPFS_FS is not set # CONFIG_QNX4FS_FS is not set +# CONFIG_ROMFS_FS is not set # CONFIG_SYSV_FS is not set # CONFIG_UFS_FS is not set CONFIG_NETWORK_FILESYSTEMS=y @@ -1629,7 +1660,6 @@ CONFIG_NLS_ISO8859_1=y # CONFIG_NLS_KOI8_U is not set # CONFIG_NLS_UTF8 is not set # CONFIG_DLM is not set -# CONFIG_UCC_SLOW is not set # # Library routines @@ -1647,11 +1677,6 @@ CONFIG_PLIST=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y -CONFIG_INSTRUMENTATION=y -CONFIG_PROFILING=y -CONFIG_OPROFILE=y -# CONFIG_KPROBES is not set -# CONFIG_MARKERS is not set # # Kernel hacking @@ -1670,6 +1695,7 @@ CONFIG_DETECT_SOFTLOCKUP=y # CONFIG_SCHEDSTATS is not set # CONFIG_TIMER_STATS is not set # CONFIG_SLUB_DEBUG_ON is not set +# CONFIG_SLUB_STATS is not set # CONFIG_DEBUG_RT_MUTEXES is not set # CONFIG_RT_MUTEX_TESTER is not set # CONFIG_DEBUG_SPINLOCK is not set @@ -1682,9 +1708,9 @@ CONFIG_DEBUG_BUGVERBOSE=y # CONFIG_DEBUG_VM is not set # CONFIG_DEBUG_LIST is not set # CONFIG_DEBUG_SG is not set -# CONFIG_FORCED_INLINING is not set # CONFIG_BOOT_PRINTK_DELAY is not set # CONFIG_RCU_TORTURE_TEST is not set +# CONFIG_BACKTRACE_SELF_TEST is not set # CONFIG_FAULT_INJECTION is not set # CONFIG_SAMPLES is not set # CONFIG_DEBUG_STACKOVERFLOW is not set @@ -1710,7 +1736,9 @@ CONFIG_ASYNC_MEMCPY=y CONFIG_ASYNC_XOR=y CONFIG_CRYPTO=y CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_AEAD=y CONFIG_CRYPTO_BLKCIPHER=y +# CONFIG_CRYPTO_SEQIV is not set CONFIG_CRYPTO_HASH=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_HMAC=y @@ -1729,6 +1757,9 @@ CONFIG_CRYPTO_CBC=y # CONFIG_CRYPTO_PCBC is not set # CONFIG_CRYPTO_LRW is not set # CONFIG_CRYPTO_XTS is not set +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_CCM is not set # CONFIG_CRYPTO_CRYPTD is not set CONFIG_CRYPTO_DES=y # CONFIG_CRYPTO_FCRYPT is not set @@ -1743,11 +1774,14 @@ CONFIG_CRYPTO_AES=y # CONFIG_CRYPTO_KHAZAD is not set # CONFIG_CRYPTO_ANUBIS is not set # CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SALSA20 is not set # CONFIG_CRYPTO_DEFLATE is not set # CONFIG_CRYPTO_MICHAEL_MIC is not set # CONFIG_CRYPTO_CRC32C is not set # CONFIG_CRYPTO_CAMELLIA is not set # CONFIG_CRYPTO_TEST is not set -# CONFIG_CRYPTO_AUTHENC is not set +CONFIG_CRYPTO_AUTHENC=y +# CONFIG_CRYPTO_LZO is not set CONFIG_CRYPTO_HW=y +# CONFIG_CRYPTO_DEV_HIFN_795X is not set # CONFIG_PPC_CLOCK is not set diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 59311ec0d422..4ec605521504 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -241,8 +241,12 @@ void discard_lazy_cpu_state(void) } #endif /* CONFIG_SMP */ +static DEFINE_PER_CPU(unsigned long, current_dabr); + int set_dabr(unsigned long dabr) { + __get_cpu_var(current_dabr) = dabr; + #ifdef CONFIG_PPC_MERGE /* XXX for now */ if (ppc_md.set_dabr) return ppc_md.set_dabr(dabr); @@ -259,8 +263,6 @@ int set_dabr(unsigned long dabr) DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array); #endif -static DEFINE_PER_CPU(unsigned long, current_dabr); - struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { @@ -325,10 +327,8 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_SMP */ - if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) { + if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) set_dabr(new->thread.dabr); - __get_cpu_var(current_dabr) = new->thread.dabr; - } new_thread = &new->thread; old_thread = ¤t->thread; diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a104c532ff70..3335b4595efd 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -10,21 +10,19 @@ * (such as the example in Documentation/lguest/lguest.c) is called the * Launcher. * - * Secondly, we only run specially modified Guests, not normal kernels. When - * you set CONFIG_LGUEST to 'y' or 'm', this automatically sets - * CONFIG_LGUEST_GUEST=y, which compiles this file into the kernel so it knows - * how to be a Guest. This means that you can use the same kernel you boot - * normally (ie. as a Host) as a Guest. + * Secondly, we only run specially modified Guests, not normal kernels: setting + * CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows + * how to be a Guest at boot time. This means that you can use the same kernel + * you boot normally (ie. as a Host) as a Guest. * * These Guests know that they cannot do privileged operations, such as disable * interrupts, and that they have to ask the Host to do such things explicitly. * This file consists of all the replacements for such low-level native * hardware operations: these special Guest versions call the Host. * - * So how does the kernel know it's a Guest? The Guest starts at a special - * entry point marked with a magic string, which sets up a few things then - * calls here. We replace the native functions various "paravirt" structures - * with our Guest versions, then boot like normal. :*/ + * So how does the kernel know it's a Guest? We'll see that later, but let's + * just say that we end up here where we replace the native functions various + * "paravirt" structures with our Guest versions, then boot like normal. :*/ /* * Copyright (C) 2006, Rusty Russell <rusty@rustcorp.com.au> IBM Corporation. @@ -134,7 +132,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, * lguest_leave_lazy_mode(). * * So, when we're in lazy mode, we call async_hcall() to store the call for - * future processing. */ + * future processing: */ static void lazy_hcall(unsigned long call, unsigned long arg1, unsigned long arg2, @@ -147,7 +145,7 @@ static void lazy_hcall(unsigned long call, } /* When lazy mode is turned off reset the per-cpu lazy mode variable and then - * issue a hypercall to flush any stored calls. */ + * issue the do-nothing hypercall to flush any stored calls. */ static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); @@ -164,7 +162,7 @@ static void lguest_leave_lazy_mode(void) * * So instead we keep an "irq_enabled" field inside our "struct lguest_data", * which the Guest can update with a single instruction. The Host knows to - * check there when it wants to deliver an interrupt. + * check there before it tries to deliver an interrupt. */ /* save_flags() is expected to return the processor state (ie. "flags"). The @@ -196,10 +194,15 @@ static void irq_enable(void) /*M:003 Note that we don't check for outstanding interrupts when we re-enable * them (or when we unmask an interrupt). This seems to work for the moment, * since interrupts are rare and we'll just get the interrupt on the next timer - * tick, but when we turn on CONFIG_NO_HZ, we should revisit this. One way + * tick, but now we can run with CONFIG_NO_HZ, we should revisit this. One way * would be to put the "irq_enabled" field in a page by itself, and have the * Host write-protect it when an interrupt comes in when irqs are disabled. - * There will then be a page fault as soon as interrupts are re-enabled. :*/ + * There will then be a page fault as soon as interrupts are re-enabled. + * + * A better method is to implement soft interrupt disable generally for x86: + * instead of disabling interrupts, we set a flag. If an interrupt does come + * in, we then disable them for real. This is uncommon, so we could simply use + * a hypercall for interrupt control and not worry about efficiency. :*/ /*G:034 * The Interrupt Descriptor Table (IDT). @@ -212,6 +215,10 @@ static void irq_enable(void) static void lguest_write_idt_entry(gate_desc *dt, int entrynum, const gate_desc *g) { + /* The gate_desc structure is 8 bytes long: we hand it to the Host in + * two 32-bit chunks. The whole 32-bit kernel used to hand descriptors + * around like this; typesafety wasn't a big concern in Linux's early + * years. */ u32 *desc = (u32 *)g; /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); @@ -243,7 +250,8 @@ static void lguest_load_idt(const struct desc_ptr *desc) * * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? + * really matters, but wouldn't it be nice if they were the same? Wouldn't + * it be even better if you were the one to send the patch to fix it? */ static void lguest_load_gdt(const struct desc_ptr *desc) { @@ -298,9 +306,9 @@ static void lguest_load_tr_desc(void) /* The "cpuid" instruction is a way of querying both the CPU identity * (manufacturer, model, etc) and its features. It was introduced before the - * Pentium in 1993 and keeps getting extended by both Intel and AMD. As you - * might imagine, after a decade and a half this treatment, it is now a giant - * ball of hair. Its entry in the current Intel manual runs to 28 pages. + * Pentium in 1993 and keeps getting extended by both Intel, AMD and others. + * As you might imagine, after a decade and a half this treatment, it is now a + * giant ball of hair. Its entry in the current Intel manual runs to 28 pages. * * This instruction even it has its own Wikipedia entry. The Wikipedia entry * has been translated into 4 languages. I am not making this up! @@ -594,17 +602,17 @@ static unsigned long lguest_get_wallclock(void) return lguest_data.time.tv_sec; } -/* The TSC is a Time Stamp Counter. The Host tells us what speed it runs at, - * or 0 if it's unusable as a reliable clock source. This matches what we want - * here: if we return 0 from this function, the x86 TSC clock will not register - * itself. */ +/* The TSC is an Intel thing called the Time Stamp Counter. The Host tells us + * what speed it runs at, or 0 if it's unusable as a reliable clock source. + * This matches what we want here: if we return 0 from this function, the x86 + * TSC clock will give up and not register itself. */ static unsigned long lguest_cpu_khz(void) { return lguest_data.tsc_khz; } -/* If we can't use the TSC, the kernel falls back to our "lguest_clock", where - * we read the time value given to us by the Host. */ +/* If we can't use the TSC, the kernel falls back to our lower-priority + * "lguest_clock", where we read the time value given to us by the Host. */ static cycle_t lguest_clock_read(void) { unsigned long sec, nsec; @@ -648,12 +656,16 @@ static struct clocksource lguest_clock = { static int lguest_clockevent_set_next_event(unsigned long delta, struct clock_event_device *evt) { + /* FIXME: I don't think this can ever happen, but James tells me he had + * to put this code in. Maybe we should remove it now. Anyone? */ if (delta < LG_CLOCK_MIN_DELTA) { if (printk_ratelimit()) printk(KERN_DEBUG "%s: small delta %lu ns\n", __FUNCTION__, delta); return -ETIME; } + + /* Please wake us this far in the future. */ hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); return 0; } @@ -738,7 +750,7 @@ static void lguest_time_init(void) * will not tolerate us trying to use that), the stack pointer, and the number * of pages in the stack. */ static void lguest_load_sp0(struct tss_struct *tss, - struct thread_struct *thread) + struct thread_struct *thread) { lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, THREAD_SIZE/PAGE_SIZE); @@ -786,9 +798,8 @@ static void lguest_safe_halt(void) hcall(LHCALL_HALT, 0, 0, 0); } -/* Perhaps CRASH isn't the best name for this hypercall, but we use it to get a - * message out when we're crashing as well as elegant termination like powering - * off. +/* The SHUTDOWN hypercall takes a string to describe what's happening, and + * an argument which says whether this to restart (reboot) the Guest or not. * * Note that the Host always prefers that the Guest speak in physical addresses * rather than virtual addresses, so we use __pa() here. */ @@ -816,8 +827,9 @@ static struct notifier_block paniced = { /* Setting