diff options
Diffstat (limited to 'Documentation')
38 files changed, 2707 insertions, 513 deletions
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index cbbd3e069945..5f3bedaf8e35 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -94,28 +94,37 @@ What: /sys/block/<disk>/queue/physical_block_size Date: May 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: - This is the smallest unit the storage device can write - without resorting to read-modify-write operation. It is - usually the same as the logical block size but may be - bigger. One example is SATA drives with 4KB sectors - that expose a 512-byte logical block size to the - operating system. + This is the smallest unit a physical storage device can + write atomically. It is usually the same as the logical + block size but may be bigger. One example is SATA + drives with 4KB sectors that expose a 512-byte logical + block size to the operating system. For stacked block + devices the physical_block_size variable contains the + maximum physical_block_size of the component devices. What: /sys/block/<disk>/queue/minimum_io_size Date: April 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: - Storage devices may report a preferred minimum I/O size, - which is the smallest request the device can perform - without incurring a read-modify-write penalty. For disk - drives this is often the physical block size. For RAID - arrays it is often the stripe chunk size. + Storage devices may report a granularity or preferred + minimum I/O size which is the smallest request the + device can perform without incurring a performance + penalty. For disk drives this is often the physical + block size. For RAID arrays it is often the stripe + chunk size. A properly aligned multiple of + minimum_io_size is the preferred request size for + workloads where a high number of I/O operations is + desired. What: /sys/block/<disk>/queue/optimal_io_size Date: April 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: Storage devices may report an optimal I/O size, which is - the device's preferred unit of receiving I/O. This is - rarely reported for disk drives. For RAID devices it is - usually the stripe width or the internal block size. + the device's preferred unit for sustained I/O. This is + rarely reported for disk drives. For RAID arrays it is + usually the stripe width or the internal track size. A + properly aligned multiple of optimal_io_size is the + preferred request size for workloads where sustained + throughput is desired. If no optimal I/O size is + reported this file contains 0. diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index 6bf68053e4b8..25be3250f7d6 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -84,6 +84,16 @@ Description: from this part of the device tree. Depends on CONFIG_HOTPLUG. +What: /sys/bus/pci/devices/.../reset +Date: July 2009 +Contact: Michael S. Tsirkin <mst@redhat.com> +Description: + Some devices allow an individual function to be reset + without affecting other functions in the same device. + For devices that have this support, a file named reset + will be present in sysfs. Writing 1 to this file + will perform reset. + What: /sys/bus/pci/devices/.../vpd Date: February 2008 Contact: Ben Hutchings <bhutchings@solarflare.com> diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index a50d6cd58573..992e67e6be7f 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -449,8 +449,8 @@ printk(KERN_INFO "i = %u\n", i); </para> <programlisting> -__u32 ipaddress; -printk(KERN_INFO "my ip: %d.%d.%d.%d\n", NIPQUAD(ipaddress)); +__be32 ipaddress; +printk(KERN_INFO "my ip: %pI4\n", &ipaddress); </programlisting> <para> diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt index 93cb28d05dcd..18f9651ff23d 100644 --- a/Documentation/RCU/rculist_nulls.txt +++ b/Documentation/RCU/rculist_nulls.txt @@ -83,11 +83,12 @@ not detect it missed following items in original chain. obj = kmem_cache_alloc(...); lock_chain(); // typically a spin_lock() obj->key = key; -atomic_inc(&obj->refcnt); /* * we need to make sure obj->key is updated before obj->next + * or obj->refcnt */ smp_wmb(); +atomic_set(&obj->refcnt, 1); hlist_add_head_rcu(&obj->obj_node, list); unlock_chain(); // typically a spin_unlock() @@ -159,6 +160,10 @@ out: obj = kmem_cache_alloc(cachep); lock_chain(); // typically a spin_lock() obj->key = key; +/* + * changes to obj->key must be visible before refcnt one + */ +smp_wmb(); atomic_set(&obj->refcnt, 1); /* * insert obj in RCU way (readers might be traversing chain) diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt index 43cb1004d35f..9d58c7c5eddd 100644 --- a/Documentation/arm/memory.txt +++ b/Documentation/arm/memory.txt @@ -21,6 +21,8 @@ ffff8000 ffffffff copy_user_page / clear_user_page use. For SA11xx and Xscale, this is used to setup a minicache mapping. +ffff4000 ffffffff cache aliasing on ARMv6 and later CPUs. + ffff1000 ffff7fff Reserved. Platforms must not use this address range. diff --git a/Documentation/connector/Makefile b/Documentation/connector/Makefile index 8df1a7285a06..d98e4df98e24 100644 --- a/Documentation/connector/Makefile +++ b/Documentation/connector/Makefile @@ -9,3 +9,8 @@ hostprogs-y := ucon always := $(hostprogs-y) HOSTCFLAGS_ucon.o += -I$(objtree)/usr/include + +all: modules + +modules clean: + $(MAKE) -C ../.. SUBDIRS=$(PWD) $@ diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index f688eba87704..1711adc33373 100644 --- a/Documentation/connector/cn_test.c +++ b/Documentation/connector/cn_test.c @@ -1,7 +1,7 @@ /* * cn_test.c * - * 2004-2005 Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru> + * 2004+ Copyright (c) Evgeniy Polyakov <zbr@ioremap.net> * All rights reserved. * * This program is free software; you can redistribute it and/or modify @@ -19,6 +19,8 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#define pr_fmt(fmt) "cn_test: " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -27,18 +29,17 @@ #include <linux/connector.h> -static struct cb_id cn_test_id = { 0x123, 0x456 }; +static struct cb_id cn_test_id = { CN_NETLINK_USERS + 3, 0x456 }; static char cn_test_name[] = "cn_test"; static struct sock *nls; static struct timer_list cn_test_timer; -void cn_test_callback(void *data) +static void cn_test_callback(struct cn_msg *msg) { - struct cn_msg *msg = (struct cn_msg *)data; - - printk("%s: %lu: idx=%x, val=%x, seq=%u, ack=%u, len=%d: %s.\n", - __func__, jiffies, msg->id.idx, msg->id.val, - msg->seq, msg->ack, msg->len, (char *)msg->data); + pr_info("%s: %lu: idx=%x, val=%x, seq=%u, ack=%u, len=%d: %s.\n", + __func__, jiffies, msg->id.idx, msg->id.val, + msg->seq, msg->ack, msg->len, + msg->len ? (char *)msg->data : ""); } /* @@ -63,9 +64,7 @@ static int cn_test_want_notify(void) skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { - printk(KERN_ERR "Failed to allocate new skb with size=%u.\n", - size); - + pr_err("failed to allocate new skb with size=%u\n", size); return -ENOMEM; } @@ -114,12 +113,12 @@ static int cn_test_want_notify(void) //netlink_broadcast(nls, skb, 0, ctl->group, GFP_ATOMIC); netlink_unicast(nls, skb, 0, 0); - printk(KERN_INFO "Request was sent. Group=0x%x.\n", ctl->group); + pr_info("request was sent: group=0x%x\n", ctl->group); return 0; nlmsg_failure: - printk(KERN_ERR "Failed to send %u.%u\n", msg->seq, msg->ack); + pr_err("failed to send %u.%u\n", msg->seq, msg->ack); kfree_skb(skb); return -EINVAL; } @@ -131,6 +130,8 @@ static void cn_test_timer_func(unsigned long __data) struct cn_msg *m; char data[32]; + pr_debug("%s: timer fired with data %lu\n", __func__, __data); + m = kzalloc(sizeof(*m) + sizeof(data), GFP_ATOMIC); if (m) { @@ -150,7 +151,7 @@ static void cn_test_timer_func(unsigned long __data) cn_test_timer_counter++; - mod_timer(&cn_test_timer, jiffies + HZ); + mod_timer(&cn_test_timer, jiffies + msecs_to_jiffies(1000)); } static int cn_test_init(void) @@ -168,8 +169,10 @@ static int cn_test_init(void) } setup_timer(&cn_test_timer, cn_test_timer_func, 0); - cn_test_timer.expires = jiffies + HZ; - add_timer(&cn_test_timer); + mod_timer(&cn_test_timer, jiffies + msecs_to_jiffies(1000)); + + pr_info("initialized with id={%u.%u}\n", + cn_test_id.idx, cn_test_id.val); return 0; @@ -194,5 +197,5 @@ module_init(cn_test_init); module_exit(cn_test_fini); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>"); +MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>"); MODULE_DESCRIPTION("Connector's test module"); diff --git a/Documentation/connector/connector.txt b/Documentation/connector/connector.txt index ad6e0ba7b38c..81e6bf6ead57 100644 --- a/Documentation/connector/connector.txt +++ b/Documentation/connector/connector.txt @@ -5,10 +5,10 @@ Kernel Connector. Kernel connector - new netlink based userspace <-> kernel space easy to use communication module. -Connector driver adds possibility to connect various agents using -netlink based network. One must register callback and -identifier. When driver receives special netlink message with -appropriate identifier, appropriate callback will be called. +The Connector driver makes it easy to connect various agents using a +netlink based network. One must register a callback and an identifier. +When the driver receives a special netlink message with the appropriate +identifier, the appropriate callback will be called. From the userspace point of view it's quite straightforward: @@ -17,10 +17,10 @@ From the userspace point of view it's quite straightforward: send(); recv(); -But if kernelspace want to use full power of such connections, driver -writer must create special sockets, must know about struct sk_buff -handling... Connector allows any kernelspace agents to use netlink -based networking for inter-process communication in a significantly +But if kernelspace wants to use the full power of such connections, the +driver writer must create special sockets, must know about struct sk_buff +handling, etc... The Connector driver allows any kernelspace agents to use +netlink based networking for inter-process communication in a significantly easier way: int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); @@ -32,15 +32,15 @@ struct cb_id __u32 val; }; -idx and val are unique identifiers which must be registered in -connector.h for in-kernel usage. void (*callback) (void *) - is a -callback function which will be called when message with above idx.val -will be received by connector core. Argument for that function must +idx and val are unique identifiers which must be registered in the +connector.h header for in-kernel usage. void (*callback) (void *) is a +callback function which will be called when a message with above idx.val +is received by the connector core. The argument for that function must be dereferenced to struct cn_msg *. struct cn_msg { - struct cb_id id; + struct cb_id id; __u32 seq; __u32 ack; @@ -55,92 +55,95 @@ Connector interfaces. int cn_add_callback(struct cb_id *id, char *name, void (*callback) (void *)); -Registers new callback with connector core. + Registers new callback with connector core. -struct cb_id *id - unique connector's user identifier. - It must be registered in connector.h for legal in-kernel users. -char *name - connector's callback symbolic name. -void (*callback) (void *) - connector's callback. + struct cb_id *id - unique connector's user identifier. + It must be registered in connector.h for legal in-kernel users. + char *name - connector's callback symbolic name. + void (*callback) (void *) - connector's callback. Argument must be dereferenced to struct cn_msg *. + void cn_del_callback(struct cb_id *id); -Unregisters new callback with connector core. + Unregisters new callback with connector core. + + struct cb_id *id - unique connector's user identifier. -struct cb_id *id - unique connector's user identifier. int cn_netlink_send(struct cn_msg *msg, u32 __groups, int gfp_mask); -Sends message to the specified groups. It can be safely called from -softirq context, but may silently fail under strong memory pressure. -If there are no listeners for given group -ESRCH can be returned. + Sends message to the specified groups. It can be safely called from + softirq context, but may silently fail under strong memory pressure. + If there are no listeners for given group -ESRCH can be returned. -struct cn_msg * - message header(with attached data). -u32 __group - destination group. + struct cn_msg * - message header(with attached data). + u32 __group - destination group. If __group is zero, then appropriate group will be searched through all registered connector users, and message will be delivered to the group which was created for user with the same ID as in msg. If __group is not zero, then message will be delivered to the specified group. -int gfp_mask - GFP mask. + int gfp_mask - GFP mask. -Note: When registering new callback user, connector core assigns -netlink group to the user which is equal to it's id.idx. + Note: When