up memory is fairly easy. */ static __init char *lguest_memory_setup(void) { - /* We do this here and not earlier because lockcheck barfs if we do it - * before start_kernel() */ + /* We do this here and not earlier because lockcheck used to barf if we + * did it before start_kernel(). I think we fixed that, so it'd be + * nice to move it back to lguest_init. Patch welcome... */ atomic_notifier_chain_register(&panic_notifier_list, &paniced); /* The Linux bootloader header contains an "e820" memory map: the @@ -850,12 +862,19 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) return len; } +/* Rebooting also tells the Host we're finished, but the RESTART flag tells the + * Launcher to reboot us. */ +static void lguest_restart(char *reason) +{ + hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); +} + /*G:050 * Patching (Powerfully Placating Performance Pedants) * - * We have already seen that pv_ops structures let us replace simple - * native instructions with calls to the appropriate back end all throughout - * the kernel. This allows the same kernel to run as a Guest and as a native + * We have already seen that pv_ops structures let us replace simple native + * instructions with calls to the appropriate back end all throughout the + * kernel. This allows the same kernel to run as a Guest and as a native * kernel, but it's slow because of all the indirect branches. * * Remember that David Wheeler quote about "Any problem in computer science can @@ -908,14 +927,9 @@ static unsigned lguest_patch(u8 type, u16 clobber, void *ibuf, return insn_len; } -static void lguest_restart(char *reason) -{ - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); -} - -/*G:030 Once we get to lguest_init(), we know we're a Guest. The pv_ops - * structures in the kernel provide points for (almost) every routine we have - * to override to avoid privileged instructions. */ +/*G:030 Once we get to lguest_init(), we know we're a Guest. The various + * pv_ops structures in the kernel provide points for (almost) every routine we + * have to override to avoid privileged instructions. */ __init void lguest_init(void) { /* We're under lguest, paravirt is enabled, and we're running at @@ -1003,9 +1017,9 @@ __init void lguest_init(void) * the normal data segment to get through booting. */ asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory"); - /* The Host uses the top of the Guest's virtual address space for the - * Host<->Guest Switcher, and it tells us how big that is in - * lguest_data.reserve_mem, set up on the LGUEST_INIT hypercall. */ + /* The Host<->Guest Switcher lives at the top of our address space, and + * the Host told us how big it is when we made LGUEST_INIT hypercall: + * it put the answer in lguest_data.reserve_mem */ reserve_top_address(lguest_data.reserve_mem); /* If we don't initialize the lock dependency checker now, it crashes @@ -1027,6 +1041,7 @@ __init void lguest_init(void) /* Math is always hard! */ new_cpu_data.hard_math = 1; + /* We don't have features. We have puppies! Puppies! */ #ifdef CONFIG_X86_MCE mce_disabled = 1; #endif @@ -1044,10 +1059,11 @@ __init void lguest_init(void) virtio_cons_early_init(early_put_chars); /* Last of all, we set the power management poweroff hook to point to - * the Guest routine to power off. */ + * the Guest routine to power off, and the reboot hook to our restart + * routine. */ pm_power_off = lguest_power_off; - machine_ops.restart = lguest_restart; + /* Now we're set up, call start_kernel() in init/main.c and we proceed * to boot as normal. It never returns. */ start_kernel(); diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 95b6fbcded63..5c7cef34c9e7 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -5,13 +5,20 @@ #include <asm/thread_info.h> #include <asm/processor-flags.h> -/*G:020 This is where we begin: head.S notes that the boot header's platform - * type field is "1" (lguest), so calls us here. +/*G:020 Our story starts with the kernel booting into startup_32 in + * arch/x86/kernel/head_32.S. It expects a boot header, which is created by + * the bootloader (the Launcher in our case). + * + * The startup_32 function does very little: it clears the uninitialized global + * C variables which we expect to be zero (ie. BSS) and then copies the boot + * header and kernel command line somewhere safe. Finally it checks the + * 'hardware_subarch' field. This was introduced in 2.6.24 for lguest and Xen: + * if it's set to '1' (lguest's assigned number), then it calls us here. * * WARNING: be very careful here! We're running at addresses equal to physical * addesses (around 0), not above PAGE_OFFSET as most code expectes * (eg. 0xC0000000). Jumps are relative, so they're OK, but we can't touch any - * data. + * data without remembering to subtract __PAGE_OFFSET! * * The .section line puts this code in .init.text so it will be discarded after * boot. */ @@ -24,7 +31,7 @@ ENTRY(lguest_entry) int $LGUEST_TRAP_ENTRY /* The Host put the toplevel pagetable in lguest_data.pgdir. The movsl - * instruction uses %esi implicitly as the source for the copy we' + * instruction uses %esi implicitly as the source for the copy we're * about to do. */ movl lguest_data - __PAGE_OFFSET + LGUEST_DATA_pgdir, %esi diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 3d936f232704..9cf33d3ee5bc 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -73,15 +73,15 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) { enum fixed_addresses idx; unsigned long vaddr; - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ - - debug_kmap_atomic_prot(type); + /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ pagefault_disable(); if (!PageHighMem(page)) return page_address(page); + debug_kmap_atomic_prot(type); + idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); BUG_ON(!pte_none(*(kmap_pte-idx))); diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 4d535c50d821..c8e3cba423ef 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -260,22 +260,24 @@ static int acpi_fan_add(struct acpi_device *device) result = PTR_ERR(cdev); goto end; } - printk(KERN_INFO PREFIX - "%s is registered as cooling_device%d\n", - device->dev.bus_id, cdev->id); - - acpi_driver_data(device) = cdev; - result = sysfs_create_link(&device->dev.kobj, - &cdev->device.kobj, - "thermal_cooling"); - if (result) - return result; - - result = sysfs_create_link(&cdev->device.kobj, - &device->dev.kobj, - "device"); - if (result) - return result; + if (cdev) { + printk(KERN_INFO PREFIX + "%s is registered as cooling_device%d\n", + device->dev.bus_id, cdev->id); + + acpi_driver_data(device) = cdev; + result = sysfs_create_link(&device->dev.kobj, + &cdev->device.kobj, + "thermal_cooling"); + if (result) + return result; + + result = sysfs_create_link(&cdev->device.kobj, + &device->dev.kobj, + "device"); + if (result) + return result; + } result = acpi_fan_add_fs(device); if (result) diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c index 3a136f6c66a3..36a68fa114e3 100644 --- a/drivers/acpi/processor_core.c +++ b/drivers/acpi/processor_core.c @@ -674,20 +674,22 @@ static int __cpuinit acpi_processor_start(struct acpi_device *device) result = PTR_ERR(pr->cdev); goto end; } - printk(KERN_INFO PREFIX - "%s is registered as cooling_device%d\n", - device->dev.bus_id, pr->cdev->id); - - result = sysfs_create_link(&device->dev.kobj, - &pr->cdev->device.kobj, - "thermal_cooling"); - if (result) - return result; - result = sysfs_create_link(&pr->cdev->device.kobj, - &device->dev.kobj, - "device"); - if (result) - return result; + if (pr->cdev) { + printk(KERN_INFO PREFIX + "%s is registered as cooling_device%d\n", + device->dev.bus_id, pr->cdev->id); + + result = sysfs_create_link(&device->dev.kobj, + &pr->cdev->device.kobj, + "thermal_cooling"); + if (result) + return result; + result = sysfs_create_link(&pr->cdev->device.kobj, + &device->dev.kobj, + "device"); + if (result) + return result; + } if (pr->flags.throttling) { printk(KERN_INFO PREFIX "%s [%s] (supports", diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index fe09b57de617..12fb44f16766 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -734,19 +734,21 @@ static void acpi_video_device_find_cap(struct acpi_video_device *device) if (IS_ERR(device->cdev)) return; - printk(KERN_INFO PREFIX - "%s is registered as cooling_device%d\n", - device->dev->dev.bus_id, device->cdev->id); - result = sysfs_create_link(&device->dev->dev.kobj, - &device->cdev->device.kobj, - "thermal_cooling"); - if (result) - printk(KERN_ERR PREFIX "Create sysfs link\n"); - result = sysfs_create_link(&device->cdev->device.kobj, - &device->dev->dev.kobj, - "device"); - if (result) - printk(KERN_ERR PREFIX "Create sysfs link\n"); + if (device->cdev) { + printk(KERN_INFO PREFIX + "%s is registered as cooling_device%d\n", + device->dev->dev.bus_id, device->cdev->id); + result = sysfs_create_link(&device->dev->dev.kobj, + &device->cdev->device.kobj, + "thermal_cooling"); + if (result) + printk(KERN_ERR PREFIX "Create sysfs link\n"); + result = sysfs_create_link(&device->cdev->device.kobj, + &device->dev->dev.kobj, + "device"); + if (result) + printk(KERN_ERR PREFIX "Create sysfs link\n"); + } } if (device->cap._DCS && device->cap._DSS){ static int count = 0; diff --git a/drivers/base/driver.c b/drivers/base/driver.c index bf31a0170a48..9a6537f14401 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -133,6 +133,7 @@ int driver_add_kobj(struct device_driver *drv, struct kobject *kobj, { va_list args; char *name; + int ret; va_start(args, fmt); name = kvasprintf(GFP_KERNEL, fmt, args); @@ -141,7 +142,9 @@ int driver_add_kobj(struct device_driver *drv, struct kobject *kobj, if (!name) return -ENOMEM; - return kobject_add(kobj, &drv->p->kobj, "%s", name); + ret = kobject_add(kobj, &drv->p->kobj, "%s", name); + kfree(name); + return ret; } EXPORT_SYMBOL_GPL(driver_add_kobj); diff --git a/drivers/char/drm/ati_pcigart.c b/drivers/char/drm/ati_pcigart.c index e5a0e97cfdda..35d25d821c38 100644 --- a/drivers/char/drm/ati_pcigart.c +++ b/drivers/char/drm/ati_pcigart.c @@ -122,8 +122,9 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga } else { address = gart_info->addr; bus_address = gart_info->bus_addr; - DRM_DEBUG("PCI: Gart Table: VRAM %08X mapped at %08lX\n", - bus_address, (unsigned long)address); + DRM_DEBUG("PCI: Gart Table: VRAM %08LX mapped at %08lX\n", + (unsigned long long)bus_address, + (unsigned long)address); } pci_gart = (u32 *) address; diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index 320f2b6ddee6..99f2f2a46bf7 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -1745,7 +1745,7 @@ int iwch_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) /* bind QP to EP and move to RTS */ attrs.mpa_attr = ep->mpa_attr; - attrs.max_ird = ep->ord; + attrs.max_ird = ep->ird; attrs.max_ord = ep->ord; attrs.llp_stream_handle = ep; attrs.next_state = IWCH_QP_STATE_RTS; diff --git a/drivers/input/misc/ixp4xx-beeper.c b/drivers/input/misc/ixp4xx-beeper.c index d2ade7443b7d..798d84c44d03 100644 --- a/drivers/input/misc/ixp4xx-beeper.c +++ b/drivers/input/misc/ixp4xx-beeper.c @@ -25,6 +25,7 @@ MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>"); MODULE_DESCRIPTION("ixp4xx beeper driver"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:ixp4xx-beeper"); static DEFINE_SPINLOCK(beep_lock); diff --git a/drivers/lguest/Makefile b/drivers/lguest/Makefile index 5e8272d296d8..7d463c26124f 100644 --- a/drivers/lguest/Makefile +++ b/drivers/lguest/Makefile @@ -19,3 +19,11 @@ Beer: @for f in Preparation Guest Drivers Launcher Host Switcher Mastery; do echo "{==- $$f -==}"; make -s $$f; done; echo "{==-==}" Preparation Preparation! Guest Drivers Launcher Host Switcher Mastery: @sh ../../Documentation/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'` +Puppy: + @clear + @printf " __ \n (___()'\`;\n /, /\`\n \\\\\\\"--\\\\\\ \n" + @sleep 2; clear; printf "\n\n Sit!\n\n"; sleep 1; clear + @printf " __ \n ()'\`; \n /\\|\` \n / | \n(/_)_|_ \n" + @sleep 2; clear; printf "\n\n Stand!\n\n"; sleep 1; clear + @printf " __ \n ()'\`; \n /\\|\` \n /._.= \n /| / \n(_\_)_ \n" + @sleep 2; clear; printf "\n\n Good puppy!\n\n"; sleep 1; clear diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index c632c08cbbdc..5eea4356d703 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -1,8 +1,6 @@ /*P:400 This contains run_guest() which actually calls into the Host<->Guest * Switcher and analyzes the return, such as determining if the Guest wants the - * Host to do something. This file also contains useful helper routines, and a - * couple of non-obvious setup and teardown pieces which were implemented after - * days of debugging pain. :*/ + * Host to do something. This file also contains useful helper routines. :*/ #include <linux/module.h> #include <linux/stringify.h> #include <linux/stddef.h> @@ -49,8 +47,8 @@ static __init int map_switcher(void) * easy. */ - /* We allocate an array of "struct page"s. map_vm_area() wants the - * pages in this form, rather than just an array of pointers. */ + /* We allocate an array of struct page pointers. map_vm_area() wants + * this, rather than just an array of pages. */ switcher_page = kmalloc(sizeof(switcher_page[0])*TOTAL_SWITCHER_PAGES, GFP_KERNEL); if (!switcher_page) { @@ -172,7 +170,7 @@ void __lgread(struct lg_cpu *cpu, void *b, unsigned long addr, unsigned bytes) } } -/* This is the write (copy into guest) version. */ +/* This is the write (copy into Guest) version. */ void __lgwrite(struct lg_cpu *cpu, unsigned long addr, const void *b, unsigned bytes) { @@ -209,9 +207,9 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user) if (cpu->break_out) return -EAGAIN; - /* Check if there are any interrupts which can be delivered - * now: if so, this sets up the hander to be executed when we - * next run the Guest. */ + /* Check if there are any interrupts which can be delivered now: + * if so, this sets up the hander to be executed when we next + * run the Guest. */ maybe_do_interrupt(cpu); /* All long-lived kernel loops need to check with this horrible @@ -246,8 +244,10 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user) lguest_arch_handle_trap(cpu); } + /* Special case: Guest is 'dead' but wants a reboot. */ if (cpu->lg->dead == ERR_PTR(-ERESTART)) return -ERESTART; + /* The Guest is dead => "No such file or directory" */ return -ENOENT; } diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c index 0f2cb4fd7c69..54d66f05fefa 100644 --- a/drivers/lguest/hypercalls.c +++ b/drivers/lguest/hypercalls.c @@ -29,7 +29,7 @@ #include "lg.h" /*H:120 This is the core hypercall routine: where the Guest gets what it wants. - * Or gets killed. Or, in the case of LHCALL_CRASH, both. */ + * Or gets killed. Or, in the case of LHCALL_SHUTDOWN, both. */ static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args) { switch (args->arg0) { @@ -190,6 +190,13 @@ static void initialize(struct lg_cpu *cpu) * pagetable. */ guest_pagetable_clear_all(cpu); } +/*:*/ + +/*M:013 If a Guest reads from a page (so creates a mapping) that it has never + * written to, and then the Launcher writes to it (ie. the output of a virtual + * device), the Guest will still see the old page. In practice, this never + * happens: why would the Guest read a page which it has never written to? But + * a similar scenario might one day bite us, so it's worth mentioning. :*/ /*H:100 * Hypercalls @@ -227,7 +234,7 @@ void do_hypercalls(struct lg_cpu *cpu) * However, if we are signalled or the Guest sends I/O to the * Launcher, the run_guest() loop will exit without running the * Guest. When it comes back it would try to re-run the - * hypercall. */ + * hypercall. Finding that bug sucked. */ cpu->hcall = NULL; } } diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 32e97c1858e5..0414ddf87587 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -144,7 +144,6 @@ void maybe_do_interrupt(struct lg_cpu *cpu) if (copy_from_user(&blk, cpu->lg->lguest_data->blocked_interrupts, sizeof(blk))) return; - bitmap_andnot(blk, cpu->irqs_pending, blk, LGUEST_IRQS); /* Find the first interrupt. */ @@ -237,9 +236,9 @@ void free_interrupts(void) clear_bit(syscall_vector, used_vectors); } -/*H:220 Now we've got the routines to deliver interrupts, delivering traps - * like page fault is easy. The only trick is that Intel decided that some - * traps should have error codes: */ +/*H:220 Now we've got the routines to deliver interrupts, delivering traps like + * page fault is easy. The only trick is that Intel decided that some traps + * should have error codes: */ static int has_err(unsigned int trap) { return (trap == 8 || (trap >= 10 && trap <= 14) || trap == 17); diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 1b2ec0bf5eb1..2bc9bf7e88e5 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -1,10 +1,10 @@ /*P:050 Lguest guests use a very simple method to describe devices. It's a - * series of device descriptors contained just above the top of normal + * series of device descriptors contained just above the top of normal Guest * memory. * * We use the standard "virtio" device infrastructure, which provides us with a * console, a network and a block driver. Each one expects some configuration - * information and a "virtqueue" mechanism to send and receive data. :*/ + * information and a "virtqueue" or two to send and receive data. :*/ #include <linux/init.h> #include <linux/bootmem.h> #include <linux/lguest_launcher.h> @@ -53,7 +53,7 @@ struct lguest_device { * Device configurations * * The configuration information for a device consists of one or more - * virtqueues, a feature bitmaks, and some configuration bytes. The + * virtqueues, a feature bitmap, and some configuration bytes. The * configuration bytes don't really matter to us: the Launcher sets them up, and * the driver will look at them during setup. * @@ -179,7 +179,7 @@ struct lguest_vq_info }; /* When the virtio_ring code wants to prod the Host, it calls us here and we - * make a hypercall. We hand the page number of the virtqueue so the Host + * make a hypercall. We hand the physical address of the virtqueue so the Host * knows which virtqueue we're talking about. */ static void lg_notify(struct virtqueue *vq) { @@ -199,7 +199,8 @@ static void lg_notify(struct virtqueue *vq) * allocate its own pages and tell the Host where they are, but for lguest it's * simpler for the Host to simply tell us where the pages are. * - * So we provide devices with a "find virtqueue and set it up" function. */ + * So we provide drivers with a "find the Nth virtqueue and set it up" + * function. */ static struct virtqueue *lg_find_vq(struct virtio_device *vdev, unsigned index, void (*callback)(struct virtqueue *vq)) diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 2221485b0773..564e425d71dd 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -73,7 +73,7 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) if (current != cpu->tsk) return -EPERM; - /* If the guest is already dead, we indicate why */ + /* If the Guest is already dead, we indicate why */ if (lg->dead) { size_t len; @@ -88,7 +88,7 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) return len; } - /* If we returned from read() last time because the Guest notified, + /* If we returned from read() last time because the Guest sent I/O, * clear the flag. */ if (cpu->pending_notify) cpu->pending_notify = 0; @@ -97,14 +97,20 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) return run_guest(cpu, (unsigned long __user *)user); } +/*L:025 This actually initializes a CPU. For the moment, a Guest is only + * uniprocessor, so "id" is always 0. */ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip) { + /* We have a limited number the number of CPUs in the lguest struct. */ if (id >= NR_CPUS) return -EINVAL; + /* Set up this CPU's id, and pointer back to the lguest struct. */ cpu->id = id; cpu->lg = container_of((cpu - id), struct lguest, cpus[0]); cpu->lg->nr_cpus++; + + /* Each CPU has a timer it can set. */ init_clockdev(cpu); /* We need a complete page for the Guest registers: they are accessible @@ -120,11 +126,11 @@ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip) * address. */ lguest_arch_setup_regs(cpu, start_ip); - /* Initialize the queue for the waker to wait on */ + /* Initialize the queue for the Waker to wait on */ init_waitqueue_head(&cpu->break_wq); /* We keep a pointer to the Launcher task (ie. current task) for when - * other Guests want to wake this one (inter-Guest I/O). */ + * other Guests want to wake this one (eg. console input). */ cpu->tsk = current; /* We need to keep a pointer to the Launcher's memory map, because if @@ -136,6 +142,7 @@ static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip) * when the same Guest runs on the same CPU twice. */ cpu->last_pages = NULL; + /* No error == success. */ return 0; } @@ -185,14 +192,13 @@ static int initialize(struct file *file, const unsigned long __user *input) lg->mem_base = (void __user *)(long)args[0]; lg->pfn_limit = args[1]; - /* This is the first cpu */ + /* This is the first cpu (cpu 0) and it will start booting at args[3] */ err = lg_cpu_start(&lg->cpus[0], 0, args[3]); if (err) goto release_guest; /* Initialize the Guest's shadow page tables, using the toplevel - * address the Launcher gave us. This allocates memory, so can - * fail. */ + * address the Launcher gave us. This allocates memory, so can fail. */ err = init_guest_pagetable(lg, args[2]); if (err) goto free_regs; @@ -218,11 +224,16 @@ unlock: /*L:010 The first operation the Launcher does must be a write. All writes * start with an unsigned long number: for the first write this must be * LHREQ_INITIALIZE to set up the Guest. After that the Launcher can use - * writes of other values to send interrupts. */ + * writes of other values to send interrupts. + * + * Note that we overload the "offset" in the /dev/lguest file to indicate what + * CPU number we're dealing with. Currently this is always 0, since we only + * support uniprocessor Guests, but you can see the beginnings of SMP support + * here. */ static ssize_t write(struct file *file, const char __user *in, size_t size, loff_t *off) { - /* Once the guest is initialized, we hold the "struct lguest" in the + /* Once the Guest is initialized, we hold the "struct lguest" in the * file private data. */ struct lguest *lg = file->private_data; const unsigned long __user *input = (const unsigned long __user *)in; @@ -230,6 +241,7 @@ static ssize_t write(struct file *file, const char __user *in, struct lg_cpu *uninitialized_var(cpu); unsigned int cpu_id = *off; + /* The first value tells us what this request is. */ if (get_user(req, input) != 0) return -EFAULT; input++; diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c index a7f64a9d67e0..d93500f24fbb 100644 --- a/drivers/lguest/page_tables.c +++ b/drivers/lguest/page_tables.c @@ -2,8 +2,8 @@ * previous encounters. It's functional, and as neat as it can be in the * circumstances, but be wary, for