registering new callback user, connector core assigns + netlink group to the user which is equal to it's id.idx. /*****************************************/ Protocol description. /*****************************************/ -Current offers transport layer with fixed header. Recommended -protocol which uses such header is following: +The current framework offers a transport layer with fixed headers. The +recommended protocol which uses such a header is as following: msg->seq and msg->ack are used to determine message genealogy. When -someone sends message it puts there locally unique sequence and random -acknowledge numbers. Sequence number may be copied into +someone sends a message, they use a locally unique sequence and random +acknowledge number. The sequence number may be copied into nlmsghdr->nlmsg_seq too. -Sequence number is incremented with each message to be sent. +The sequence number is incremented with each message sent. -If we expect reply to our message, then sequence number in received -message MUST be the same as in original message, and acknowledge -number MUST be the same + 1. +If you expect a reply to the message, then the sequence number in the +received message MUST be the same as in the original message, and the +acknowledge number MUST be the same + 1. -If we receive message and it's sequence number is not equal to one we -are expecting, then it is new message. If we receive message and it's -sequence number is the same as one we are expecting, but it's -acknowledge is not equal acknowledge number in original message + 1, -then it is new message. +If we receive a message and its sequence number is not equal to one we +are expecting, then it is a new message. If we receive a message and +its sequence number is the same as one we are expecting, but its +acknowledge is not equal to the acknowledge number in the original +message + 1, then it is a new message. -Obviously, protocol header contains above id. +Obviously, the protocol header contains the above id. -connector allows event notification in the following form: kernel +The connector allows event notification in the following form: kernel driver or userspace process can ask connector to notify it when -selected id's will be turned on or off(registered or unregistered it's -callback). It is done by sending special command to connector -driver(it also registers itself with id={-1, -1}). +selected ids will be turned on or off (registered or unregistered its +callback). It is done by sending a special command to the connector +driver (it also registers itself with id={-1, -1}). -As example of usage Documentation/connector now contains cn_test.c - -testing module which uses connector to request notification and to -send messages. +As example of this usage can be found in the cn_test.c module which +uses the connector to request notification and to send messages. /*****************************************/ Reliability. /*****************************************/ -Netlink itself is not reliable protocol, that means that messages can +Netlink itself is not a reliable protocol. That means that messages can be lost due to memory pressure or process' receiving queue overflowed, -so caller is warned must be prepared. That is why struct cn_msg [main -connector's message header] contains u32 seq and u32 ack fields. +so caller is warned that it must be prepared. That is why the struct +cn_msg [main connector's message header] contains u32 seq and u32 ack +fields. /*****************************************/ Userspace usage. /*****************************************/ + 2.6.14 has a new netlink socket implementation, which by default does not -allow to send data to netlink groups other than 1. -So, if to use netlink socket (for example using connector) -with different group number userspace application must subscribe to -that group. It can be achieved by following pseudocode: +allow people to send data to netlink groups other than 1. +So, if you wish to use a netlink socket (for example using connector) +with a different group number, the userspace application must subscribe to +that group first. It can be achieved by the following pseudocode: s = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR); @@ -160,8 +163,8 @@ if (bind(s, (struct sockaddr *)&l_local, sizeof(struct sockaddr_nl)) == -1) { } Where 270 above is SOL_NETLINK, and 1 is a NETLINK_ADD_MEMBERSHIP socket -option. To drop multicast subscription one should call above socket option -with NETLINK_DROP_MEMBERSHIP parameter which is defined as 0. +option. To drop a multicast subscription, one should call the above socket +option with the NETLINK_DROP_MEMBERSHIP parameter which is defined as 0. 2.6.14 netlink code only allows to select a group which is less or equal to the maximum group number, which is used at netlink_kernel_create() time. diff --git a/Documentation/connector/ucon.c b/Documentation/connector/ucon.c index d738cde2a8d5..4848db8c71ff 100644 --- a/Documentation/connector/ucon.c +++ b/Documentation/connector/ucon.c @@ -1,7 +1,7 @@ /* * ucon.c * - * Copyright (c) 2004+ Evgeniy Polyakov <johnpol@2ka.mipt.ru> + * Copyright (c) 2004+ Evgeniy Polyakov <zbr@ioremap.net> * * * This program is free software; you can redistribute it and/or modify @@ -30,18 +30,24 @@ #include <arpa/inet.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <errno.h> #include <time.h> +#include <getopt.h> #include <linux/connector.h> #define DEBUG #define NETLINK_CONNECTOR 11 +/* Hopefully your userspace connector.h matches this kernel */ +#define CN_TEST_IDX CN_NETLINK_USERS + 3 +#define CN_TEST_VAL 0x456 + #ifdef DEBUG #define ulog(f, a...) fprintf(stdout, f, ##a) #else @@ -83,6 +89,25 @@ static int netlink_send(int s, struct cn_msg *msg) return err; } +static void usage(void) +{ + printf( + "Usage: ucon [options] [output file]\n" + "\n" + "\t-h\tthis help screen\n" + "\t-s\tsend buffers to the test module\n" + "\n" + "The default behavior of ucon is to subscribe to the test module\n" + "and wait for state messages. Any ones received are dumped to the\n" + "specified output file (or stdout). The test module is assumed to\n" + "have an id of {%u.%u}\n" + "\n" + "If you get no output, then verify the cn_test module id matches\n" + "the expected id above.\n" + , CN_TEST_IDX, CN_TEST_VAL + ); +} + int main(int argc, char *argv[]) { int s; @@ -94,17 +119,34 @@ int main(int argc, char *argv[]) FILE *out; time_t tm; struct pollfd pfd; + bool send_msgs = false; - if (argc < 2) - out = stdout; - else { - out = fopen(argv[1], "a+"); + while ((s = getopt(argc, argv, "hs")) != -1) { + switch (s) { + case 's': + send_msgs = true; + break; + + case 'h': + usage(); + return 0; + + default: + /* getopt() outputs an error for us */ + usage(); + return 1; + } + } + + if (argc != optind) { + out = fopen(argv[optind], "a+"); if (!out) { ulog("Unable to open %s for writing: %s\n", argv[1], strerror(errno)); out = stdout; } - } + } else + out = stdout; memset(buf, 0, sizeof(buf)); @@ -115,9 +157,11 @@ int main(int argc, char *argv[]) } l_local.nl_family = AF_NETLINK; - l_local.nl_groups = 0x123; /* bitmask of requested groups */ + l_local.nl_groups = -1; /* bitmask of requested groups */ l_local.nl_pid = 0; + ulog("subscribing to %u.%u\n", CN_TEST_IDX, CN_TEST_VAL); + if (bind(s, (struct sockaddr *)&l_local, sizeof(struct sockaddr_nl)) == -1) { perror("bind"); close(s); @@ -130,15 +174,15 @@ int main(int argc, char *argv[]) setsockopt(s, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &on, sizeof(on)); } #endif - if (0) { + if (send_msgs) { int i, j; memset(buf, 0, sizeof(buf)); data = (struct cn_msg *)buf; - data->id.idx = 0x123; - data->id.val = 0x456; + data->id.idx = CN_TEST_IDX; + data->id.val = CN_TEST_VAL; data->seq = seq++; data->ack = 0; data->len = 0; diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt index 5d5f5fadd1c2..2a5b850847c0 100644 --- a/Documentation/cpu-freq/user-guide.txt +++ b/Documentation/cpu-freq/user-guide.txt @@ -176,7 +176,9 @@ scaling_governor, and by "echoing" the name of another work on some specific architectures or processors. -cpuinfo_cur_freq : Current speed of the CPU, in KHz. +cpuinfo_cur_freq : Current frequency of the CPU as obtained from + the hardware, in KHz. This is the frequency + the CPU actually runs at. scaling_available_frequencies : List of available frequencies, in KHz. @@ -196,7 +198,10 @@ related_cpus : List of CPUs that need some sort of frequency scaling_driver : Hardware driver for cpufreq. -scaling_cur_freq : Current frequency of the CPU, in KHz. +scaling_cur_freq : Current frequency of the CPU as determined by + the governor and cpufreq core, in KHz. This is + the frequency the kernel thinks the CPU runs + at. If you have selected the "userspace" governor which allows you to set the CPU operating frequency to a specific value, you can read out diff --git a/Documentation/dontdiff b/Documentation/dontdiff index 88519daab6e9..6fef118371e3 100644 --- a/Documentation/dontdiff +++ b/Documentation/dontdiff @@ -68,7 +68,6 @@ autoconf.h* bbootsect bin2c binkernel.spec -binoffset bootsect bounds.h bsetup diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 09e031c55887..b3b62903f08c 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -206,24 +206,6 @@ Who: Len Brown <len.brown@intel.com> --------------------------- -What: libata spindown skipping and warning -When: Dec 2008 -Why: Some halt(8) implementations synchronize caches for and spin - down libata disks because libata didn't use to spin down disk on - system halt (only synchronized caches). - Spin down on system halt is now implemented. sysfs node - /sys/class/scsi_disk/h:c:i:l/manage_start_stop is present if - spin down support is available. - Because issuing spin down command to an already spun down disk - makes some disks spin up just to spin down again, libata tracks - device spindown status to skip the extra spindown command and - warn about it. - This is to give userspace tools the time to get updated and will - be removed after userspace is reasonably updated. -Who: Tejun Heo <htejun@gmail.com> - ---------------------------- - What: i386/x86_64 bzImage symlinks When: April 2010 diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 7e81e37c0b1e..b245d524d568 100644 --- a/Documentation/filesystems/sysfs.txt +++ b/Documentation/filesystems/sysfs.txt @@ -23,7 +23,8 @@ interface. Using sysfs ~~~~~~~~~~~ -sysfs is always compiled in. You can access it by doing: +sysfs is always compiled in if CONFIG_SYSFS is defined. You can access +it by doing: mount -t sysfs sysfs /sys diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index b58b84b50fa2..eed520fd0c8e 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -102,7 +102,7 @@ shortname=lower|win95|winnt|mixed winnt: emulate the Windows NT rule for display/create. mixed: emulate the Windows NT rule for display, emulate the Windows 95 rule for create. - Default setting is `lower'. + Default setting is `mixed'. tz=UTC -- Interpret timestamps as UTC rather than local time. This option disables the conversion of timestamps diff --git a/Documentation/hwmon/tmp421 b/Documentation/hwmon/tmp421 new file mode 100644 index 000000000000..0cf07f824741 --- /dev/null +++ b/Documentation/hwmon/tmp421 @@ -0,0 +1,36 @@ +Kernel driver tmp421 +==================== + +Supported chips: + * Texas Instruments TMP421 + Prefix: 'tmp421' + Addresses scanned: I2C 0x2a, 0x4c, 0x4d, 0x4e and 0x4f + Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html + * Texas Instruments TMP422 + Prefix: 'tmp422' + Addresses scanned: I2C 0x2a, 0x4c, 0x4d, 0x4e and 0x4f + Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html + * Texas Instruments TMP423 + Prefix: 'tmp423' + Addresses scanned: I2C 0x2a, 0x4c, 0x4d, 0x4e and 0x4f + Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html + +Authors: + Andre Prendel <andre.prendel@gmx.de> + +Description +----------- + +This driver implements support for Texas Instruments TMP421, TMP422 +and TMP423 temperature sensor chips. These chips implement one local +and up to one (TMP421), up to two (TMP422) or up to three (TMP423) +remote sensors. Temperature is measured in degrees Celsius. The chips +are wired over I2C/SMBus and specified over a temperature range of -40 +to +125 degrees Celsius. Resolution for both the local and remote +channels is 0.0625 degree C. + +The chips support only temperature measurement. The driver exports +the temperature values via the following sysfs files: + +temp[1-4]_input +temp[2-4]_fault diff --git a/Documentation/hwmon/wm831x b/Documentation/hwmon/wm831x new file mode 100644 index 000000000000..24f47d8f6a42 --- /dev/null +++ b/Documentation/hwmon/wm831x @@ -0,0 +1,37 @@ +Kernel driver wm831x-hwmon +========================== + +Supported chips: + * Wolfson Microelectronics WM831x PMICs + Prefix: 'wm831x' + Datasheet: + http://www.wolfsonmicro.com/products/WM8310 + http://www.wolfsonmicro.com/products/WM8311 + http://www.wolfsonmicro.com/products/WM8312 + +Authors: Mark Brown <broonie@opensource.wolfsonmicro.com> + +Description +----------- + +The WM831x series of PMICs include an AUXADC which can be used to +monitor a range of system operating parameters, including the voltages +of the major supplies within the system. Currently the driver provides +reporting of all the input values but does not provide any alarms. + +Voltage Monitoring +------------------ + +Voltages are sampled by a 12 bit ADC. Voltages in milivolts are 1.465 +times the ADC value. + +Temperature Monitoring +---------------------- + +Temperatures are sampled by a 12 bit ADC. Chip and battery temperatures +are available. The chip temperature is calculated as: + + Degrees celsius = (512.18 - data) / 1.0983 + +while the battery temperature calculation will depend on the NTC +thermistor component. diff --git a/Documentation/hwmon/wm8350 b/Documentation/hwmon/wm8350 new file mode 100644 index 000000000000..98f923bd2e92 --- /dev/null +++ b/Documentation/hwmon/wm8350 @@ -0,0 +1,26 @@ +Kernel driver wm8350-hwmon +========================== + +Supported chips: + * Wolfson Microelectronics WM835x PMICs + Prefix: 'wm8350' + Datasheet: + http://www.wolfsonmicro.com/products/WM8350 + http://www.wolfsonmicro.com/products/WM8351 + http://www.wolfsonmicro.com/products/WM8352 + +Authors: Mark Brown <broonie@opensource.wolfsonmicro.com> + +Description +----------- + +The WM835x series of PMICs include an AUXADC which can be used to +monitor a range of system operating parameters, including the voltages +of the major supplies within the system. Currently the driver provides +simple access to these major supplies. + +Voltage Monitoring +------------------ + +Voltages are sampled by a 12 bit ADC. For the internal supplies the ADC +is referenced to the system VRTC. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index dd1a6d4bb747..f8e63d63d517 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -57,6 +57,7 @@ parameter is applicable: ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. JOY Appropriate joystick support is enabled. + KVM Kernel Virtual Machine support is enabled. LIBATA Libata driver is enabled LP Printer support is enabled. LOOP Loopback device support is enabled. @@ -1098,6 +1099,44 @@ and is between 256 and 4096 characters. It is defined in the file kstack=N [X86] Print N words from the kernel stack in oops dumps. + kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. + Default is 0 (don't ignore, but inject #GP) + + kvm.oos_shadow= [KVM] Disable out-of-sync shadow paging. + Default is 1 (enabled) + + kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM. + Default is 0 (off) + + kvm-amd.npt= [KVM,AMD] Disable nested paging (virtualized MMU) + for all guests. + Default is 1 (enabled) if in 64bit or 32bit-PAE mode + + kvm-intel.bypass_guest_pf= + [KVM,Intel] Disables bypassing of guest page faults + on Intel chips. Default is 1 (enabled) + + kvm-intel.ept= [KVM,Intel] Disable extended page tables + (virtualized MMU) support on capable Intel chips. + Default is 1 (enabled) + + kvm-intel.emulate_invalid_guest_state= + [KVM,Intel] Enable emulation of invalid guest states + Default is 0 (disabled) + + kvm-intel.flexpriority= + [KVM,Intel] Disable FlexPriority feature (TPR shadow). + Default is 1 (enabled) + + kvm-intel.unrestricted_guest= + [KVM,Intel] Disable unrestricted guest feature + (virtualized real and unpaged mode) on capable + Intel chips. Default is 1 (enabled) + + kvm-intel.vpid= [KVM,Intel] Disable Virtual Processor Identification + feature (tagged TLBs) on capable Intel chips. + Default is 1 (enabled) + l2cr= [PPC] l3cr= [PPC] @@ -1531,6 +1570,11 @@ and is between 256 and 4096 characters. It is defined in the file symbolic names: lapic and ioapic Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic + netpoll.carrier_timeout= + [NET] Specifies amount of time (in seconds) that + netpoll should wait for a carrier. By default netpoll + waits 4 seconds. + no387 [BUGS=X86-32] Tells the kernel to use the 387 maths emulation library even if a 387 maths coprocessor is present. diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt new file mode 100644 index 000000000000..1b1c22da211b --- /dev/null +++ b/Documentation/kvm/api.txt @@ -0,0 +1,683 @@ +The Definitive KVM (Kernel-based Virtual Machine) API Documentation +=================================================================== + +1. General description + +The kvm API is a set of ioctls that are issued to control various aspects +of a virtual machine. The ioctls belong to three classes + + - System ioctls: These query and set global attributes which affect the + whole kvm subsystem. In addition a system ioctl is used to create + virtual machines + + - VM ioctls: These query and set attributes that affect an entire virtual + machine, for example memory layout. In addition a VM ioctl is used to + create virtual cpus (vcpus). + + Only run VM ioctls from the same process (address space) that was used + to create the VM. + + - vcpu ioctls: These query and set attributes that control the operation + of a single virtual cpu. + + Only run vcpu ioctls from the same thread that was used to create the + vcpu. + +2. File descritpors + +The kvm API is centered around file descriptors. An initial +open("/dev/kvm") obtains a handle to the kvm subsystem; this handle +can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this +handle will create a VM file descripror which can be used to issue VM +ioctls. A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu +and return a file descriptor pointing to it. Finally, ioctls on a vcpu +fd can be used to control the vcpu, including the important task of +actually running guest code. + +In general file descriptors can be migrated among processes by means +of fork() and the SCM_RIGHTS facility of unix domain socket. These +kinds of tricks are explicitly not supported by kvm. While they will +not cause harm to the host, their actual behavior is not guaranteed by +the API. The only supported use is one virtual machine per process, +and one vcpu per thread. + +3. Extensions + +As of Linux 2.6.22, the KVM ABI has been stabilized: no backward +incompatible change are allowed. However, there is an extension +facility that allows backward-compatible extensions to the API to be +queried and used. + +The extension mechanism is not based on on the Linux version number. +Instead, kvm defines extension identifiers and a facility to query +whether a particular extension identifier is available. If it is, a +set of ioctls is available for application use. + +4. API description + +This section describes ioctls that can be used to control kvm guests. +For each ioctl, the following information is provided along with a +description: + + Capability: which KVM extension provides this ioctl. Can be 'basic', + which means that is will be provided by any kernel that supports + API version 12 (see section 4.1), or a KVM_CAP_xyz constant, which + means availability needs to be checked with KVM_CHECK_EXTENSION + (see section 4.4). + + Architectures: which instruction set architectures provide this ioctl. + x86 includes both i386 and x86_64. + + Type: system, vm, or vcpu. + + Parameters: what parameters are accepted by the ioctl. + + Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL) + are not detailed, but errors with specific meanings are. + +4.1 KVM_GET_API_VERSION + +Capability: basic +Architectures: all +Type: system ioctl +Parameters: none +Returns: the constant KVM_API_VERSION (=12) + +This identifies the API version as the stable kvm API. It is not +expected that this number will change. However, Linux 2.6.20 and +2.6.21 report earlier versions; these are not documented and not +supported. Applications should refuse to run if KVM_GET_API_VERSION +returns a value other than 12. If this check passes, all ioctls +described as 'basic' will be available. + +4.2 KVM_CREATE_VM + +Capability: basic +Architectures: all +Type: system ioctl +Parameters: none +Returns: a VM fd that can be used to control the new virtual machine. + +The new VM has no virtual cpus and no memory. An mmap() of a VM fd +will access the virtual machine's physical address space; offset zero +corresponds to guest physical address zero. Use of mmap() on a VM fd +is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is +available. + +4.3 KVM_GET_MSR_INDEX_LIST + +Capability: basic +Architectures: x86 +Type: system +Parameters: struct kvm_msr_list (in/out) +Returns: 0 on success; -1 on error +Errors: + E2BIG: the msr index list is to be to fit in the array specified by + the user. + +struct kvm_msr_list { + __u32 nmsrs; /* number of msrs in entries */ + __u32 indices[0]; +}; + +This ioctl returns the guest msrs that are supported. The list varies +by kvm version and host processor, but does not change otherwise. The +user fills in the size of the indices array in nmsrs, and in return +kvm adjusts nmsrs to reflect the actual number of msrs and fills in +the indices array with their numbers. + +4.4 KVM_CHECK_EXTENSION + +Capability: basic +Architectures: all +Type: system ioctl +Parameters: extension identifier (KVM_CAP_*) +Returns: 0 if unsupported; 1 (or some other positive integer) if supported + +The API allows the application to query about extensions to the core +kvm API. Userspace passes an extension identifier (an integer) and +receives an integer that describes the extension availability. +Generally 0 means no and 1 means yes, but some extensions may report +additional information in the integer return value. + +4.5 KVM_GET_VCPU_MMAP_SIZE + +Capability: basic +Architectures: all +Type: system ioctl +Parameters: none +Returns: size of vcpu mmap area, in bytes + +The KVM_RUN ioctl (cf.) communicates with userspace via a shared +memory region. This ioctl returns the size of that region. See the +KVM_RUN documentation for details. + +4.6 KVM_SET_MEMORY_REGION + +Capability: basic +Architectures: all +Type: vm ioctl +Parameters: struct kvm_memory_region (in) +Returns: 0 on success, -1 on error + +struct kvm_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ +}; + +/* for kvm_memory_region::flags */ +#define KVM_MEM_LOG_DIRTY_PAGES 1UL + +This ioctl allows the user to create or modify a guest physical memory +slot. When changing an existing slot, it may be moved in the guest +physical memory space, or its flags may be modified. It may not be +resized. Slots may not overlap. + +The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which +instructs kvm to keep track of writes to memory within the slot. See +the KVM_GET_DIRTY_LOG ioctl. + +It is recommended to use the KVM_SET_USER_MEMORY_REGION ioctl instead +of this API, if available. This newer API allows placing guest memory +at specified locations in the host address space, yielding better +control and easy access. + +4.6 KVM_CREATE_VCPU + +Capability: basic +Architectures: all +Type: vm ioctl +Parameters: vcpu id (apic id on x86) +Returns: vcpu fd on success, -1 on error + +This API adds a vcpu to a virtual machine. The vcpu id is a small integer +in the range [0, max_vcpus). + +4.7 KVM_GET_DIRTY_LOG (vm ioctl) + +Capability: basic +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_dirty_log (in/out) +Returns: 0 on success, -1 on error + +/* for KVM_GET_DIRTY_LOG */ +struct kvm_dirty_log { + __u32 slot; + __u32 padding; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding; + }; +}; + +Given a memory slot, return a bitmap containing any pages dirtied +since the last call to this ioctl. Bit 0 is the first page in the +memory slot. Ensure the entire structure is cleared to avoid padding +issues. + +4.8 KVM_SET_MEMORY_ALIAS + +Capability: basic +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_memory_alias (in) +Returns: 0 (success), -1 (error) + +struct kvm_memory_alias { + __u32 slot; /* this has a different namespace than memory slots */ + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; + __u64 target_phys_addr; +}; + +Defines a guest physical address space region as an alias to another +region. Useful for aliased address, for example the VGA low memory +window. Should not be used with userspace memory. + +4.9 KVM_RUN + +Capability: basic +Architectures: all +Type: vcpu ioctl +Parameters: none +Returns: 0 on success, -1 on error +Errors: + EINTR: an unmasked signal is pending + +This ioctl is used to run a guest virtual cpu. While there are no +explicit parameters, there is an implicit parameter block that can be +obtained by mmap()ing the vcpu fd at offset 0, with the size given by +KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct +kvm_run' (see below). + +4.10 KVM_GET_REGS + +Capability: basic +Architectures: all +Type: vcpu ioctl +Parameters: struct kvm_regs (out) +Returns: 0 on success, -1 on error + +Reads the general purpose registers from the vcpu. + +/* x86 */ +struct kvm_regs { + /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ + __u64 rax, rbx, rcx, rdx; + __u64 rsi, rdi, rsp, rbp; + __u64 r8, r9, r10, r11; + __u64 r12, r13, r14, r15; + __u64 rip, rflags; +}; + +4.11 KVM_SET_REGS + +Capability: basic +Architectures: all +Type: vcpu ioctl +Parameters: struct kvm_regs (in) +Returns: 0 on success, -1 on error + +Writes the general purpose registers into the vcpu. + +See KVM_GET_REGS for the data structure. + +4.12 KVM_GET_SREGS + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_sregs (out) +Returns: 0 on success, -1 on error + +Reads special registers from the vcpu. + +/* x86 */ +struct kvm_sregs { + struct kvm_segment cs, ds, es, fs, gs, ss; + struct kvm_segment tr, ldt; + struct kvm_dtable gdt, idt; + __u64 cr0, cr2, cr3, cr4, cr8; + __u64 efer; + __u64 apic_base; + __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64]; +}; + +interrupt_bitmap is a bitmap of pending external interrupts. At most +one bit may be set. This interrupt has been acknowledged by the APIC +but not yet injected into the cpu core. + +4.13 KVM_SET_SREGS + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_sregs (in) +Returns: 0 on success, -1 on error + +Writes special registers into the vcpu. See KVM_GET_SREGS for the +data structures. + +4.14 KVM_TRANSLATE + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_translation (in/out) +Returns: 0 on success, -1 on error + +Translates a virtual address according to the vcpu's current address +translation mode. + +struct kvm_translation { + /* in */ + __u64 linear_address; + + /* out */ + __u64 physical_address; + __u8 valid; + __u8 writeable; + __u8 usermode; + __u8 pad[5]; +}; + +4.15 KVM_INTERRUPT + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_interrupt (in) +Returns: 0 on success, -1 on error + +Queues a hardware interrupt vector to be injected. This is only +useful if in-kernel local APIC is not used. + +/* for KVM_INTERRUPT */ +struct kvm_interrupt { + /* in */ + __u32 irq; +}; + +Note 'irq' is an interrupt vector, not an interrupt pin or line. + +4.16 KVM_DEBUG_GUEST + +Capability: basic +Architectures: none +Type: vcpu ioctl +Parameters: none) +Returns: -1 on error + +Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. + +4.17 KVM_GET_MSRS + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_msrs (in/out) +Returns: 0 on success, -1 on error + +Reads model-specific registers from the vcpu. Supported msr indices can +be obtained using KVM_GET_MSR_INDEX_LIST. + +struct kvm_msrs { + __u32 nmsrs; /* number of msrs in entries */ + __u32 pad; + + struct kvm_msr_entry entries[0]; +}; + +struct kvm_msr_entry { + __u32 index; + __u32 reserved; + __u64 data; +}; + +Application code should set the 'nmsrs' member (which indicates the +size of the entries array) and the 'index' member of each array entry. +kvm will fill in the 'data' member. + +4.18 KVM_SET_MSRS + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_msrs (in) +Returns: 0 on success, -1 on error + +Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the +data structures. + +Application code should set the 'nmsrs' member (which indicates the +size of the entries array), and the 'index' and 'data' members of each +array entry. + +4.19 KVM_SET_CPUID + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_cpuid (in) +Returns: 0 on success, -1 on error + +Defines the vcpu responses to the cpuid instruction. Applications +should use the KVM_SET_CPUID2 ioctl if available. + + +struct kvm_cpuid_entry { + __u32 function; + __u32 eax; + __u32 ebx; + __u32 ecx; + __u32 edx; + __u32 padding; +}; + +/* for KVM_SET_CPUID */ +struct kvm_cpuid { + __u32 nent; + __u32 padding; + struct kvm_cpuid_entry entries[0]; +}; + +4.20 KVM_SET_SIGNAL_MASK + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_signal_mask (in) +Returns: 0 on success, -1 on error + +Defines which signals are blocked during execution of KVM_RUN. This +signal mask temporarily overrides the threads signal mask. Any +unblocked signal received (except SIGKILL and SIGSTOP, which retain +their traditional behaviour) will cause KVM_RUN to return with -EINTR. + +Note the signal will only be delivered if not blocked by the original +signal mask. + +/* for KVM_SET_SIGNAL_MASK */ +struct kvm_signal_mask { + __u32 len; + __u8 sigset[0]; +}; + +4.21 KVM_GET_FPU + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_fpu (out) +Returns: 0 on success, -1 on error + +Reads the floating point state from the vcpu. + +/* for KVM_GET_FPU and KVM_SET_FPU */ +struct kvm_fpu { + __u8 fpr[8][16]; + __u16 fcw; + __u16 fsw; + __u8 ftwx; /* in fxsave format */ + __u8 pad1; + __u16 last_opcode; + __u64 last_ip; + __u64 last_dp; + __u8 xmm[16][16]; + __u32 mxcsr; + __u32 pad2; +}; + +4.22 KVM_SET_FPU + +Capability: basic +Architectures: x86 +Type: vcpu ioctl +Parameters: struct kvm_fpu (in) +Returns: 0 on success, -1 on error + +Writes the floating point state to the vcpu. + +/* for KVM_GET_FPU and KVM_SET_FPU */ +struct kvm_fpu { + __u8 fpr[8][16]; + __u16 fcw; + __u16 fsw; + __u8 ftwx; /* in fxsave format */ + __u8 pad1; + __u16 last_opcode; + __u64 last_ip; + __u64 last_dp; + __u8 xmm[16][16]; + __u32 mxcsr; + __u32 pad2; +}; + +5. The kvm_run structure + +Application code obtains a pointer to the kvm_run structure by +mmap()ing a vcpu fd. From that point, application code can control +execution by changing fields in kvm_run prior to calling the KVM_RUN +ioctl, and obtain information about the reason KVM_RUN returned by +looking up structure members. + +struct kvm_run { + /* in */ + __u8 request_interrupt_window; + +Request that KVM_RUN return when it becomes possible to inject external +interrupts into the guest. Useful in conjunction with KVM_INTERRUPT. + + __u8 padding1[7]; + + /* out */ + __u32 exit_reason; + +When KVM_RUN has returned successfully (return value 0), this informs +application code why KVM_RUN has returned. Allowable values for this +field are detailed below. + + __u8 ready_for_interrupt_injection; + +If request_interrupt_window has been specified, this field indicates +an interrupt can be injected now with KVM_INTERRUPT. + + __u8 if_flag; + +The value of the current interrupt flag. Only valid if in-kernel +local APIC is not used. + + __u8 padding2[2]; + + /* in (pre_kvm_run), out (post_kvm_run) */ + __u64 cr8; + +The value of the cr8 register. Only valid if in-kernel local APIC is +not used. Both input and output. + + __u64 apic_base; + +The value of the APIC BASE msr. Only valid if in-kernel local +APIC is not used. Both input and output. + + union { + /* KVM_EXIT_UNKNOWN */ + struct { + __u64 hardware_exit_reason; + } hw; + +If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown +reasons. Further architecture-specific information is available in +hardware_exit_reason. + + /* KVM_EXIT_FAIL_ENTRY */ + struct { + __u64 hardware_entry_failure_reason; + } fail_entry; + +If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due +to unknown reasons. Further architecture-specific information is +available in hardware_entry_failure_reason. + + /* KVM_EXIT_EXCEPTION */ + struct { + __u32 exception; + __u32 error_code; + } ex; + +Unused. + + /* KVM_EXIT_IO */ + struct { +#define KVM_EXIT_IO_IN 0 +#define KVM_EXIT_IO_OUT 1 + __u8 direction; + __u8 size; /* bytes */ + __u16 port; + __u32 count; + __u64 data_offset; /* relative to kvm_run start */ + } io; + +If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has +executed a port I/O instruction which could not be satisfied by kvm. +data_offset describes where the data is located (KVM_EXIT_IO_OUT) or +where kvm expects application code to place the data for the next +KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a patcked array. + + struct { + struct kvm_debug_exit_arch arch; + } debug; + +Unused. + + /* KVM_EXIT_MMIO */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } mmio; + +If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has +executed a memory-mapped I/O instruction which could not be satisfied +by kvm. The 'data' member contains the written data if 'is_write' is +true, and should be filled by application code otherwise. + + /* KVM_EXIT_HYPERCALL */ + struct { + __u64 nr; + __u64 args[6]; + __u64 ret; + __u32 longmode; + __u32 pad; + } hypercall; + +Unused. + + /* KVM_EXIT_TPR_ACCESS */ + struct { + __u64 rip; + __u32 is_write; + __u32 pad; + } tpr_access; + +To be documented (KVM_TPR_ACCESS_REPORTING). + + /* KVM_EXIT_S390_SIEIC */ + struct { + __u8 icptcode; + __u64 mask; /* psw upper half */ + __u64 addr; /* psw lower half */ + __u16 ipa; + __u32 ipb; + } s390_sieic; + +s390 specific. + + /* KVM_EXIT_S390_RESET */ +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + __u64 s390_reset_flags; + +s390 specific. + + /* KVM_EXIT_DCR */ + struct { + __u32 dcrn; + __u32 data; + __u8 is_write; + } dcr; + +powerpc specific. + + /* Fix the size of the union. */ + char padding[256]; + }; +}; diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index f2296ecedb89..e2ddcdeb61b6 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -36,8 +36,6 @@ detailed description): - Bluetooth enable and disable - video output switching, expansion control - ThinkLight on and off - - limited docking and undocking - - UltraBay eject - CMOS/UCMS control - LED control - ACPI sounds @@ -729,131 +727,6 @@ cannot be read or if it is unknown, thinkpad-acpi will report it as "off". It is impossible to know if the status returned through sysfs is valid. -Docking / undocking -- /proc/acpi/ibm/dock ------------------------------------------- - -Docking and undocking (e.g. with the X4 UltraBase) requires some -actions to be taken by the operating system to safely make or break -the electrical connections with the dock. - -The docking feature of this driver generates the following ACPI events: - - ibm/dock GDCK 00000003 00000001 -- eject request - ibm/dock GDCK 00000003 00000002 -- undocked - ibm/dock GDCK 00000000 00000003 -- docked - -NOTE: These events will only be generated if the laptop was docked -when originally booted. This is due to the current lack of support for -hot plugging of devices in the Linux ACPI framework. If the laptop was -booted while not in the dock, the following message is shown in the -logs: - - Mar 17 01:42:34 aero kernel: thinkpad_acpi: dock device not present - -In this case, no dock-related events are generated but the dock and -undock commands described below still work. They can be executed -manually or triggered by Fn key combinations (see the example acpid -configuration files included in the driver tarball package available -on the web site). - -When the eject request button on the dock is pressed, the first event -above is generated. The handler for this event should issue the -following command: - - echo undock > /proc/acpi/ibm/dock - -After the LED on the dock goes off, it is safe to eject the laptop. -Note: if you pressed this key by mistake, go ahead and eject the -laptop, then dock it back in. Otherwise, the dock may not function as -expected. - -When the laptop is docked, the third event above is generated. The -handler for this event should issue the following command to fully -enable the dock: - - echo dock > /proc/acpi/ibm/dock - -The contents of the /proc/acpi/ibm/dock file shows the current status -of the dock, as provided by the ACPI framework. - -The docking support in this driver does not take care of enabling or -disabling any other devices you may have attached to the dock. For -example, a CD drive plugged into the UltraBase needs to be disabled or -enabled separately. See the provided example acpid configuration files -for how this can be accomplished. - -There is no support yet for PCI devices that may be attached to a -docking station, e.g. in the ThinkPad Dock II. The driver currently -does not recognize, enable or disable such devices. This means that -the only docking stations currently supported are the X-series -UltraBase docks and "dumb" port replicators like the Mini Dock (the -latter don't need any ACPI support, actually). - - -UltraBay eject -- /proc/acpi/ibm/bay ------------------------------------- - -Inserting or ejecting an UltraBay device requires some actions to be -taken by the operating system to safely make or break the electrical -connections with the device. - -This feature generates the following ACPI events: - - ibm/bay MSTR 00000003 00000000 -- eject request - ibm/bay MSTR 00000001 00000000 -- eject lever inserted - -NOTE: These events will only be generated if the UltraBay was present -when the laptop was originally booted (on the X series, the UltraBay -is in the dock, so it may not be present if the laptop was undocked). -This is due to the current lack of support for hot plugging of devices -in the Linux ACPI framework. If the laptop was booted without the -UltraBay, the following message is shown in the logs: - - Mar 17 01:42:34 aero kernel: thinkpad_acpi: bay device not present - -In this case, no bay-related events