these things are subtle and break easily. * The Guest provides a virtual to physical mapping, but we can neither trust - * it nor use it: we verify and convert it here to point the hardware to the - * actual Guest pages when running the Guest. :*/ + * it nor use it: we verify and convert it here then point the CPU to the + * converted Guest pages when running the Guest. :*/ /* Copyright (C) Rusty Russell IBM Corporation 2006. * GPL v2 and any later version */ @@ -106,6 +106,11 @@ static unsigned long gpte_addr(pgd_t gpgd, unsigned long vaddr) BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT)); return gpage + ((vaddr>>PAGE_SHIFT) % PTRS_PER_PTE) * sizeof(pte_t); } +/*:*/ + +/*M:014 get_pfn is slow; it takes the mmap sem and calls get_user_pages. We + * could probably try to grab batches of pages here as an optimization + * (ie. pre-faulting). :*/ /*H:350 This routine takes a page number given by the Guest and converts it to * an actual, physical page number. It can fail for several reasons: the @@ -113,8 +118,8 @@ static unsigned long gpte_addr(pgd_t gpgd, unsigned long vaddr) * and the page is read-only, or the write flag was set and the page was * shared so had to be copied, but we ran out of memory. * - * This holds a reference to the page, so release_pte() is careful to - * put that back. */ + * This holds a reference to the page, so release_pte() is careful to put that + * back. */ static unsigned long get_pfn(unsigned long virtpfn, int write) { struct page *page; @@ -532,13 +537,13 @@ static void do_set_pte(struct lg_cpu *cpu, int idx, * all processes. So when the page table above that address changes, we update * all the page tables, not just the current one. This is rare. * - * The benefit is that when we have to track a new page table, we can copy keep - * all the kernel mappings. This speeds up context switch immensely. */ + * The benefit is that when we have to track a new page table, we can keep all + * the kernel mappings. This speeds up context switch immensely. */ void guest_set_pte(struct lg_cpu *cpu, unsigned long gpgdir, unsigned long vaddr, pte_t gpte) { - /* Kernel mappings must be changed on all top levels. Slow, but - * doesn't happen often. */ + /* Kernel mappings must be changed on all top levels. Slow, but doesn't + * happen often. */ if (vaddr >= cpu->lg->kernel_address) { unsigned int i; for (i = 0; i < ARRAY_SIZE(cpu->lg->pgdirs); i++) @@ -704,12 +709,11 @@ static __init void populate_switcher_pte_page(unsigned int cpu, /* We've made it through the page table code. Perhaps our tired brains are * still processing the details, or perhaps we're simply glad it's over. * - * If nothing else, note that all this complexity in juggling shadow page - * tables in sync with the Guest's page tables is for one reason: for most - * Guests this page table dance determines how bad performance will be. This - * is why Xen uses exotic direct Guest pagetable manipulation, and why both - * Intel and AMD have implemented shadow page table support directly into - * hardware. + * If nothing else, note that all this complexity in juggling shadow page tables + * in sync with the Guest's page tables is for one reason: for most Guests this + * page table dance determines how bad performance will be. This is why Xen + * uses exotic direct Guest pagetable manipulation, and why both Intel and AMD + * have implemented shadow page table support directly into hardware. * * There is just one file remaining in the Host. */ diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index 635187812d52..5126d5d9ea0e 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -17,6 +17,13 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +/*P:450 This file contains the x86-specific lguest code. It used to be all + * mixed in with drivers/lguest/core.c but several foolhardy code slashers + * wrestled most of the dependencies out to here in preparation for porting + * lguest to other architectures (see what I mean by foolhardy?). + * + * This also contains a couple of non-obvious setup and teardown pieces which + * were implemented after days of debugging pain. :*/ #include <linux/kernel.h> #include <linux/start_kernel.h> #include <linux/string.h> @@ -157,6 +164,8 @@ static void run_guest_once(struct lg_cpu *cpu, struct lguest_pages *pages) * also simplify copy_in_guest_info(). Note that we'd still need to restore * things when we exit to Launcher userspace, but that's fairly easy. * + * We could also try using this hooks for PGE, but that might be too expensive. + * * The hooks were designed for KVM, but we can also put them to good use. :*/ /*H:040 This is the i386-specific code to setup and run the Guest. Interrupts @@ -182,7 +191,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu) * was doing. */ run_guest_once(cpu, lguest_pages(raw_smp_processor_id())); - /* Note that the "regs" pointer contains two extra entries which are + /* Note that the "regs" structure contains two extra entries which are * not really registers: a trap number which says what interrupt or * trap made the switcher code come back, and an error code which some * traps set. */ @@ -293,11 +302,10 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu) break; case 14: /* We've intercepted a Page Fault. */ /* The Guest accessed a virtual address that wasn't mapped. - * This happens a lot: we don't actually set up most of the - * page tables for the Guest at all when we start: as it runs - * it asks for more and more, and we set them up as - * required. In this case, we don't even tell the Guest that - * the fault happened. + * This happens a lot: we don't actually set up most of the page + * tables for the Guest at all when we start: as it runs it asks + * for more and more, and we set them up as required. In this + * case, we don't even tell the Guest that the fault happened. * * The errcode tells whether this was a read or a write, and * whether kernel or userspace code. */ @@ -342,7 +350,7 @@ void lguest_arch_handle_trap(struct lg_cpu *cpu) if (!deliver_trap(cpu, cpu->regs->trapnum)) /* If the Guest doesn't have a handler (either it hasn't * registered any yet, or it's one of the faults we don't let - * it handle), it dies with a cryptic error message. */ + * it handle), it dies with this cryptic error message. */ kill_guest(cpu, "unhandled trap %li at %#lx (%#lx)", cpu->regs->trapnum, cpu->regs->eip, cpu->regs->trapnum == 14 ? cpu->arch.last_pagefault @@ -375,8 +383,8 @@ void __init lguest_arch_host_init(void) * The only exception is the interrupt handlers in switcher.S: their * addresses are placed in a table (default_idt_entries), so we need to * update the table with the new addresses. switcher_offset() is a - * convenience function which returns the distance between the builtin - * switcher code and the high-mapped copy we just made. */ + * convenience function which returns the distance between the + * compiled-in switcher code and the high-mapped copy we just made. */ for (i = 0; i < IDT_ENTRIES; i++) default_idt_entries[i] += switcher_offset(); @@ -416,7 +424,7 @@ void __init lguest_arch_host_init(void) state->guest_gdt_desc.address = (long)&state->guest_gdt; /* We know where we want the stack to be when the Guest enters - * the switcher: in pages->regs. The stack grows upwards, so + * the Switcher: in pages->regs. The stack grows upwards, so * we start it at the end of that structure. */ state->guest_tss.sp0 = (long)(&pages->regs + 1); /* And this is the GDT entry to use for the stack: we keep a @@ -513,8 +521,8 @@ int lguest_arch_init_hypercalls(struct lg_cpu *cpu) { u32 tsc_speed; - /* The pointer to the Guest's "struct lguest_data" is the only - * argument. We check that address now. */ + /* The pointer to the Guest's "struct lguest_data" is the only argument. + * We check that address now. */ if (!lguest_address_ok(cpu->lg, cpu->hcall->arg1, sizeof(*cpu->lg->lguest_data))) return -EFAULT; @@ -546,6 +554,7 @@ int lguest_arch_init_hypercalls(struct lg_cpu *cpu) return 0; } +/*:*/ /*L:030 lguest_arch_setup_regs() * diff --git a/drivers/lguest/x86/switcher_32.S b/drivers/lguest/x86/switcher_32.S index 0af8baaa0d4a..3fc15318a80f 100644 --- a/drivers/lguest/x86/switcher_32.S +++ b/drivers/lguest/x86/switcher_32.S @@ -1,6 +1,6 @@ -/*P:900 This is the Switcher: code which sits at 0xFFC00000 to do the low-level - * Guest<->Host switch. It is as simple as it can be made, but it's naturally - * very specific to x86. +/*P:900 This is the Switcher: code which sits at 0xFFC00000 astride both the + * Host and Guest to do the low-level Guest<->Host switch. It is as simple as + * it can be made, but it's naturally very specific to x86. * * You have now completed Preparation. If this has whet your appetite; if you * are feeling invigorated and refreshed then the next, more challenging stage @@ -189,7 +189,7 @@ ENTRY(switch_to_guest) // Interrupts are turned back on: we are Guest. iret -// We treat two paths to switch back to the Host +// We tread two paths to switch back to the Host // Yet both must save Guest state and restore Host // So we put the routine in a macro. #define SWITCH_TO_HOST \ diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index b04f98df94ea..835def11419d 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2003 Christophe Saout <christophe@saout.de> * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org> - * Copyright (C) 2006-2007 Red Hat, Inc. All rights reserved. + * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ @@ -93,6 +93,8 @@ struct crypt_config { struct workqueue_struct *io_queue; struct workqueue_struct *crypt_queue; + wait_queue_head_t writeq; + /* * crypto related data */ @@ -331,14 +333,7 @@ static void crypt_convert_init(struct crypt_config *cc, ctx->idx_out = bio_out ? bio_out->bi_idx : 0; ctx->sector = sector + cc->iv_offset; init_completion(&ctx->restart); - /* - * Crypto operation can be asynchronous, - * ctx->pending is increased after request submission. - * We need to ensure that we don't call the crypt finish - * operation before pending got incremented - * (dependent on crypt submission return code). - */ - atomic_set(&ctx->pending, 2); + atomic_set(&ctx->pending, 1); } static int crypt_convert_block(struct crypt_config *cc, @@ -411,43 +406,42 @@ static void crypt_alloc_req(struct crypt_config *cc, static int crypt_convert(struct crypt_config *cc, struct convert_context *ctx) { - int r = 0; + int r; while(ctx->idx_in < ctx->bio_in->bi_vcnt && ctx->idx_out < ctx->bio_out->bi_vcnt) { crypt_alloc_req(cc, ctx); + atomic_inc(&ctx->pending); + r = crypt_convert_block(cc, ctx, cc->req); switch (r) { + /* async */ case -EBUSY: wait_for_completion(&ctx->restart); INIT_COMPLETION(ctx->restart); /* fall through*/ case -EINPROGRESS: - atomic_inc(&ctx->pending); cc->req = NULL; - r = 0; - /* fall through*/ + ctx->sector++; + continue; + + /* sync */ case 0: + atomic_dec(&ctx->pending); ctx->sector++; continue; - } - break; + /* error */ + default: + atomic_dec(&ctx->pending); + return r; + } } - /* - * If there are pending crypto operation run async - * code. Otherwise process return code synchronously. - * The step of 2 ensures that async finish doesn't - * call crypto finish too early. - */ - if (atomic_sub_return(2, &ctx->pending)) - return -EINPROGRESS; - - return r; + return 0; } static void dm_crypt_bio_destructor(struct bio *bio) @@ -624,8 +618,10 @@ static void kcryptd_io_read(struct dm_crypt_io *io) static void kcryptd_io_write(struct dm_crypt_io *io) { struct bio *clone = io->ctx.bio_out; + struct crypt_config *cc = io->target->private; generic_make_request(clone); + wake_up(&cc->writeq); } static void kcryptd_io(struct work_struct *work) @@ -698,7 +694,8 @@ static void kcryptd_crypt_write_convert_loop(struct dm_crypt_io *io) r = crypt_convert(cc, &io->ctx); - if (r != -EINPROGRESS) { + if (atomic_dec_and_test(&io->ctx.pending)) { + /* processed, no running async crypto */ kcryptd_crypt_write_io_submit(io, r, 0); if (unlikely(r < 0)) return; @@ -706,8 +703,12 @@ static void kcryptd_crypt_write_convert_loop(struct dm_crypt_io *io) atomic_inc(&io->pending); /* out of memory -> run queues */ - if (unlikely(remaining)) + if (unlikely(remaining)) { + /* wait for async crypto then reinitialize pending */ + wait_event(cc->writeq, !atomic_read(&io->ctx.pending)); + atomic_set(&io->ctx.pending, 1); congestion_wait(WRITE, HZ/100); + } } } @@ -746,7 +747,7 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) r = crypt_convert(cc, &io->ctx); - if (r != -EINPROGRESS) + if (atomic_dec_and_test(&io->ctx.pending)) kcryptd_crypt_read_done(io, r); crypt_dec_pending(io); @@ -1047,6 +1048,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_crypt_queue; } + init_waitqueue_head(&cc->writeq); ti->private = cc; return 0; diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index b8e342fe7586..8f25f628ef16 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -114,7 +114,7 @@ static void dec_count(struct io *io, unsigned int region, int error) wake_up_process(io->sleeper); else { - int r = io->error; + unsigned long r = io->error; io_notify_fn fn = io->callback; void *context = io->context; diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 51605870f898..762cb086bb7f 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -753,7 +753,7 @@ out: * are in the no-sync state. We have to recover these by * recopying from the default mirror to all the others. *---------------------------------------------------------------*/ -static void recovery_complete(int read_err, unsigned int write_err, +static void recovery_complete(int read_err, unsigned long write_err, void *context) { struct region *reg = (struct region *)context; @@ -767,7 +767,7 @@ static void recovery_complete(int read_err, unsigned int write_err, } if (write_err) { - DMERR_LIMIT("Write error during recovery (error = 0x%x)", + DMERR_LIMIT("Write error during recovery (error = 0x%lx)", write_err); /* * Bits correspond to devices (excluding default mirror). diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index ae24eab8cd81..4dc8a43c034b 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -804,7 +804,7 @@ static void commit_callback(void *context, int success) * Called when the copy I/O has finished. kcopyd actually runs * this code so don't block. */ -static void copy_callback(int read_err, unsigned int write_err, void *context) +static void copy_callback(int read_err, unsigned long write_err, void *context) { struct dm_snap_pending_exception *pe = context; struct dm_snapshot *s = pe->snap; diff --git a/drivers/md/kcopyd.c b/drivers/md/kcopyd.c index f3831f31223e..e76b52ade690 100644 --- a/drivers/md/kcopyd.c +++ b/drivers/md/kcopyd.c @@ -169,7 +169,7 @@ struct kcopyd_job { * Error state of the job. */ int read_err; - unsigned int write_err; + unsigned long write_err; /* * Either READ or WRITE @@ -293,7 +293,7 @@ static int run_complete_job(struct kcopyd_job *job) { void *context = job->context; int read_err = job->read_err; - unsigned int write_err = job->write_err; + unsigned long write_err = job->write_err; kcopyd_notify_fn fn = job->fn; struct kcopyd_client *kc = job->kc; @@ -396,7 +396,7 @@ static int process_jobs(struct list_head *jobs, int (*fn) (struct kcopyd_job *)) if (r < 0) { /* error this rogue job */ if (job->rw == WRITE) - job->write_err = (unsigned int) -1; + job->write_err = (unsigned long) -1L; else job->read_err = 1; push(&_complete_jobs, job); @@ -448,8 +448,8 @@ static void dispatch_job(struct kcopyd_job *job) } #define SUB_JOB_SIZE 128 -static void segment_complete(int read_err, - unsigned int write_err, void *context) +static void segment_complete(int read_err, unsigned long write_err, + void *context) { /* FIXME: tidy this function */ sector_t progress = 0; diff --git a/drivers/md/kcopyd.h b/drivers/md/kcopyd.h index 4621ea055c0e..4845f2a0c676 100644 --- a/drivers/md/kcopyd.h +++ b/drivers/md/kcopyd.h @@ -32,8 +32,8 @@ void kcopyd_client_destroy(struct kcopyd_client *kc); * read_err is a boolean, * write_err is a bitset, with 1 bit for each destination region */ -typedef void (*kcopyd_notify_fn)(int read_err, - unsigned int write_err, void *context); +typedef void (*kcopyd_notify_fn)(int read_err, unsigned long write_err, + void *context); int kcopyd_copy(struct kcopyd_client *kc, struct io_region *from, unsigned int num_dests, struct io_region *dests, diff --git a/drivers/memstick/host/tifm_ms.c b/drivers/memstick/host/tifm_ms.c index eb150dfb637f..8577de4ebb0e 100644 --- a/drivers/memstick/host/tifm_ms.c +++ b/drivers/memstick/host/tifm_ms.c @@ -182,7 +182,7 @@ static unsigned int tifm_ms_transfer_data(struct tifm_ms *host) struct tifm_dev *sock = host->dev; unsigned int length; unsigned int off; - unsigned int t_size, p_off, p_cnt; + unsigned int t_size, p_cnt; unsigned char *buf; struct page *pg; unsigned long flags = 0; @@ -198,6 +198,8 @@ static unsigned int tifm_ms_transfer_data(struct tifm_ms *host) host->block_pos); while (length) { + unsigned int uninitialized_var(p_off); + if (host->req->long_data) { pg = nth_page(sg_page(&host->req->sg), off >> PAGE_SHIFT); diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c index f00e04efbe28..bc4649a17b9d 100644 --- a/drivers/mtd/maps/physmap.c +++ b/drivers/mtd/maps/physmap.c @@ -202,9 +202,8 @@ static int physmap_flash_suspend(struct platform_device *dev, pm_message_t state int ret = 0; int i; - if (info) - for (i = 0; i < MAX_RESOURCES; i++) - ret |= info->mtd[i]->suspend(info->mtd[i]); + for (i = 0; i < MAX_RESOURCES && info->mtd[i]; i++) + ret |= info->mtd[i]->suspend(info->mtd[i]); return ret; } @@ -214,9 +213,9 @@ static int physmap_flash_resume(struct platform_device *dev) struct physmap_flash_info *info = platform_get_drvdata(dev); int i; - if (info) - for (i = 0; i < MAX_RESOURCES; i++) - info->mtd[i]->resume(info->mtd[i]); + for (i = 0; i < MAX_RESOURCES && info->mtd[i]; i++) + info->mtd[i]->resume(info->mtd[i]); + return 0; } @@ -225,8 +224,8 @@ static void physmap_flash_shutdown(struct platform_device *dev) struct physmap_flash_info *info = platform_get_drvdata(dev); int i; - for (i = 0; i < MAX_RESOURCES; i++) - if (info && info->mtd[i]->suspend(info->mtd[i]) == 0) + for (i = 0; i < MAX_RESOURCES && info->mtd[i]; i++) + if (info->mtd[i]->suspend(info->mtd[i]) == 0) info->mtd[i]->resume(info->mtd[i]); } #else diff --git a/drivers/mtd/nand/rtc_from4.c b/drivers/mtd/nand/rtc_from4.c index 9189ec8f243e..0f6ac250f434 100644 --- a/drivers/mtd/nand/rtc_from4.c +++ b/drivers/mtd/nand/rtc_from4.c @@ -460,7 +460,7 @@ static int rtc_from4_errstat(struct mtd_info *mtd, struct nand_chip *this, er_stat |= 1 << 1; kfree(buf); } - +out: rtn = status; if (er_stat == 0) { /* if ECC is available */ rtn = (status & ~NAND_STATUS_FAIL); /* clear the error bit */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e9a333d98552..e887aa45c9cd 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -951,6 +951,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82375, quirk_e * accesses to the SMBus registers, with potentially bad effects. Thus you * should be very careful when adding new entries: if SMM is accessing the * Intel SMBus, this is a very good reason to leave it hidden. + * + * Likewise, many recent laptops use ACPI for thermal management. If the + * ACPI DSDT code accesses the SMBus, then Linux should not access it + * natively, and keeping the SMBus hidden is the right thing to do. If you + * are about to add an entry in the table below, please first disassemble + * the DSDT and double-check that there is no code accessing the SMBus. */ static int asus_hides_smbus; @@ -1028,11 +1034,6 @@ static void __init asus_hides_smbus_hostbridge(struct pci_dev *dev) case 0x12bf: /* HP xw4100 */ asus_hides_smbus = 1; } - else if (dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB) - switch (dev->subsystem_device) { - case 0x099c: /* HP Compaq nx6110 */ - asus_hides_smbus = 1; - } } else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG)) { if (dev->device == PCI_DEVICE_ID_INTEL_82855PM_HB) switch(dev->subsystem_device) { diff --git a/drivers/video/bf54x-lq043fb.c b/drivers/video/bf54x-lq043fb.c index 986a550c0439..eefba3d0e4b9 100644 --- a/drivers/video/bf54x-lq043fb.c +++ b/drivers/video/bf54x-lq043fb.c @@ -384,7 +384,7 @@ static int bfin_bf54x_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) * Other flags can be set, and are documented in * include/linux/mm.h */ - vma->vm_flags |= VM_MAYSHARE; + vma->vm_flags |= VM_MAYSHARE | VM_SHARED; return 0; } diff --git a/drivers/video/bfin-t350mcqb-fb.c b/drivers/video/bfin-t350mcqb-fb.c index a2bb2de9e020..135d6dd7e672 100644 --- a/drivers/video/bfin-t350mcqb-fb.c +++ b/drivers/video/bfin-t350mcqb-fb.c @@ -91,6 +91,7 @@ struct bfin_t350mcqbfb_info { int lq043_open_cnt; int irq; spinlock_t lock; /* lock */ + u32 pseudo_pal[16]; }; static int nocursor; @@ -182,13 +183,13 @@ static void bfin_t350mcqb_config_dma(struct bfin_t350mcqbfb_info *fbi) } -static int bfin_t350mcqb_request_ports(int action) -{ - u16 ppi0_req_8[] = {P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, +static u16 ppi0_req_8[] = {P_PPI0_CLK, P_PPI0_FS1, P_PPI0_FS2, P_PPI0_D0, P_PPI0_D1, P_PPI0_D2, P_PPI0_D3, P_PPI0_D4, P_PPI0_D5, P_PPI0_D6, P_PPI0_D7, 0}; +static int bfin_t350mcqb_request_ports(int action) +{ if (action) { if (peripheral_request_list(ppi0_req_8, DRIVER_NAME)) { printk(KERN_ERR "Requesting Peripherals faild\n"); @@ -301,7 +302,7 @@ static int bfin_t350mcqb_fb_mmap(struct fb_info *info, struct vm_area_struct *vm * Other flags can be set, and are documented in * include/linux/mm.h */ - vma->vm_flags |= VM_MAYSHARE; + vma->vm_flags |= VM_MAYSHARE | VM_SHARED; return 0; } @@ -520,16 +521,7 @@ static int __init bfin_t350mcqb_probe(struct platform_device *pdev) fbinfo->fbops = &bfin_t350mcqb_fb_ops; - fbinfo->pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL); - if (!fbinfo->pseudo_palette) { - printk(KERN_ERR DRIVER_NAME - "Fail to allocate pseudo_palette\n"); - - ret = -ENOMEM; - goto out4; - } - - memset(fbinfo->pseudo_palette, 0, sizeof(u32) * 16); + fbinfo->pseudo_palette = &info->pseudo_pal; if (fb_alloc_cmap(&fbinfo->cmap, BFIN_LCD_NBR_PALETTE_ENTRIES, 0) < 0) { @@ -537,7 +529,7 @@ static int __init bfin_t350mcqb_probe(struct platform_device *pdev) "Fail to allocate colormap (%d entries)\n", BFIN_LCD_NBR_PALETTE_ENTRIES); ret = -EFAULT; - goto out5; + goto out4; } if (bfin_t350mcqb_request_ports(1)) { @@ -552,11 +544,11 @@ static int __init bfin_t350mcqb_probe(struct platform_device *pdev) goto out7; } - if (request_irq(info->irq, (void *)bfin_t350mcqb_irq_error, IRQF_DISABLED, - "PPI ERROR", info) < 0) { + ret = request_irq(info->irq, bfin_t350mcqb_irq_error, IRQF_DISABLED, + "PPI ERROR", info); + if (ret < 0) { printk(KERN_ERR DRIVER_NAME ": unable to request PPI ERROR IRQ\n"); - ret = -EFAULT; goto out7; } @@ -584,8 +576,6 @@ out7: bfin_t350mcqb_request_ports(0); out6: fb_dealloc_cmap(&fbinfo->cmap); -out5: - kfree(fbinfo->pseudo_palette); out4: dma_free_coherent(NULL, fbinfo->fix.smem_len, info->fb_buffer, info->dma_handle); @@ -605,6 +595,8 @@ static int bfin_t350mcqb_remove(struct platform_device *pdev) struct fb_info *fbinfo = platform_get_drvdata(pdev); struct bfin_t350mcqbfb_info *info = fbinfo->par; + unregister_framebuffer(fbinfo); + free_dma(CH_PPI); free_irq(info->irq, info); @@ -612,7 +604,6 @@ static int bfin_t350mcqb_remove(struct platform_device *pdev) dma_free_coherent(NULL, fbinfo->fix.smem_len, info->fb_buffer, info->dma_handle); - kfree(fbinfo->pseudo_palette); fb_dealloc_cmap(&fbinfo->cmap); #ifndef NO_BL_SUPPORT @@ -620,10 +611,11 @@ static int bfin_t350mcqb_remove(struct platform_device *pdev) backlight_device_unregister(bl_dev); #endif - unregister_framebuffer(fbinfo); - bfin_t350mcqb_request_ports(0); + platform_set_drvdata(pdev, NULL); + framebuffer_release(fbinfo); + printk(KERN_INFO DRIVER_NAME ": Unregister LCD driver.\n"); return 0; diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c index 59a8f73dec73..6c8ecde6aad1 100644 --- a/drivers/virtio/virtio_pci.c +++ b/drivers/virtio/virtio_pci.c @@ -388,6 +388,7 @@ static void __devexit virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + unregister_virtio_device(&vp_dev->vdev); free_irq(pci_dev->irq, vp_dev); pci_set_drvdata(pci_dev, NULL); pci_iounmap(pci_dev, vp_dev->ioaddr); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 970d38f30565..788865df1bc9 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -127,14 +127,20 @@ struct afs_cell *afs_cell_create(const char *name, char *vllist) _enter("%s,%s", name, vllist); + down_write(&afs_cells_sem); + read_lock(&afs_cells_lock); + list_for_each_entry(cell, &afs_cells, link) { + if (strcasecmp(cell->name, name) == 0) + goto duplicate_name; + } + read_unlock(&afs_cells_lock); + cell = afs_cell_alloc(name, vllist); if (IS_ERR(cell)) { _leave(" = %ld", PTR_ERR(cell)); return cell; } - down_write(&afs_cells_sem); - /* add a proc directory for this cell */ ret = afs_proc_cell_setup(cell); if (ret < 0) @@ -167,6 +173,11 @@ error: kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); + +duplicate_name: + read_unlock(&afs_cells_lock); + up_write(&afs_cells_sem); + return ERR_PTR(-EEXIST); } /* diff --git a/fs/buffer.c b/fs/buffer.c index 7ba58386beee..98196327ddf0 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2564,14 +2564,13 @@ int nobh_write_end(struct file *file, struct address_space *mapping, struct inode *inode = page->mapping->host; struct buffer_head *head = fsdata; struct buffer_head *bh; + BUG_ON(fsdata != NULL && page_has_buffers(page)); - if (!PageMappedToDisk(page)) { - if (unlikely(copied < len) && !page_has_buffers(page)) - attach_nobh_buffers(page, head); - if (page_has_buffers(page)) - return generic_write_end(file, mapping, pos, len, - copied, page, fsdata); - } + if (unlikely(copied < len) && !page_has_buffers(page)) + attach_nobh_buffers(page, head); + if (page_has_buffers(page)) + return generic_write_end(file, mapping, pos, len, + copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); diff --git a/include/asm-x86/lguest_hcall.h b/include/asm-x86/lguest_hcall.h index 758b9a5d4539..f239e7069cab 100644 --- a/include/asm-x86/lguest_hcall.h +++ b/include/asm-x86/lguest_hcall.h @@ -27,7 +27,7 @@ #ifndef __ASSEMBLY__ #include <asm/hw_irq.h> -/*G:031 First, how does our Guest contact the Host to ask for privileged +/*G:031 But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 4108b38ebb16..4a446a19295e 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -195,7 +195,6 @@ unifdef-y += ethtool.h unifdef-y += eventpoll.h unifdef-y += signalfd.h unifdef-y += ext2_fs.h -unifdef-y += ext3_fs.h unifdef-y += fb.h unifdef-y += fcntl.h unifdef-y += filter.h @@ -248,7 +247,6 @@ unifdef-y += isdn.h unifdef-y += isdnif.h unifdef-y += isdn_divertif.h unifdef-y += isdn_ppp.h -unifdef-y += jbd.h unifdef-y += joystick.h unifdef-y += kdev_t.h unifdef-y += kd.h diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 69c1edb9fe54..40d54731de7e 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -65,6 +65,46 @@ static inline __u32 ror32(__u32 word, unsigned int shift) return (word >> shift) | (word << (32 - shift)); } +/** + * rol16 - rotate a 16-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u16 rol16(__u16 word, unsigned int shift) +{ + return (word << shift) | (word >> (16 - shift)); +} + +/** + * ror16 - rotate a 16-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u16 ror16(__u16 word, unsigned int shift) +{ + return (word >> shift) | (word << (16 - shift)); +} + +/** + * rol8 - rotate an 8-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u8 rol8(__u8 word, unsigned int shift) +{ + return (word << shift) | (word >> (8 - shift)); +} + +/** + * ror8 - rotate an 8-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline __u8 ror8(__u8 word, unsigned int shift) +{ + return (word >> shift) | (word << (8 - shift)); +} + static inline unsigned fls_long(unsigned long l) { if (sizeof(l) == 4) diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index 49829988bfa0..897f723bd222 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -72,6 +72,13 @@ #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) +/* + * Are we running in atomic context? WARNING: this macro cannot + * always detect atomic context; in particular, it cannot know about + * held spinlocks in non-preemptible kernels. Thus it should not be + * used in the general case to determine whether sleeping is possible. + * Do not use in_atomic() in driver code. + */ #define in_atomic() ((preempt_count() & ~PREEMPT_ACTIVE) != 0) #ifdef CONFIG_PREEMPT diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 589be3e1f3ac..e7217dc58f39 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -16,6 +16,10 @@ * a new device, we simply need to write a new virtio driver and create support * for it in the Launcher: this code won't need to change. * + * Virtio devices are also used by kvm, so we can simply reuse their optimized + * device drivers. And one day when everyone uses virtio, my plan will be + * complete. Bwahahahah! + * * Devices are described by a simplified ID, a status byte, and some "config" * bytes which describe this device's configuration. This is placed by the * Launcher just above the top of physical memory: @@ -26,7 +30,7 @@ struct lguest_device_desc { /* The number of virtqueues (first in config array) */ __u8 num_vq; /* The number of bytes of feature bits. Multiply by 2: one for host - * features and one for guest acknowledgements. */ + * features and one for Guest acknowledgements. */ __u8 feature_len; /* The number of bytes of the config array after virtqueues. */ __u8 config_len; diff --git a/kernel/audit.c b/kernel/audit.c index be55cb503633..b782b046543d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1269,8 +1269,8 @@ static void audit_log_n_string(struct audit_buffer *ab, size_t slen, /** * audit_string_contains_control - does a string need to be logged in hex - * @string - string to be checked - * @len - max length of the string to check + * @string: string to be checked + * @len: max length of the string to check */ int audit_string_contains_control(const char *string, size_t len) { @@ -1285,7 +1285,7 @@ int audit_string_contains_control(const char *string, size_t len) /** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer - * @len: lenth of string (not including trailing null) + * @len: length of string (not including trailing null) * @string: string to be logged * * This code will escape a string that is passed to it if the string diff --git a/kernel/fork.c b/kernel/fork.c index dd249c37b3a3..9c042f901570 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -394,7 +394,6 @@ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); mm_free_pgd(mm); - mm_free_cgroup(mm); destroy_context(mm); free_mm(mm); } @@ -416,6 +415,7 @@ void mmput(struct mm_struct *mm) spin_unlock(&mmlist_lock); } put_swap_token(mm); + mm_free_cgroup(mm); mmdrop(mm); } } diff --git a/mm/slub.c b/mm/slub.c index b72bc98e2dc1..84ed734b96b3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1470,6 +1470,9 @@ static void *__slab_alloc(struct kmem_cache *s, void **object; struct page *new; + /* We handle __GFP_ZERO in the caller */ + gfpflags &= ~__GFP_ZERO; + if (!c->page) goto new_slab; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 4e8d4e724b96..f624dff76852 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1520,7 +1520,7 @@ static int __init p9_trans_fd_init(void) v9fs_register_trans(&p9_unix_trans); v9fs_register_trans(&p9_fd_trans); - return 1; + return 0; } module_init(p9_trans_fd_init); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2a7cef9726e4..58a94947d655 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -9,7 +9,7 @@ use strict; my $P = $0; $P =~ s@.*/@@g; -my $V = '0.15'; +my $V = '0.16'; use Getopt::Long qw(:config no_auto_abbrev); @@ -18,6 +18,7 @@ my $tree = 1; my $chk_signoff = 1; my $chk_patch = 1; my $tst_type = 0; +my $tst_only; my $emacs = 0; my $terse = 0; my $file = 0; @@ -44,6 +45,7 @@ GetOptions( 'debug=s' => \%debug, 'test-type!' => \$tst_type, + 'test-only=s' => \$tst_only, ) or exit; my $exit = 0; @@ -263,17 +265,7 @@ sub expand_tabs { return $res; } sub copy_spacing { - my ($str) = @_; - - my $res = ''; - for my $c (split(//, $str)) { - if ($c eq "\t") { - $res .= $c; - } else { - $res .= ' '; - } - } - + (my $res = shift) =~ tr/\t/ /c; return $res; } @@ -290,53 +282,76 @@ sub line_stats { return (length($line), length($white)); } +my $sanitise_quote = ''; + +sub sanitise_line_reset { + my ($in_comment) = @_; + + if ($in_comment) { + $sanitise_quote = '*/'; + } else { + $sanitise_quote = ''; + } +} sub sanitise_line { my ($line) = @_; my $res = ''; my $l = ''; - my $quote = ''; my $qlen = 0; + my $off = 0; + my $c; - foreach my $c (split(//, $line)) { - # The second backslash of a pair is not a "quote". - if ($l eq "\\" && $c eq "\\") { - $c = 'X'; - } - if ($l ne "\\" && ($c eq "'" || $c eq '"')) { - if ($quote eq '') { - $quote = $c; - $res .= $c; - $l = $c; - $qlen = 0; - next; - } elsif ($quote eq $c) { - $quote = ''; - } + # Always copy over the diff marker. + $res = substr($line, 0, 1); + + for ($off = 1; $off < length($line); $off++) { + $c = substr($line, $off, 1); + + # Comments we are wacking completly including the begin + # and end, all to $;. + if ($sanitise_quote eq '' && substr($line, $off, 2) eq '/*') { + $sanitise_quote = '*/'; + + substr($res, $off, 2, "$;$;"); + $off++; + next; } - if ($quote eq "'" && $qlen > 1) { - $quote = ''; + if (substr($line, $off, 2) eq $sanitise_quote) { + $sanitise_quote = ''; + substr($res, $off, 2, "$;$;"); + $off++; + next; } - if ($quote && $c ne "\t") { - $res .= "X"; - $qlen++; - } else { - $res .= $c; + + # A \ in a string means ignore the next character. + if (($sanitise_quote eq "'" || $sanitise_quote eq '"') && + $c eq "\\") { + substr($res, $off, 2, 'XX'); + $off++; + next; } + # Regular quotes. + if ($c eq "'" || $c eq '"') { + if ($sanitise_quote eq '') { + $sanitise_quote = $c; - $l = $c; - } + substr($res, $off, 1, $c); + next; + } elsif ($sanitise_quote eq $c) { + $sanitise_quote = ''; + } + } - # Clear out the comments. - while ($res =~ m@(/\*.*?\*/)@g) { - substr($res, $-[1], $+[1] - $-[1]) = $; x ($+[1] - $-[1]); - } - if ($res =~ m@(/\*.*)@) { - substr($res, $-[1], $+[1] - $-[1]) = $; x ($+[1] - $-[1]); - } - if ($res =~ m@^.(.