are generated but the eject -command described below still works. It can be executed manually or -triggered by a hot key combination. - -Sliding the eject lever generates the first event shown above. The -handler for this event should take whatever actions are necessary to -shut down the device in the UltraBay (e.g. call idectl), then issue -the following command: - - echo eject > /proc/acpi/ibm/bay - -After the LED on the UltraBay goes off, it is safe to pull out the -device. - -When the eject lever is inserted, the second event above is -generated. The handler for this event should take whatever actions are -necessary to enable the UltraBay device (e.g. call idectl). - -The contents of the /proc/acpi/ibm/bay file shows the current status -of the UltraBay, as provided by the ACPI framework. - -EXPERIMENTAL warm eject support on the 600e/x, A22p and A3x (To use -this feature, you need to supply the experimental=1 parameter when -loading the module): - -These models do not have a button near the UltraBay device to request -a hot eject but rather require the laptop to be put to sleep -(suspend-to-ram) before the bay device is ejected or inserted). -The sequence of steps to eject the device is as follows: - - echo eject > /proc/acpi/ibm/bay - put the ThinkPad to sleep - remove the drive - resume from sleep - cat /proc/acpi/ibm/bay should show that the drive was removed - -On the A3x, both the UltraBay 2000 and UltraBay Plus devices are -supported. Use "eject2" instead of "eject" for the second bay. - -Note: the UltraBay eject support on the 600e/x, A22p and A3x is -EXPERIMENTAL and may not work as expected. USE WITH CAUTION! - - CMOS/UCMS control ----------------- diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 9ebcd6ef361b..950cde6d6e58 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -1,7 +1,9 @@ -/*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 opens /dev/lguest to tell the kernel - * about the Guest and control it. :*/ +/*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 opens /dev/lguest to tell the kernel about the Guest and + * control it. +:*/ #define _LARGEFILE64_SOURCE #define _GNU_SOURCE #include <stdio.h> @@ -46,13 +48,15 @@ #include "linux/virtio_rng.h" #include "linux/virtio_ring.h" #include "asm/bootparam.h" -/*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. +/*L:110 + * We can ignore the 42 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 * like these abbreviations, so we define them here. Note that u64 is always * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. */ + * use %llu in printf for any u64. + */ typedef unsigned long long u64; typedef uint32_t u32; typedef uint16_t u16; @@ -69,8 +73,10 @@ typedef uint8_t u8; /* This will occupy 3 pages: it must be a power of 2. */ #define VIRTQUEUE_NUM 256 -/*L:120 verbose is both a global flag and a macro. The C preprocessor allows - * this, and although I wouldn't recommend it, it works quite nicely here. */ +/*L:120 + * verbose is both a global flag and a macro. The C preprocessor allows + * this, and although I wouldn't recommend it, it works quite nicely here. + */ static bool verbose; #define verbose(args...) \ do { if (verbose) printf(args); } while(0) @@ -87,8 +93,7 @@ static int lguest_fd; static unsigned int __thread cpu_id; /* This is our list of devices. */ -struct device_list -{ +struct device_list { /* Counter to assign interrupt numbers. */ unsigned int next_irq; @@ -100,8 +105,7 @@ struct device_list /* A single linked list of devices. */ struct device *dev; - /* And a pointer to the last device for easy append and also for - * configuration appending. */ + /* And a pointer to the last device for easy append. */ struct device *lastdev; }; @@ -109,8 +113,7 @@ struct device_list static struct device_list devices; /* The device structure describes a single device. */ -struct device -{ +struct device { /* The linked-list pointer. */ struct device *next; @@ -135,8 +138,7 @@ struct device }; /* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue -{ +struct virtqueue { struct virtqueue *next; /* Which device owns me. */ @@ -168,20 +170,24 @@ static char **main_args; /* The original tty settings to restore on exit. */ static struct termios orig_term; -/* We have to be careful with barriers: our devices are all run in separate +/* + * We have to be careful with barriers: our devices are all run in separate * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. */ + * in precise order. + */ #define wmb() __asm__ __volatile__("" : : : "memory") #define mb() __asm__ __volatile__("" : : : "memory") -/* Convert an iovec element to the given type. +/* + * Convert an iovec element to the given type. * * This is a fairly ugly trick: we need to know the size of the type and * alignment requirement to check the pointer is kosher. It's also nice to * have the name of the type in case we report failure. * * Typing those three things all the time is cumbersome and error prone, so we - * have a macro which sets them all up and passes to the real function. */ + * have a macro which sets them all up and passes to the real function. + */ #define convert(iov, type) \ ((type *)_convert((iov), sizeof(type), __alignof__(type), #type)) @@ -198,8 +204,10 @@ static void *_convert(struct iovec *iov, size_t size, size_t align, /* Wrapper for the last available index. Makes it easier to change. */ #define lg_last_avail(vq) ((vq)->last_avail_idx) -/* The virtio configuration space is defined to be little-endian. x86 is - * little-endian too, but it's nice to be explicit so we have these helpers. */ +/* + * The virtio configuration space is defined to be little-endian. x86 is + * little-endian too, but it's nice to be explicit so we have these helpers. + */ #define cpu_to_le16(v16) (v16) #define cpu_to_le32(v32) (v32) #define cpu_to_le64(v64) (v64) @@ -241,11 +249,12 @@ static u8 *get_feature_bits(struct device *dev) + dev->num_vq * sizeof(struct lguest_vqconfig); } -/*L:100 The Launcher code itself takes us out into userspace, that scary place - * where pointers run wild and free! Unfortunately, like most userspace - * programs, it's quite boring (which is why everyone likes to hack on the - * kernel!). Perhaps if you make up an Lguest Drinking Game at this point, it - * will get you through this section. Or, maybe not. +/*L:100 + * The Launcher code itself takes us out into userspace, that scary place where + * pointers run wild and free! Unfortunately, like most userspace programs, + * it's quite boring (which is why everyone likes to hack on the kernel!). + * Perhaps if you make up an Lguest Drinking Game at this point, it will get + * you through this section. Or, maybe not. * * The Launcher sets up a big chunk of memory to be the Guest's "physical" * memory and stores it in "guest_base". In other words, Guest physical == @@ -253,7 +262,8 @@ static u8 *get_feature_bits(struct device *dev) * * This can be tough to get your head around, but usually it just means that we * use these trivial conversion functions when the Guest gives us it's - * "physical" addresses: */ + * "physical" addresses: + */ static void *from_guest_phys(unsigned long addr) { return guest_base + addr; @@ -268,7 +278,8 @@ static unsigned long to_guest_phys(const void *addr) * Loading the Kernel. * * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: */ + * error-checking code cluttering the callers: + */ static int open_or_die(const char *name, int flags) { int fd = open(name, flags); @@ -283,12 +294,19 @@ static void *map_zeroed_pages(unsigned int num) int fd = open_or_die("/dev/zero", O_RDONLY); void *addr; - /* We use a private mapping (ie. if we write to the page, it will be - * copied). */ + /* + * We use a private mapping (ie. if we write to the page, it will be + * copied). + */ addr = mmap(NULL, getpagesize() * num, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0); if (addr == MAP_FAILED) err(1, "Mmaping %u pages of /dev/zero", num); + + /* + * One neat mmap feature is that you can close the fd, and it + * stays mapped. + */ close(fd); return addr; @@ -305,20 +323,24 @@ static void *get_pages(unsigned int num) return addr; } -/* This routine is used to load the kernel or initrd. It tries mmap, but if +/* + * This routine is used to load the kernel or initrd. It tries mmap, but if * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries), - * it falls back to reading the memory in. */ + * it falls back to reading the memory in. + */ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) { ssize_t r; - /* We map writable even though for some segments are marked read-only. + /* + * We map writable even though for some segments are marked read-only. * The kernel really wants to be writable: it patches its own * instructions. * * MAP_PRIVATE means that the page won't be copied until a write is * done to it. This allows us to share untouched memory between - * Guests. */ + * Guests. + */ if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) return; @@ -329,7 +351,8 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) err(1, "Reading offset %lu len %lu gave %zi", offset, len, r); } -/* This routine takes an open vmlinux image, which is in ELF, and maps it into +/* + * This routine takes an open vmlinux image, which is in ELF, and maps it into * the Guest memory. ELF = Embedded Linking Format, which is the format used * by all modern binaries on Linux including the kernel. * @@ -337,23 +360,28 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) * address. We use the physical address; the Guest will map itself to the * virtual address. * - * We return the starting address. */ + * We return the starting address. + */ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) { Elf32_Phdr phdr[ehdr->e_phnum]; unsigned int i; - /* Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. */ + /* + * Sanity checks on the main ELF header: an x86 executable with a + * reasonable number of correctly-sized program headers. + */ if (ehdr->e_type != ET_EXEC || ehdr->e_machine != EM_386 || ehdr->e_phentsize != sizeof(Elf32_Phdr) || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) errx(1, "Malformed elf header"); - /* An ELF executable contains an ELF header and a number of "program" + /* + * An ELF executable contains an ELF header and a number of "program" * headers which indicate which parts ("segments") of the program to - * load where. */ + * load where. + */ /* We read in all the program headers at once: */ if (lseek(elf_fd, ehdr->e_phoff, SEEK_SET) < 0) @@ -361,8 +389,10 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr)) 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 we don't load. */ + /* + * Try all the headers: there are usually only three. A read-only one, + * 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) @@ -380,13 +410,15 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) return ehdr->e_entry; } -/*L:150 A bzImage, unlike an ELF file, is not meant to be loaded. You're - * supposed to jump into it and it will unpack itself. We used to have to - * perform some hairy magic because the unpacking code scared me. +/*L:150 + * A bzImage, unlike an ELF file, is not meant to be loaded. You're supposed + * to jump into it and it will unpack itself. We used to have to perform some + * hairy magic because the unpacking code scared me. * * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote * a small patch to jump over the tricky bits in the Guest, so now we just read - * the funky header so we know where in the file to load, and away we go! */ + * the funky header so we know where in the file to load, and away we go! + */ static unsigned long load_bzimage(int fd) { struct boot_params boot; @@ -394,8 +426,10 @@ static unsigned long load_bzimage(int fd) /* Modern bzImages get loaded at 1M. */ void *p = from_guest_phys(0x100000); - /* Go back to the start of the file and read the header. It should be - * a Linux boot header (see Documentation/x86/i386/boot.txt) */ + /* + * Go back to the start of the file and read the header. It should be + * a Linux boot header (see Documentation/x86/i386/boot.txt) + */ lseek(fd, 0, SEEK_SET); read(fd, &boot, sizeof(boot)); @@ -414,9 +448,11 @@ static unsigned long load_bzimage(int fd) return boot.hdr.code32_start; } -/*L:140 Loading the kernel is easy when it's a "vmlinux", but most kernels +/*L:140 + * Loading the kernel is easy when it's a "vmlinux", but most kernels * come wrapped up in the self-decompressing "bzImage" format. With a little - * work, we can load those, too. */ + * work, we can load those, too. + */ static unsigned long load_kernel(int fd) { Elf32_Ehdr hdr; @@ -433,24 +469,28 @@ static unsigned long load_kernel(int fd) return load_bzimage(fd); } -/* This is a trivial little helper to align pages. Andi Kleen hated it because +/* + * This is a trivial little helper to align pages. Andi Kleen hated it because * it calls getpagesize() twice: "it's dumb