*\*/)@) { - substr($res, $-[1], $+[1] - $-[1]) = $; x ($+[1] - $-[1]); + #print "SQ:$sanitise_quote\n"; + if ($off != 0 && $sanitise_quote eq '*/' && $c ne "\t") { + substr($res, $off, 1, $;); + } elsif ($off != 0 && $sanitise_quote && $c ne "\t") { + substr($res, $off, 1, 'X'); + } else { + substr($res, $off, 1, $c); + } } # The pathname on a #include may be surrounded by '<' and '>'. @@ -359,6 +374,7 @@ sub ctx_statement_block { my $blk = ''; my $soff = $off; my $coff = $off - 1; + my $coff_set = 0; my $loff = 0; @@ -370,7 +386,7 @@ sub ctx_statement_block { my $remainder; while (1) { - #warn "CSB: blk<$blk>\n"; + #warn "CSB: blk<$blk> remain<$remain>\n"; # If we are about to drop off the end, pull in more # context. if ($off >= $len) { @@ -393,7 +409,7 @@ sub ctx_statement_block { $c = substr($blk, $off, 1); $remainder = substr($blk, $off); - #warn "CSB: c<$c> type<$type> level<$level>\n"; + #warn "CSB: c<$c> type<$type> level<$level> remainder<$remainder> coff_set<$coff_set>\n"; # Statement ends at the ';' or a close '}' at the # outermost level. if ($level == 0 && $c eq ';') { @@ -401,10 +417,14 @@ sub ctx_statement_block { } # An else is really a conditional as long as its not else if - if ($level == 0 && (!defined($p) || $p =~ /(?:\s|\})/) && - $remainder =~ /(else)(?:\s|{)/ && - $remainder !~ /else\s+if\b/) { - $coff = $off + length($1); + if ($level == 0 && $coff_set == 0 && + (!defined($p) || $p =~ /(?:\s|\}|\+)/) && + $remainder =~ /^(else)(?:\s|{)/ && + $remainder !~ /^else\s+if\b/) { + $coff = $off + length($1) - 1; + $coff_set = 1; + #warn "CSB: mark coff<$coff> soff<$soff> 1<$1>\n"; + #warn "[" . substr($blk, $soff, $coff - $soff + 1) . "]\n"; } if (($type eq '' || $type eq '(') && $c eq '(') { @@ -417,6 +437,8 @@ sub ctx_statement_block { if ($level == 0 && $coff < $soff) { $coff = $off; + $coff_set = 1; + #warn "CSB: mark coff<$coff>\n"; } } if (($type eq '' || $type eq '{') && $c eq '{') { @@ -444,7 +466,7 @@ sub ctx_statement_block { #warn "STATEMENT<$statement>\n"; #warn "CONDITION<$condition>\n"; - #print "off<$off> loff<$loff>\n"; + #print "coff<$coff> soff<$off> loff<$loff>\n"; return ($statement, $condition, $line, $remain + 1, $off - $loff + 1, $level); @@ -502,7 +524,7 @@ sub ctx_statement_full { # Grab the first conditional/block pair. ($statement, $condition, $linenr, $remain, $off, $level) = ctx_statement_block($linenr, $remain, $off); - #print "F: c<$condition> s<$statement>\n"; + #print "F: c<$condition> s<$statement> remain<$remain>\n"; push(@chunks, [ $condition, $statement ]); if (!($remain > 0 && $condition =~ /^\s*(?:\n[+-])?\s*(?:if|else|do)\b/s)) { return ($level, $linenr, @chunks); @@ -514,7 +536,7 @@ sub ctx_statement_full { ($statement, $condition, $linenr, $remain, $off, $level) = ctx_statement_block($linenr, $remain, $off); #print "C: c<$condition> s<$statement> remain<$remain>\n"; - last if (!($remain > 0 && $condition =~ /^\s*(?:\n[+-])?\s*(?:else|do)\b/s)); + last if (!($remain > 0 && $condition =~ /^(?:\s*\n[+-])*\s*(?:else|do)\b/s)); #print "C: push\n"; push(@chunks, [ $condition, $statement ]); } @@ -668,6 +690,7 @@ sub annotate_values { print "$stream\n" if ($dbg_values > 1); while (length($cur)) { + @av_paren_type = ('E') if ($#av_paren_type < 0); print " <" . join('', @av_paren_type) . "> <$type> " if ($dbg_values > 1); if ($cur =~ /^(\s+)/o) { @@ -804,28 +827,34 @@ sub possible { my $prefix = ''; sub report { + if (defined $tst_only && $_[0] !~ /\Q$tst_only\E/) { + return 0; + } my $line = $prefix . $_[0]; $line = (split('\n', $line))[0] . "\n" if ($terse); push(our @report, $line); + + return 1; } sub report_dump { our @report; } sub ERROR { - report("ERROR: $_[0]\n"); - our $clean = 0; - our $cnt_error++; + if (report("ERROR: $_[0]\n")) { + our $clean = 0; + our $cnt_error++; + } } sub WARN { - report("WARNING: $_[0]\n"); - our $clean = 0; - our $cnt_warn++; + if (report("WARNING: $_[0]\n")) { + our $clean = 0; + our $cnt_warn++; + } } sub CHK { - if ($check) { - report("CHECK: $_[0]\n"); + if ($check && report("CHECK: $_[0]\n")) { our $clean = 0; our $cnt_chk++; } @@ -867,30 +896,76 @@ sub process { my $prev_values = 'E'; # suppression flags - my $suppress_ifbraces = 0; + my %suppress_ifbraces; # Pre-scan the patch sanitizing the lines. # Pre-scan the patch looking for any __setup documentation. # my @setup_docs = (); my $setup_docs = 0; + + sanitise_line_reset(); my $line; foreach my $rawline (@rawlines) { - # Standardise the strings and chars within the input to - # simplify matching. - $line = sanitise_line($rawline); - push(@lines, $line); - - ##print "==>$rawline\n"; - ##print "-->$line\n"; + $linenr++; + $line = $rawline; - if ($line=~/^\+\+\+\s+(\S+)/) { + if ($rawline=~/^\+\+\+\s+(\S+)/) { $setup_docs = 0; if ($1 =~ m@Documentation/kernel-parameters.txt$@) { $setup_docs = 1; } - next; + #next; + } + if ($rawline=~/^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { + $realline=$1-1; + if (defined $2) { + $realcnt=$3+1; + } else { + $realcnt=1+1; + } + + # Guestimate if this is a continuing comment. Run + # the context looking for a comment "edge". If this + # edge is a close comment then we must be in a comment + # at context start. + my $edge; + for (my $ln = $linenr; $ln < ($linenr + $realcnt); $ln++) { + next if ($line =~ /^-/); + ($edge) = ($rawlines[$ln - 1] =~ m@(/\*|\*/)@); + last if (defined $edge); + } + if (defined $edge && $edge eq '*/') { + $in_comment = 1; + } + + # Guestimate if this is a continuing comment. If this + # is the start of a diff block and this line starts + # ' *' then it is very likely a comment. + if (!defined $edge && + $rawlines[$linenr] =~ m@^.\s* \*(?:\s|$)@) + { + $in_comment = 1; + } + + ##print "COMMENT:$in_comment edge<$edge> $rawline\n"; + sanitise_line_reset($in_comment); + + } elsif ($realcnt) { + # Standardise the strings and chars within the input to + # simplify matching. + $line = sanitise_line($rawline); } + push(@lines, $line); + + if ($realcnt > 1) { + $realcnt-- if ($line =~ /^(?:\+| |$)/); + } else { + $realcnt = 0; + } + + #print "==>$rawline\n"; + #print "-->$line\n"; if ($setup_docs && $line =~ /^\+/) { push(@setup_docs, $line); @@ -899,23 +974,17 @@ sub process { $prefix = ''; + $realcnt = 0; + $linenr = 0; foreach my $line (@lines) { $linenr++; my $rawline = $rawlines[$linenr - 1]; -#extract the filename as it passes - if ($line=~/^\+\+\+\s+(\S+)/) { - $realfile=$1; - $realfile =~ s@^[^/]*/@@; - $in_comment = 0; - next; - } #extract the line range in the file after the patch is applied if ($line=~/^\@\@ -\d+(?:,\d+)? \+(\d+)(,(\d+))? \@\@/) { $is_patch = 1; $first_line = $linenr + 1; - $in_comment = 0; $realline=$1-1; if (defined $2) { $realcnt=$3+1; @@ -925,50 +994,16 @@ sub process { annotate_reset(); $prev_values = 'E'; - $suppress_ifbraces = $linenr - 1; + %suppress_ifbraces = (); next; - } # track the line number as we move through the hunk, note that # new versions of GNU diff omit the leading space on completely # blank context lines so we need to count that too. - if ($line =~ /^( |\+|$)/) { + } elsif ($line =~ /^( |\+|$)/) { $realline++; $realcnt-- if ($realcnt != 0); - # Guestimate if this is a continuing comment. Run - # the context looking for a comment "edge". If this - # edge is a close comment then we must be in a comment - # at context start. - if ($linenr == $first_line) { - my $edge; - for (my $ln = $first_line; $ln < ($linenr + $realcnt); $ln++) { - ($edge) = ($rawlines[$ln - 1] =~ m@(/\*|\*/)@); - last if (defined $edge); - } - if (defined $edge && $edge eq '*/') { - $in_comment = 1; - } - } - - # Guestimate if this is a continuing comment. If this - # is the start of a diff block and this line starts - # ' *' then it is very likely a comment. - if ($linenr == $first_line and $rawline =~ m@^.\s* \*(?:\s|$)@) { - $in_comment = 1; - } - - # Find the last comment edge on _this_ line. - $comment_edge = 0; - while (($rawline =~ m@(/\*|\*/)@g)) { - if ($1 eq '/*') { - $in_comment = 1; - } else { - $in_comment = 0; - } - $comment_edge = 1; - } - # Measure the line length and indent. ($length, $indent) = line_stats($rawline); @@ -977,23 +1012,36 @@ sub process { ($previndent, $stashindent) = ($stashindent, $indent); ($prevrawline, $stashrawline) = ($stashrawline, $rawline); - #warn "ic<$in_comment> ce<$comment_edge> line<$line>\n"; + #warn "line<$line>\n"; } elsif ($realcnt == 1) { $realcnt--; } #make up the handle for any error we report on this line + $prefix = "$filename:$realline: " if ($emacs && $file); + $prefix = "$filename:$linenr: " if ($emacs && !$file); + $here = "#$linenr: " if (!$file); $here = "#$realline: " if ($file); + + # extract the filename as it passes + if ($line=~/^\+\+\+\s+(\S+)/) { + $realfile = $1; + $realfile =~ s@^[^/]*/@@; + + if ($realfile =~ m@include/asm/@) { + ERROR("do not modify files in include/asm, change architecture specific files in include/asm-<architecture>\n" . "$here$rawline\n"); + } + next; + } + $here .= "FILE: $realfile:$realline:" if ($realcnt != 0); my $hereline = "$here\n$rawline\n"; my $herecurr = "$here\n$rawline\n"; my $hereprev = "$here\n$prevrawline\n$rawline\n"; - $prefix = "$filename:$realline: " if ($emacs && $file); - $prefix = "$filename:$linenr: " if ($emacs && !$file); $cnt_lines++ if ($realcnt != 0); #check the patch for a signoff: @@ -1005,7 +1053,7 @@ sub process { $herecurr); } if ($line =~ /^\s*signed-off-by:\S/i) { - WARN("need space after Signed-off-by:\n" . + WARN("space required after Signed-off-by:\n" . $herecurr); } } @@ -1072,11 +1120,6 @@ sub process { WARN("CVS style keyword markers, these will _not_ be updated\n". $herecurr); } -# The rest of our checks refer specifically to C style -# only apply those _outside_ comments. Only skip -# lines in the middle of comments. - next if (!$comment_edge && $in_comment); - # Check for potential 'bare' types if ($realcnt) { my ($s, $c) = ctx_statement_block($linenr, $realcnt, 0); @@ -1110,7 +1153,7 @@ sub process { my ($name_len) = length($1); my $ctx = $s; - substr($ctx, 0, $name_len + 1) = ''; + substr($ctx, 0, $name_len + 1, ''); $ctx =~ s/\)[^\)]*$//; for my $arg (split(/\s*,\s*/, $ctx)) { @@ -1151,27 +1194,33 @@ sub process { # if/while/etc brace do not go on next line, unless defining a do while loop, # or if that brace on the next line is for something else - if ($line =~ /\b(?:(if|while|for|switch)\s*\(|do\b|else\b)/ && $line !~ /^.#/) { + if ($line =~ /(.*)\b((?:if|while|for|switch)\s*\(|do\b|else\b)/ && $line !~ /^.#/) { + my $pre_ctx = "$1$2"; + my ($level, @ctx) = ctx_statement_level($linenr, $realcnt, 0); my $ctx_ln = $linenr + $#ctx + 1; my $ctx_cnt = $realcnt - $#ctx - 1; my $ctx = join("\n", @ctx); + ##warn "realcnt<$realcnt> ctx_cnt<$ctx_cnt>\n"; + # Skip over any removed lines in the context following statement. - while ($ctx_cnt > 0 && $lines[$ctx_ln - 1] =~ /^-/) { + while (defined($lines[$ctx_ln - 1]) && $lines[$ctx_ln - 1] =~ /^-/) { $ctx_ln++; - $ctx_cnt--; } - ##warn "line<$line>\nctx<$ctx>\nnext<$lines[$ctx_ln - 1]>"; + ##warn "pre<$pre_ctx>\nline<$line>\nctx<$ctx>\nnext<$lines[$ctx_ln - 1]>\n"; - if ($ctx !~ /{\s*/ && $ctx_cnt > 0 && $lines[$ctx_ln - 1] =~ /^\+\s*{/) { - ERROR("That open brace { should be on the previous line\n" . + if ($ctx !~ /{\s*/ && defined($lines[$ctx_ln -1]) && $lines[$ctx_ln - 1] =~ /^\+\s*{/) { + ERROR("that open brace { should be on the previous line\n" . "$here\n$ctx\n$lines[$ctx_ln - 1]"); } - if ($level == 0 && $ctx =~ /\)\s*\;\s*$/ && defined $lines[$ctx_ln - 1]) { + if ($level == 0 && $pre_ctx !