code." * * Kernel guys get really het up about optimization, even when it's not - * necessary. I leave this code as a reaction against that. */ + * necessary. I leave this code as a reaction against that. + */ static inline unsigned long page_align(unsigned long addr) { /* Add upwards and truncate downwards. */ return ((addr + getpagesize()-1) & ~(getpagesize()-1)); } -/*L:180 An "initial ram disk" is a disk image loaded into memory along with - * the kernel which the kernel can use to boot from without needing any - * drivers. Most distributions now use this as standard: the initrd contains - * the code to load the appropriate driver modules for the current machine. +/*L:180 + * An "initial ram disk" is a disk image loaded into memory along with the + * kernel which the kernel can use to boot from without needing any drivers. + * Most distributions now use this as standard: the initrd contains the code to + * load the appropriate driver modules for the current machine. * * Importantly, James Morris works for RedHat, and Fedora uses initrds for its - * kernels. He sent me this (and tells me when I break it). */ + * kernels. He sent me this (and tells me when I break it). + */ static unsigned long load_initrd(const char *name, unsigned long mem) { int ifd; @@ -462,12 +502,16 @@ static unsigned long load_initrd(const char *name, unsigned long mem) if (fstat(ifd, &st) < 0) err(1, "fstat() on initrd '%s'", name); - /* We map the initrd at the top of memory, but mmap wants it to be - * page-aligned, so we round the size up for that. */ + /* + * We map the initrd at the top of memory, but mmap wants it to be + * page-aligned, so we round the size up for that. + */ len = page_align(st.st_size); map_at(ifd, from_guest_phys(mem - len), 0, st.st_size); - /* Once a file is mapped, you can close the file descriptor. It's a - * little odd, but quite useful. */ + /* + * Once a file is mapped, you can close the file descriptor. It's a + * little odd, but quite useful. + */ close(ifd); verbose("mapped initrd %s size=%lu @ %p\n", name, len, (void*)mem-len); @@ -476,8 +520,10 @@ static unsigned long load_initrd(const char *name, unsigned long mem) } /*:*/ -/* Simple routine to roll all the commandline arguments together with spaces - * between them. */ +/* + * Simple routine to roll all the commandline arguments together with spaces + * between them. + */ static void concat(char *dst, char *args[]) { unsigned int i, len = 0; @@ -494,10 +540,12 @@ static void concat(char *dst, char *args[]) dst[len] = '\0'; } -/*L:185 This is where we actually tell the kernel to initialize the Guest. We +/*L:185 + * This is where we actually tell the kernel to initialize the Guest. We * saw the arguments it expects when we looked at initialize() in lguest_user.c: * the base of Guest "physical" memory, the top physical page to allow and the - * entry point for the Guest. */ + * entry point for the Guest. + */ static void tell_kernel(unsigned long start) { unsigned long args[] = { LHREQ_INITIALIZE, @@ -511,7 +559,7 @@ static void tell_kernel(unsigned long start) } /*:*/ -/* +/*L:200 * Device Handling. * * When the Guest gives us a buffer, it sends an array of addresses and sizes. @@ -522,20 +570,26 @@ static void tell_kernel(unsigned long start) static void *_check_pointer(unsigned long addr, unsigned int size, unsigned int line) { - /* We have to separately check addr and addr+size, because size could - * be huge and addr + size might wrap around. */ + /* + * We have to separately check addr and addr+size, because size could + * be huge and addr + size might wrap around. + */ if (addr >= guest_limit || addr + size >= guest_limit) errx(1, "%s:%i: Invalid address %#lx", __FILE__, line, addr); - /* We return a pointer for the caller's convenience, now we know it's - * safe to use. */ + /* + * We return a pointer for the caller's convenience, now we know it's + * safe to use. + */ return from_guest_phys(addr); } /* A macro which transparently hands the line number to the real function. */ #define check_pointer(addr,size) _check_pointer(addr, size, __LINE__) -/* Each buffer in the virtqueues is actually a chain of descriptors. This +/* + * Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, or vq->vring.num if we're - * at the end. */ + * at the end. + */ static unsigned next_desc(struct vring_desc *desc, unsigned int i, unsigned int max) { @@ -556,7 +610,10 @@ static unsigned next_desc(struct vring_desc *desc, return next; } -/* This actually sends the interrupt for this virtqueue */ +/* + * This actually sends the interrupt for this virtqueue, if we've used a + * buffer. + */ static void trigger_irq(struct virtqueue *vq) { unsigned long buf[] = { LHREQ_IRQ, vq->config.irq }; @@ -576,12 +633,14 @@ static void trigger_irq(struct virtqueue *vq) err(1, "Triggering irq %i", vq->config.irq); } -/* This looks in the virtqueue and for the first available buffer, and converts +/* + * This looks in the virtqueue for the first available buffer, and converts * it to an iovec for convenient access. Since descriptors consist of some * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * - * This function returns the descriptor number found. */ + * This function waits if necessary, and returns the descriptor number found. + */ static unsigned wait_for_vq_desc(struct virtqueue *vq, struct iovec iov[], unsigned int *out_num, unsigned int *in_num) @@ -590,17 +649,23 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, struct vring_desc *desc; u16 last_avail = lg_last_avail(vq); + /* There's nothing available? */ while (last_avail == vq->vring.avail->idx) { u64 event; - /* OK, tell Guest about progress up to now. */ + /* + * Since we're about to sleep, now is a good time to tell the + * Guest about what we've used up to now. + */ trigger_irq(vq); /* OK, now we need to know about added descriptors. */ vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY; - /* They could have slipped one in as we were doing that: make - * sure it's written, then check again. */ + /* + * They could have slipped one in as we were doing that: make + * sure it's written, then check again. + */ mb(); if (last_avail != vq->vring.avail->idx) { vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY; @@ -620,8 +685,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, errx(1, "Guest moved used index from %u to %u", last_avail, vq->vring.avail->idx); - /* Grab the next descriptor number they're advertising, and increment - * the index we've seen. */ + /* + * Grab the next descriptor number they're advertising, and increment + * the index we've seen. + */ head = vq->vring.avail->ring[last_avail % vq->vring.num]; lg_last_avail(vq)++; @@ -636,8 +703,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, desc = vq->vring.desc; i = head; - /* If this is an indirect entry, then this buffer contains a descriptor - * table which we handle as if it's any normal descriptor chain. */ + /* + * If this is an indirect entry, then this buffer contains a descriptor + * table which we handle as if it's any normal descriptor chain. + */ if (desc[i].flags & VRING_DESC_F_INDIRECT) { if (desc[i].len % sizeof(struct vring_desc)) errx(1, "Invalid size for indirect buffer table"); @@ -656,8 +725,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, if (desc[i].flags & VRING_DESC_F_WRITE) (*in_num)++; else { - /* If it's an output descriptor, they're all supposed - * to come before any input descriptors. */ + /* + * If it's an output descriptor, they're all supposed + * to come before any input descriptors. + */ if (*in_num) errx(1, "Descriptor has out after in"); (*out_num)++; @@ -671,14 +742,19 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, return head; } -/* After we've used one of their buffers, we tell them about it. We'll then - * want to send them an interrupt, using trigger_irq(). */ +/* + * After we've used one of their buffers, we tell the Guest about it. Sometime + * later we'll want to send them an interrupt using trigger_irq(); note that + * wait_for_vq_desc() does that for us if it has to wait. + */ static void add_used(struct virtqueue *vq, unsigned int head, int len) { struct vring_used_elem *used; - /* The virtqueue contains a ring of used buffers. Get a pointer to the - * next entry in that used ring. */ + /* + * The virtqueue contains a ring of used buffers. Get a pointer to the + * next entry in that used ring. + */ used = &vq->vring.used->ring[vq->vring.used->idx % vq->vring.num]; used->id = head; used->len = len; @@ -698,9 +774,9 @@ static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) /* * The Console * - * We associate some data with the console for our exit hack. */ -struct console_abort -{ + * We associate some data with the console for our exit hack. + */ +struct console_abort { /* How many times have they hit ^C? */ int count; /* When did they start? */ @@ -715,30 +791,35 @@ static void console_input(struct virtqueue *vq) struct console_abort *abort = vq->dev->priv; struct iovec iov[vq->vring.num]; - /* Make sure there's a descriptor waiting. */ + /* Make sure there's a descriptor available. */ head = wait_for_vq_desc(vq, iov, &out_num, &in_num); if (out_num) errx(1, "Output buffers in console in queue?"); - /* Read it in. */ + /* Read into it. This is where we usually wait. */ len = readv(STDIN_FILENO, iov, in_num); if (len <= 0) { /* Ran out of input? */ warnx("Failed to get console input, ignoring console."); - /* For simplicity, dying threads kill the whole Launcher. So - * just nap here. */ + /* + * For simplicity, dying threads kill the whole Launcher. So + * just nap here. + */ for (;;) pause(); } + /* Tell the Guest we used a buffer. */ add_used_and_trigger(vq, head, len); - /* Three ^C within one second? Exit. + /* + * Three ^C within one second? Exit. * * This is such a hack, but works surprisingly well. Each ^C has to * be in a buffer by itself, so they can't be too fast. But we check * that we get three within about a second, so they can't be too - * slow. */ + * slow. + */ if (len != 1 || ((char *)iov[0].iov_base)[0] != 3) { abort->count = 0; return; @@ -763,15 +844,23 @@ static void console_output(struct virtqueue *vq) unsigned int head, out, in; struct iovec iov[vq->vring.num]; + /* We usually wait in here, for the Guest to give us something. */ head = wait_for_vq_desc(vq, iov, &out, &in); if (in) errx(1, "Input buffers in console output queue?"); + + /* writev can return a partial write, so we loop here. */ while (!iov_empty(iov, out)) { int len = writev(STDOUT_FILENO, iov, out); if (len <= 0) err(1, "Write to stdout gave %i", len); iov_consume(iov, out, len); } + + /* + * We're finished with that buffer: if we're going to sleep, + * wait_for_vq_desc() will prod the Guest with an interrupt. + */ add_used(vq, head, 0); } @@ -791,15 +880,30 @@ static void net_output(struct virtqueue *vq) unsigned int head, out, in; struct iovec iov[vq->vring.num]; + /* We usually wait in here for the Guest to give us a packet. */ head = wait_for_vq_desc(vq, iov, &out, &in); if (in) errx(1, "Input buffers in net output queue?"); + /* + * Send the whole thing through to /dev/net/tun. It expects the exact + * same format: what a coincidence! + */ if (writev(net_info->tunfd, iov, out) < 0) errx(1, "Write to tun failed?"); + + /* + * Done with that one; wait_for_vq_desc() will send the interrupt if + * all packets are processed. + */ add_used(vq, head, 0); } -/* Will reading from this file descriptor block? */ +/* + * Handling network input is a bit trickier, because I've tried to optimize it. + * + * First we have a helper routine which tells is if from this file descriptor + * (ie. the /dev/net/tun device) will block: + */ static bool will_block(int fd) { fd_set fdset; @@ -809,8 +913,11 @@ static bool will_block(int fd) return select(fd+1, &fdset, NULL, NULL, &zero) != 1; } -/* This is where we handle packets coming in from the tun device to our - * Guest. */ +/* + * This handles packets coming in from the tun device to our Guest. Like all + * service routines, it gets called again as soon as it returns, so you don't + * see a while(1) loop here. + */ static void net_input(struct virtqueue *vq) { int len; @@ -818,21 +925,38 @@ static void net_input(struct virtqueue *vq) struct iovec iov[vq->vring.num]; struct net_info *net_info = vq->dev->priv; + /* + * Get a descriptor to write an incoming packet into. This will also + * send an interrupt if they're out of descriptors. + */ head = wait_for_vq_desc(vq, iov, &out, &in); if (out) errx(1, "Output buffers in net input queue?"); - /* Deliver interrupt now, since we're about to sleep. */ + /* + * If it looks like we'll block reading from the tun device, send them + * an interrupt. + */ if (vq->pending_used && will_block(net_info->tunfd)) trigger_irq(vq); + /* + * Read in the packet. This is where we normally wait (when there's no + * incoming network traffic). + */ len = readv(net_info->tunfd, iov, in); if (len <= 