~ /}\s*while\s*\($/ && + $ctx =~ /\)\s*\;\s*$/ && + defined $lines[$ctx_ln - 1]) + { my ($nlength, $nindent) = line_stats($lines[$ctx_ln - 1]); if ($nindent > $indent) { - WARN("Trailing semicolon indicates no statements, indent implies otherwise\n" . + WARN("trailing semicolon indicates no statements, indent implies otherwise\n" . "$here\n$ctx\n$lines[$ctx_ln - 1]"); } } @@ -1200,7 +1249,7 @@ sub process { # check for initialisation to aggregates open brace on the next line if ($prevline =~ /$Declare\s*$Ident\s*=\s*$/ && $line =~ /^.\s*{/) { - ERROR("That open brace { should be on the previous line\n" . $hereprev); + ERROR("that open brace { should be on the previous line\n" . $hereprev); } # @@ -1325,22 +1374,31 @@ sub process { # check for spaces between functions and their parentheses. while ($line =~ /($Ident)\s+\(/g) { my $name = $1; - my $ctx = substr($line, 0, $-[1]); + my $ctx_before = substr($line, 0, $-[1]); + my $ctx = "$ctx_before$name"; # Ignore those directives where spaces _are_ permitted. - if ($name =~ /^(?:if|for|while|switch|return|volatile|__volatile__|__attribute__|format|__extension__|Copyright|case|__asm__)$/) { + if ($name =~ /^(?: + if|for|while|switch|return|case| + volatile|__volatile__| + __attribute__|format|__extension__| + asm|__asm__)$/x) + { # cpp #define statements have non-optional spaces, ie # if there is a space between the name and the open # parenthesis it is simply not a parameter group. - } elsif ($ctx =~ /^.\#\s*define\s*$/) { + } elsif ($ctx_before =~ /^.\#\s*define\s*$/) { + + # cpp #elif statement condition may start with a ( + } elsif ($ctx =~ /^.\#\s*elif\s*$/) { # If this whole things ends with a type its most # likely a typedef for a function. - } elsif ("$ctx$name" =~ /$Type$/) { + } elsif ($ctx =~ /$Type$/) { } else { - WARN("no space between function name and open parenthesis '('\n" . $herecurr); + WARN("space prohibited between function name and open parenthesis '('\n" . $herecurr); } } # Check operator spacing. @@ -1359,13 +1417,21 @@ sub process { for (my $n = 0; $n < $#elements; $n += 2) { $off += length($elements[$n]); + # Pick up the preceeding and succeeding characters. + my $ca = substr($opline, 0, $off); + my $cc = ''; + if (length($opline) >= ($off + length($elements[$n + 1]))) { + $cc = substr($opline, $off + length($elements[$n + 1])); + } + my $cb = "$ca$;$cc"; + my $a = ''; $a = 'V' if ($elements[$n] ne ''); $a = 'W' if ($elements[$n] =~ /\s$/); $a = 'C' if ($elements[$n] =~ /$;$/); $a = 'B' if ($elements[$n] =~ /(\[|\()$/); $a = 'O' if ($elements[$n] eq ''); - $a = 'E' if ($elements[$n] eq '' && $n == 0); + $a = 'E' if ($ca =~ /^\s*$/); my $op = $elements[$n + 1]; @@ -1381,14 +1447,6 @@ sub process { $c = 'E'; } - # Pick up the preceeding and succeeding characters. - my $ca = substr($opline, 0, $off); - my $cc = ''; - if (length($opline) >= ($off + length($elements[$n + 1]))) { - $cc = substr($opline, $off + length($elements[$n + 1])); - } - my $cb = "$ca$;$cc"; - my $ctx = "${a}x${c}"; my $at = "(ctx:$ctx)"; @@ -1424,7 +1482,7 @@ sub process { } elsif ($op eq ';') { if ($ctx !~ /.x[WEBC]/ && $cc !~ /^\\/ && $cc !~ /^;/) { - ERROR("need space after that '$op' $at\n" . $hereptr); + ERROR("space required after that '$op' $at\n" . $hereptr); } # // is a comment @@ -1433,13 +1491,13 @@ sub process { # -> should have no spaces } elsif ($op eq '->') { if ($ctx =~ /Wx.|.xW/) { - ERROR("no spaces around that '$op' $at\n" . $hereptr); + ERROR("spaces prohibited around that '$op' $at\n" . $hereptr); } # , must have a space on the right. } elsif ($op eq ',') { if ($ctx !~ /.x[WEC]/ && $cc !~ /^}/) { - ERROR("need space after that '$op' $at\n" . $hereptr); + ERROR("space required after that '$op' $at\n" . $hereptr); } # '*' as part of a type definition -- reported already. @@ -1452,21 +1510,26 @@ sub process { } elsif ($op eq '!' || $op eq '~' || ($is_unary && ($op eq '*' || $op eq '-' || $op eq '&'))) { if ($ctx !~ /[WEBC]x./ && $ca !~ /(?:\)|!|~|\*|-|\&|\||\+\+|\-\-|\{)$/) { - ERROR("need space before that '$op' $at\n" . $hereptr); + ERROR("space required before that '$op' $at\n" . $hereptr); } if ($ctx =~ /.xW/) { - ERROR("no space after that '$op' $at\n" . $hereptr); + ERROR("space prohibited after that '$op' $at\n" . $hereptr); } # unary ++ and unary -- are allowed no space on one side. } elsif ($op eq '++' or $op eq '--') { - if ($ctx !~ /[WOBC]x[^W]/ && $ctx !~ /[^W]x[WOBEC]/) { - ERROR("need space one side of that '$op' $at\n" . $hereptr); + if ($ctx !~ /[WEOBC]x[^W]/ && $ctx !~ /[^W]x[WOBEC]/) { + ERROR("space required one side of that '$op' $at\n" . $hereptr); + } + if ($ctx =~ /Wx[BE]/ || + ($ctx =~ /Wx./ && $cc =~ /^;/)) { + ERROR("space prohibited before that '$op' $at\n" . $hereptr); } - if ($ctx =~ /WxB/ || ($ctx =~ /Wx./ && $cc =~ /^;/)) { - ERROR("no space before that '$op' $at\n" . $hereptr); + if ($ctx =~ /ExW/) { + ERROR("space prohibited after that '$op' $at\n" . $hereptr); } + # << and >> may either have or not have spaces both sides } elsif ($op eq '<<' or $op eq '>>' or $op eq '&' or $op eq '^' or $op eq '|' or @@ -1474,7 +1537,7 @@ sub process { $op eq '*' or $op eq '/' or $op eq '%') { - if ($ctx !~ /VxV|WxW|VxE|WxE|VxO|Cx.|.xC/) { + if ($ctx =~ /Wx[^WCE]|[^WCE]xW/) { ERROR("need consistent spacing around '$op' $at\n" . $hereptr); } @@ -1484,7 +1547,7 @@ sub process { # Ignore email addresses <foo@bar> if (!($op eq '<' && $cb =~ /$;\S+\@\S+>/) && !($op eq '>' && $cb =~ /<\S+\@\S+$;/)) { - ERROR("need spaces around that '$op' $at\n" . $hereptr); + ERROR("spaces required around that '$op' $at\n" . $hereptr); } } $off += length($elements[$n + 1]); @@ -1514,31 +1577,31 @@ sub process { #need space before brace following if, while, etc if (($line =~ /\(.*\){/ && $line !~ /\($Type\){/) || $line =~ /do{/) { - ERROR("need a space before the open brace '{'\n" . $herecurr); + ERROR("space required before the open brace '{'\n" . $herecurr); } # closing brace should have a space following it when it has anything # on the line if ($line =~ /}(?!(?:,|;|\)))\S/) { - ERROR("need a space after that close brace '}'\n" . $herecurr); + ERROR("space required after that close brace '}'\n" . $herecurr); } # check spacing on square brackets if ($line =~ /\[\s/ && $line !~ /\[\s*$/) { - ERROR("no space after that open square bracket '['\n" . $herecurr); + ERROR("space prohibited after that open square bracket '['\n" . $herecurr); } if ($line =~ /\s\]/) { - ERROR("no space before that close square bracket ']'\n" . $herecurr); + ERROR("space prohibited before that close square bracket ']'\n" . $herecurr); } # check spacing on paretheses if ($line =~ /\(\s/ && $line !~ /\(\s*(?:\\)?$/ && $line !~ /for\s*\(\s+;/) { - ERROR("no space after that open parenthesis '('\n" . $herecurr); + ERROR("space prohibited after that open parenthesis '('\n" . $herecurr); } if ($line =~ /(\s+)\)/ && $line !~ /^.\s*\)/ && $line !~ /for\s*\(.*;\s+\)/) { - ERROR("no space before that close parenthesis ')'\n" . $herecurr); + ERROR("space prohibited before that close parenthesis ')'\n" . $herecurr); } #goto labels aren't indented, allow a single space however @@ -1549,7 +1612,7 @@ sub process { # Need a space before open parenthesis after if, while etc if ($line=~/\b(if|while|for|switch)\(/) { - ERROR("need a space before the open parenthesis '('\n" . $herecurr); + ERROR("space required before the open parenthesis '('\n" . $herecurr); } # Check for illegal assignment in if conditional. @@ -1562,10 +1625,12 @@ sub process { # Find out what is on the end of the line after the # conditional. - substr($s, 0, length($c)) = ''; + substr($s, 0, length($c), ''); $s =~ s/\n.*//g; $s =~ s/$;//g; # Remove any comments - if (length($c) && $s !~ /^\s*({|;|)\s*\\*\s*$/) { + if (length($c) && $s !~ /^\s*({|;|)\s*\\*\s*$/ && + $c !~ /^.\#\s*if/) + { ERROR("trailing statements should be on next line\n" . $herecurr); } } @@ -1607,7 +1672,7 @@ sub process { # Find out what is on the end of the line after the # conditional. - substr($s, 0, length($c)) = ''; + substr($s, 0, length($c), ''); $s =~ s/\n.*//g; if ($s =~ /^\s*;/) { @@ -1631,7 +1696,7 @@ sub process { if ($tree && $rawline =~ m{^.\#\s*include\s*\<asm\/(.*)\.h\>}) { my $checkfile = "$root/include/linux/$1.h"; if (-f $checkfile && $1 ne 'irq.h') { - CHK("Use #include <linux/$1.h> instead of <asm/$1.h>\n" . + WARN("Use #include <linux/$1.h> instead of <asm/$1.h>\n" . $herecurr); } } @@ -1692,15 +1757,24 @@ sub process { if ($#chunks > 0 && $level == 0) { my $allowed = 0; my $seen = 0; - my $herectx = $here . "\n";; + my $herectx = $here . "\n"; my $ln = $linenr - 1; for my $chunk (@chunks) { my ($cond, $block) = @{$chunk}; - $herectx .= "$rawlines[$ln]\n[...]\n"; + # If the condition carries leading newlines, then count those as offsets. + my ($whitespace) = ($cond =~ /^((?:\s*\n[+-])*\s*)/s); + my $offset = statement_rawlines($whitespace) - 1; + + #print "COND<$cond> whitespace<$whitespace> offset<$offset>\n"; + + # We have looked at and allowed this specific line. + $suppress_ifbraces{$ln + $offset} = 1; + + $herectx .= "$rawlines[$ln + $offset]\n[...]\n"; $ln += statement_rawlines($block) - 1; - substr($block, 0, length($cond)) = ''; + substr($block, 0, length($cond), ''); $seen++ if ($block =~ /^\s*{/); @@ -1721,16 +1795,10 @@ sub process { if ($seen && !$allowed) { WARN("braces {} are not necessary for any arm of this statement\n" . $herectx); } - # Either way we have looked over this whole - # statement and said what needs to be said. - $suppress_ifbraces = $endln; } } - if ($linenr > $suppress_ifbraces && + if (!defined $suppress_ifbraces{$linenr - 1} && $line =~ /\b(if|while|for|else)\b/) { - my ($level, $endln, @chunks) = - ctx_statement_full($linenr, $realcnt, $-[0]); - my $allowed = 0; # Check the pre-context. @@ -1738,10 +1806,15 @@ sub process { #print "APW: ALLOWED: pre<$1>\n"; $allowed = 1; } + + my ($level, $endln, @chunks) = + ctx_statement_full($linenr, $realcnt, $-[0]); + # Check the condition. my ($cond, $block) = @{$chunks[0]}; + #print "CHECKING<$linenr> cond<$cond> block<$block>\n"; if (defined $cond) { - substr($block, 0, length($cond)) = ''; + substr($block, 0, length($cond), ''); } if (statement_lines($cond) > 1) { #print "APW: ALLOWED: cond<$cond>\n"; @@ -1759,7 +1832,7 @@ sub process { if (defined $chunks[1]) { my ($cond, $block) = @{$chunks[1]}; if (defined $cond) { - substr($block, 0, length($cond)) = ''; + substr($block, 0, length($cond), ''); } if ($block =~ /^\s*\{/) { #print "APW: ALLOWED: chunk-1 block<$block>\n"; @@ -1882,6 +1955,28 @@ sub process { if ($line =~ /__FUNCTION__/) { WARN("__func__ should be used instead of gcc specific __FUNCTION__\n" . $herecurr); } + +# check for semaphores used as mutexes + if ($line =~ /\b(DECLARE_MUTEX|init_MUTEX)\s*\(/) { + WARN("mutexes are preferred for single holder semaphores\n" . $herecurr); + } +# check for semaphores used as mutexes + if ($line =~ /\binit_MUTEX_LOCKED\s*\(/) { + WARN("consider using a completion\n" . $herecurr); + } +# recommend strict_strto* over simple_strto* + if ($line =~ /\bsimple_(strto.*?)\s*\(/) { + WARN("consider using strict_$1 in preference to simple_$1\n" . $herecurr); + } + +# use of NR_CPUS is usually wrong +# ignore definitions of NR_CPUS and usage to define arrays as likely right + if ($line =~ /\bNR_CPUS\b/ && + $line !~ /^.#\s*define\s+NR_CPUS\s+/ && + $line !~ /^.\s*$Declare\s.*\[[^\]]*NR_CPUS[^\]]*\]/) + { + WARN("usage of NR_CPUS is often wrong - consider using cpu_possible(), num_possible_cpus(), for_each_possible_cpu(), etc\n" . $herecurr); + } } # If we have no input at all, then there is nothing to report on |