0) err(1, "Failed to read from tun."); + + /* + * Mark that packet buffer as used, but don't interrupt here. We want + * to wait until we've done as much work as we can. + */ add_used(vq, head, len); } +/*:*/ -/* This is the helper to create threads. */ +/* This is the helper to create threads: run the service routine in a loop. */ static int do_thread(void *_vq) { struct virtqueue *vq = _vq; @@ -842,8 +966,10 @@ static int do_thread(void *_vq) return 0; } -/* When a child dies, we kill our entire process group with SIGTERM. This - * also has the side effect that the shell restores the console for us! */ +/* + * When a child dies, we kill our entire process group with SIGTERM. This + * also has the side effect that the shell restores the console for us! + */ static void kill_launcher(int signal) { kill(0, SIGTERM); @@ -878,11 +1004,15 @@ static void reset_device(struct device *dev) signal(SIGCHLD, (void *)kill_launcher); } +/*L:216 + * This actually creates the thread which services the virtqueue for a device. + */ static void create_thread(struct virtqueue *vq) { - /* Create stack for thread and run it. Since stack grows - * upwards, we point the stack pointer to the end of this - * region. */ + /* + * Create stack for thread. Since the stack grows upwards, we point + * the stack pointer to the end of this region. + */ char *stack = malloc(32768); unsigned long args[] = { LHREQ_EVENTFD, vq->config.pfn*getpagesize(), 0 }; @@ -893,17 +1023,22 @@ static void create_thread(struct virtqueue *vq) err(1, "Creating eventfd"); args[2] = vq->eventfd; - /* Attach an eventfd to this virtqueue: it will go off - * when the Guest does an LHCALL_NOTIFY for this vq. */ + /* + * Attach an eventfd to this virtqueue: it will go off when the Guest + * does an LHCALL_NOTIFY for this vq. + */ if (write(lguest_fd, &args, sizeof(args)) != 0) err(1, "Attaching eventfd"); - /* CLONE_VM: because it has to access the Guest memory, and - * SIGCHLD so we get a signal if it dies. */ + /* + * CLONE_VM: because it has to access the Guest memory, and SIGCHLD so + * we get a signal if it dies. + */ vq->thread = clone(do_thread, stack + 32768, CLONE_VM | SIGCHLD, vq); if (vq->thread == (pid_t)-1) err(1, "Creating clone"); - /* We close our local copy, now the child has it. */ + + /* We close our local copy now the child has it. */ close(vq->eventfd); } @@ -955,7 +1090,10 @@ static void update_device_status(struct device *dev) } } -/* This is the generic routine we call when the Guest uses LHCALL_NOTIFY. */ +/*L:215 + * This is the generic routine we call when the Guest uses LHCALL_NOTIFY. In + * particular, it's used to notify us of device status changes during boot. + */ static void handle_output(unsigned long addr) { struct device *i; @@ -964,25 +1102,42 @@ static void handle_output(unsigned long addr) for (i = devices.dev; i; i = i->next) { struct virtqueue *vq; - /* Notifications to device descriptors update device status. */ + /* + * Notifications to device descriptors mean they updated the + * device status. + */ if (from_guest_phys(addr) == i->desc) { update_device_status(i); return; } - /* Devices *can* be used before status is set to DRIVER_OK. */ + /* + * Devices *can* be used before status is set to DRIVER_OK. + * The original plan was that they would never do this: they + * would always finish setting up their status bits before + * actually touching the virtqueues. In practice, we allowed + * them to, and they do (eg. the disk probes for partition + * tables as part of initialization). + * + * If we see this, we start the device: once it's running, we + * expect the device to catch all the notifications. + */ for (vq = i->vq; vq; vq = vq->next) { if (addr != vq->config.pfn*getpagesize()) continue; if (i->running) errx(1, "Notification on running %s", i->name); + /* This just calls create_thread() for each virtqueue */ start_device(i); return; } } - /* Early console write is done using notify on a nul-terminated string - * in Guest memory. */ + /* + * Early console write is done using notify on a nul-terminated string + * in Guest memory. It's also great for hacking debugging messages + * into a Guest. + */ if (addr >= guest_limit) errx(1, "Bad NOTIFY %#lx", addr); @@ -998,10 +1153,12 @@ static void handle_output(unsigned long addr) * routines to allocate and manage them. */ -/* The layout of the device page is a "struct lguest_device_desc" followed by a +/* + * 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 * array of configuration bytes. This routine returns the configuration - * pointer. */ + * pointer. + */ static u8 *device_config(const struct device *dev) { return (void *)(dev->desc + 1) @@ -1009,9 +1166,11 @@ static u8 *device_config(const struct device *dev) + dev->feature_len * 2; } -/* This routine allocates a new "struct lguest_device_desc" from descriptor +/* + * This routine allocates a new "struct lguest_device_desc" from descriptor * table page just above the Guest's normal memory. It returns a pointer to - * that descriptor. */ + * that descriptor. + */ static struct lguest_device_desc *new_dev_desc(u16 type) { struct lguest_device_desc d = { .type = type }; @@ -1032,8 +1191,10 @@ static struct lguest_device_desc *new_dev_desc(u16 type) return memcpy(p, &d, sizeof(d)); } -/* Each device descriptor is followed by the description of its virtqueues. We - * specify how many descriptors the virtqueue is to have. */ +/* + * Each device descriptor is followed by the description of its virtqueues. We + * specify how many descriptors the virtqueue is to have. + */ static void add_virtqueue(struct device *dev, unsigned int num_descs, void (*service)(struct virtqueue *)) { @@ -1050,6 +1211,11 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, vq->next = NULL; vq->last_avail_idx = 0; vq->dev = dev; + + /* + * This is the routine the service thread will run, and its Process ID + * once it's running. + */ vq->service = service; vq->thread = (pid_t)-1; @@ -1061,10 +1227,12 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, /* Initialize the vring. */ vring_init(&vq->vring, num_descs, p, LGUEST_VRING_ALIGN); - /* Append virtqueue to this device's descriptor. We use + /* + * Append virtqueue to this device's descriptor. We use * device_config() to get the end of the device's current virtqueues; * we check that we haven't added any config or feature information - * yet, otherwise we'd be overwriting them. */ + * yet, otherwise we'd be overwriting them. + */ assert(dev->desc->config_len == 0 && dev->desc->feature_len == 0); memcpy(device_config(dev), &vq->config, sizeof(vq->config)); dev->num_vq++; @@ -1072,14 +1240,18 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs, verbose("Virtqueue page %#lx\n", to_guest_phys(p)); - /* Add to tail of list, so dev->vq is first vq, dev->vq->next is - * second. */ + /* + * Add to tail of list, so dev->vq is first vq, dev->vq->next is + * second. + */ for (i = &dev->vq; *i; i = &(*i)->next); *i = vq; } -/* The first half of the feature bitmask is for us to advertise features. The - * second half is for the Guest to accept features. */ +/* + * The first half of the feature bitmask is for us to advertise features. The + * second half is for the Guest to accept features. + */ static void add_feature(struct device *dev, unsigned bit) { u8 *features = get_feature_bits(dev); @@ -1093,9 +1265,11 @@ static void add_feature(struct device *dev, unsigned bit) features[bit / CHAR_BIT] |= (1 << (bit % CHAR_BIT)); } -/* This routine sets the configuration fields for an existing device's +/* + * This routine sets the configuration fields for an existing device's * descriptor. It only works for the last device, but that's OK because that's - * how we use it. */ + * how we use it. + */ static void set_config(struct device *dev, unsigned len, const void *conf) { /* Check we haven't overflowed our single page. */ @@ -1105,12 +1279,18 @@ static void set_config(struct device *dev, unsigned len, const void *conf) /* Copy in the config information, and store the length. */ memcpy(device_config(dev), conf, len); dev->desc->config_len = len; + + /* Size must fit in config_len field (8 bits)! */ + assert(dev->desc->config_len == len); } -/* This routine does all the creation and setup of a new device, including - * calling new_dev_desc() to allocate the descriptor and device memory. +/* + * This routine does all the creation and setup of a new device, including + * calling new_dev_desc() to allocate the descriptor and device memory. We + * don't actually start the service threads until later. * - * See what I mean about userspace being boring? */ + * See what I mean about userspace being boring? + */ static struct device *new_device(const char *name, u16 type) { struct device *dev = malloc(sizeof(*dev)); @@ -1123,10 +1303,12 @@ static struct device *new_device(const char *name, u16 type) dev->num_vq = 0; dev->running = false; - /* Append to device list. Prepending to a single-linked list is + /* + * Append to device list. Prepending to a single-linked list is * easier, but the user expects the devices to be arranged on the bus * in command-line order. The first network device on the command line - * is eth0, the first block device /dev/vda, etc. */ + * is eth0, the first block device /dev/vda, etc. + */ if (devices.lastdev) devices.lastdev->next = dev; else @@ -1136,8 +1318,10 @@ static struct device *new_device(const char *name, u16 type) return dev; } -/* Our first setup routine is the console. It's a fairly simple device, but - * UNIX tty handling makes it uglier than it could be. */ +/* + * Our first setup routine is the console. It's a fairly simple device, but + * UNIX tty handling makes it uglier than it could be. + */ static void setup_console(void) { struct device *dev; @@ -1145,8 +1329,10 @@ static void setup_console(void) /* If we can save the initial standard input settings... */ if (tcgetattr(STDIN_FILENO, &orig_term) == 0) { struct termios term = orig_term; - /* Then we turn off echo, line buffering and ^C etc. We want a - * raw input stream to the Guest. */ + /* + * Then we turn off echo, line buffering and ^C etc: We want a + * raw input stream to the Guest. + */ term.c_lflag &= ~(ISIG|ICANON|ECHO); tcsetattr(STDIN_FILENO, TCSANOW, &term); } @@ -1157,10 +1343,12 @@ static void setup_console(void) dev->priv = malloc(sizeof(struct console_abort)); ((struct console_abort *)dev->priv)->count = 0; - /* The console needs two virtqueues: the input then the output. When + /* + * The console needs two virtqueues: the input then the output. When * they put something the input queue, we make sure we're listening to * stdin. When they put something in the output queue, we write it to - * stdout. */ + * stdout. + */ add_virtqueue(dev, VIRTQUEUE_NUM, console_input); add_virtqueue(dev, VIRTQUEUE_NUM, console_output); @@ -1168,7 +1356,8 @@ static void setup_console(void) } /*:*/ -/*M:010 Inter-guest networking is an interesting area. Simplest is to have a +/*M:010 + * Inter-guest networking is an interesting area. Simplest is to have a * --sharenet=<name> option which opens or creates a named pipe. This can be * used to send packets to another guest in a 1:1 manner. * @@ -1182,7 +1371,8 @@ static void setup_console(void) * multiple inter-guest channels behind one interface, although it would * require some manner of hotplugging new virtio channels. * - * Finally, we could implement a virtio network switch in the kernel. :*/ + * Finally, we could implement a virtio network switch in the kernel. +:*/ static u32 str2ip(const char *ipaddr) { @@ -1207,11 +1397,13 @@ static void str2mac(const char *macaddr, unsigned char mac[6]) mac[5] = m[5]; } -/* This code is "adapted" from libbridge: it attaches the Host end of the +/* + * This code is "adapted" from libbridge: it attaches the Host end of the * network device to the bridge device specified by the command line. * * This is yet another James Morris contribution (I'm an IP-level guy, so I - * dislike bridging), and I just try not to break it. */ + * dislike bridging), and I just try not to break it. + */ static void add_to_bridge(int fd, const char *if_name, const char *br_name) { int ifidx; @@ -1231,9 +1423,11 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name) err(1, "can't add %s to bridge %s", if_name, br_name); } -/* This sets up the Host end of the network device with an IP address, brings +/* + * This sets up the Host end of the network device with an IP address, brings * it up so packets will flow, the copies the MAC address into the hwaddr - * pointer. */ + * pointer. + */ static void configure_device(int fd, const char *tapif, u32 ipaddr) { struct ifreq ifr; @@ -1260,10 +1454,12 @@ static int get_tun_device(char tapif[IFNAMSIZ]) /* Start with this zeroed. Messy but sure. */ memset(&ifr, 0, sizeof(ifr)); - /* We open the /dev/net/tun device and tell it we want a tap device. A + /* + * We open the /dev/net/tun device and tell it we want a tap device. A * tap device is like a tun device, only somehow different. To tell * the truth, I completely blundered my way through this code, but it - * works now! */ + * works now! + */ netfd = open_or_die("/dev/net/tun", O_RDWR); ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; strcpy(ifr.ifr_name, "tap%d"); @@ -1274,18 +1470,22 @@ static int get_tun_device(char tapif[IFNAMSIZ]) TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0) err(1, "Could not set features for tun device"); - /* We don't need checksums calculated for packets coming in this - * device: trust us! */ + /* + * We don't need checksums calculated for packets coming in this + * device: trust us! + */ ioctl(netfd, TUNSETNOCSUM, 1); memcpy(tapif, ifr.ifr_name, IFNAMSIZ); return netfd; } -/*L:195 Our network is a Host<->Guest network. This can either use bridging or +/*L:195 + * Our network is a Host<->Guest network. This can either use bridging or * routing, but the principle is the same: it uses the "tun" device to inject * packets into the Host as if they came in from a normal network card. We - * just shunt packets between the Guest and the tun device. */ + * just shunt packets between the Guest and the tun device. + */ static void setup_tun_net(char *arg) { struct device *dev; @@ -1302,13 +1502,14 @@ static void setup_tun_net(char *arg) dev = new_device("net", VIRTIO_ID_NET); dev->priv = net_info; - /* Network devices need a receive and a send queue, just like - * console. */ + /* Network devices need a recv and a send queue, just like console. */ add_virtqueue(dev, VIRTQUEUE_NUM, net_input); add_virtqueue(dev, VIRTQUEUE_NUM, net_output); - /* We need a socket to perform the magic network ioctls to bring up the - * tap interface, connect to the bridge etc. Any socket will do! */ + /* + * We need a socket to perform the magic network ioctls to bring up the + * tap interface, connect to the bridge etc. Any socket will do! + */ ipfd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP); if (ipfd < 0) err(1, "opening IP socket"); @@ -1362,39 +1563,31 @@ static void setup_tun_net(char *arg) verbose("device %u: tun %s: %s\n", devices.device_num, tapif, arg); } - -/* Our block (disk) device should be really simple: the Guest asks for a block - * number and we read or write that position in the file. Unfortunately, that - * was amazingly slow: the Guest waits until the read is finished before - * running anything else, even if it could have been doing useful work. - * - * We could use async I/O, except it's reputed to suck so hard that characters - * actually go missing from your code when you try to use it. - * - * So we farm the I/O out to thread, and communicate with it via a pipe. */ +/*:*/ /* This hangs off device->priv. */ -struct vblk_info -{ +struct vblk_info { /* The size of the file. */ off64_t len; /* The file descriptor for the file. */ int fd; - /* IO thread listens on this file descriptor [0]. */ - int workpipe[2]; - - /* IO thread writes to this file descriptor to mark it done, then - * Launcher triggers interrupt to Guest. */ - int done_fd; }; /*L:210 * The Disk * - * Remember that the block device is handled by a separate I/O thread. We head - * straight into the core of that thread here: + * The disk only has one virtqueue, so it only has one thread. It is really + * simple: the Guest asks for a block number and we read or write that position + * in the file. + * + * Before we serviced each virtqueue in a separate thread, that was unacceptably + * slow: the Guest waits until the read is finished before running anything + * else, even if it could have been doing useful work. + * + * We could have used async I/O, except it's reputed to suck so hard that + * characters actually go missing from your code when you try to use it. */ static void blk_request(struct virtqueue *vq) { @@ -1406,47 +1599,64 @@ static void blk_request(struct virtqueue *vq) struct iovec iov[vq->vring.num]; off64_t off; - /* Get the next request. */ + /* + * Get the next request, where we normally wait. It triggers the + * interrupt to acknowledge previously serviced requests (if any). + */ head = wait_for_vq_desc(vq, iov, &out_num, &in_num); - /* Every block request should contain at least one output buffer + /* + * Every block request should contain at least one output buffer * (detailing the location on disk and the type of request) and one - * input buffer (to hold the result). */ + * input buffer (to hold the result). + */ if (out_num == 0 || in_num == 0) errx(1, "Bad virtblk cmd %u out=%u in=%u", head, out_num, in_num); out = convert(&iov[0], struct virtio_blk_outhdr); in = convert(&iov[out_num+in_num-1], u8); + /* + * For historical reasons, block operations are expressed in 512 byte + * "sectors". + */ off = out->sector * 512; - /* The block device implements "barriers", where the Guest indicates + /* + * The block device implements "barriers", where the Guest indicates * that it wants all previous writes to occur before this write. We * don't have a way of asking our kernel to do a barrier, so we just - * synchronize all the data in the file. Pretty poor, no? */ + * synchronize all the data in the file. Pretty poor, no? + */ if (out->type & VIRTIO_BLK_T_BARRIER) fdatasync(vblk->fd); - /* In general the virtio block driver is allowed to try SCSI commands. - * It'd be nice if we supported eject, for example, but we don't. */ + /* + * In general the virtio block driver is allowed to try SCSI commands. + * It'd be nice if we supported eject, for example, but we don't. + */ if (out->type & VIRTIO_BLK_T_SCSI_CMD) { fprintf(stderr, "Scsi commands unsupported\n"); *in = VIRTIO_BLK_S_UNSUPP; wlen = sizeof(*in); } else if (out->type & VIRTIO_BLK_T_OUT) { - /* Write */ - - /* Move to the right location in the block file. This can fail - * if they try to write past end. */ + /* + * Write + * + * Move to the right location in the block file. This can fail + * if they try to write past end. + */ if (lseek64(vblk->fd, off, SEEK_SET) != off) err(1, "Bad seek to sector %llu", out->sector); ret = writev(vblk->fd, iov+1, out_num-1); verbose("WRITE to sector %llu: %i\n", out->sector, ret); - /* Grr... Now we know how long the descriptor they sent was, we + /* + * Grr... Now we know how long the descriptor they sent was, we * make sure they didn't try to write over the end of the block - * file (possibly extending it). */ + * file (possibly extending it). + */ if (ret > 0 && off + ret > vblk->len) { /* Trim it back to the correct length */ ftruncate64(vblk->fd, vblk->len); @@ -1456,10 +1666,12 @@ static void blk_request(struct virtqueue *vq) wlen = sizeof(*in); *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR); } else { - /* Read */ - - /* Move to the right location in the block file. This can fail - * if they try to read past end. */ + /* + * Read + * + * Move to the right location in the block file. This can fail + * if they try to read past end. + */ if (lseek64(vblk->fd, off, SEEK_SET) != off) err(1, "Bad seek to sector %llu", out->sector); @@ -1474,13 +1686,16 @@ static void blk_request(struct virtqueue *vq) } } - /* OK, so we noted that it was pretty poor to use an fdatasync as a + /* + * OK, so we noted that it was pretty poor to use an fdatasync as a * barrier. But Christoph Hellwig points out that we need a sync * *afterwards* as well: "Barriers specify no reordering to the front - * or the back." And Jens Axboe confirmed it, so here we are: */ + * or the back." And Jens Axboe confirmed it, so here we are: + */ if (out->type & VIRTIO_BLK_T_BARRIER) fdatasync(vblk->fd); + /* Finished that request. */ add_used(vq, head, wlen); } @@ -1491,7 +1706,7 @@ static void setup_block_file(const char *filename) struct vblk_info *vblk; struct virtio_blk_config conf; - /* The device responds to return from I/O thread. */ + /* Creat the device. */ dev = new_device("block", VIRTIO_ID_BLOCK); /* The device has one virtqueue, where the Guest places requests. */ @@ -1510,27 +1725,32 @@ static void setup_block_file(const char *filename) /* Tell Guest how many sectors this device has. */ conf.capacity = cpu_to_le64(vblk->len / 512); - /* Tell Guest not to put in too many descriptors at once: two are used - * for the in and out elements. */ + /* + * Tell Guest not to put in too many descriptors at once: two are used + * for the in and out elements. + */ add_feature(dev, VIRTIO_BLK_F_SEG_MAX); conf.seg_max = cpu_to_le32(VIRTQUEUE_NUM - 2); - set_config(dev, sizeof(conf), &conf); + /* Don't try to put whole struct: we have 8 bit limit. */ + set_config(dev, offsetof(struct virtio_blk_config, geometry), &conf); verbose("device %u: virtblock %llu sectors\n", ++devices.device_num, le64_to_cpu(conf.capacity)); } -struct rng_info { - int rfd; -}; - -/* Our random number generator device reads from /dev/random into the Guest's +/*L:211 + * Our random number generator device reads from /dev/random into the Guest's * input buffers. The usual case is that the Guest doesn't want random numbers * and so has no buffers although /dev/random is still readable, whereas * console is the reverse. * - * The same logic applies, however. */ + * The same logic applies, however. + */ +struct rng_info { + int rfd; +}; + static void rng_input(struct virtqueue *vq) { int len; @@ -1543,9 +1763,10 @@ static void rng_input(struct virtqueue *vq) if (out_num) errx(1, "Output buffers in rng?"); - /* This is why we convert to iovecs: the readv() call uses them, and so - * it reads straight into the Guest's buffer. We loop to make sure we - * fill it. */ + /* + * Just like the console write, we loop to cover the whole iovec. + * In this case, short reads actually happen quite a bit. + */ while (!iov_empty(iov, in_num)) { len = readv(rng_info->rfd, iov, in_num); if (len <= 0) @@ -1558,15 +1779,18 @@ static void rng_input(struct virtqueue *vq) add_used(vq, head, totlen); } -/* And this creates a "hardware" random number device for the Guest. */ +/*L:199 + * This creates a "hardware" random number device for the Guest. + */ static void setup_rng(void) { struct device *dev; struct rng_info *rng_info = malloc(sizeof(*rng_info)); + /* Our device's privat info simply contains the /dev/random fd. */ rng_info->rfd = open_or_die("/dev/random", O_RDONLY); - /* The device responds to return from I/O thread. */ + /* Create the new device. */ dev = new_device("rng", VIRTIO_ID_RNG); dev->priv = rng_info; @@ -1582,8 +1806,10 @@ static void __attribute__((noreturn)) restart_guest(void) { unsigned int i; - /* Since we don't track all open fds, we simply close everything beyond - * stderr. */ + /* + * Since we don't track all open fds, we simply close everything beyond + * stderr. + */ for (i = 3; i < FD_SETSIZE; i++) close(i); @@ -1594,8 +1820,10 @@ 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 - * its input and output, and finally, lays it to rest. */ +/*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(void) { for (;;) { @@ -1630,7 +1858,7 @@ static void __attribute__((noreturn)) run_guest(void) * * Are you ready? Take a deep breath and join me in the core of the Host, in * "make Host". - :*/ +:*/ static struct option opts[] = { { "verbose", 0, NULL, 'v' }, @@ -1651,8 +1879,7 @@ static void usage(void) /*L:105 The main routine is where the real work begins: */ int main(int argc, char *argv[]) { - /* Memory, top-level pagetable, code startpoint and size of the - * (optional) initrd. */ + /* Memory, code startpoint and size of the (optional) initrd. */ unsigned long mem = 0, start, initrd_size = 0; /* Two temporaries. */ int i, c; @@ -1664,24 +1891,32 @@ int main(int argc, char *argv[]) /* Save the args: we "reboot" by execing ourselves again. */ main_args = argv; - /* First we initialize the device list. We keep a pointer to the last + /* + * First we initialize the device list. We keep a pointer to the last * device, and the next interrupt number to use for devices (1: - * remember that 0 is used by the timer). */ + * remember that 0 is used by the timer). + */ devices.lastdev = NULL; devices.next_irq = 1; + /* We're CPU 0. In fact, that's the only CPU possible right now. */ cpu_id = 0; - /* We need to know how much memory so we can set up the device + + /* + * We need to know how much memory so we can set up the device * descriptor and memory pages for the devices as we parse the command * line. So we quickly look through the arguments to find the amount - * of memory now. */ + * of memory now. + */ for (i = 1; i < argc; i++) { if (argv[i][0] != '-') { mem = atoi(argv[i]) * 1024 * 1024; - /* We start by mapping anonymous pages over all of + /* + * We start by mapping anonymous pages over all of * guest-physical memory range. This fills it with 0, * and ensures that the Guest won't be killed when it - * tries to access it. */ + * tries to access it. + */ guest_base = map_zeroed_pages(mem / getpagesize() + DEVICE_PAGES); guest_limit = mem; @@ -1714,8 +1949,10 @@ int main(int argc, char *argv[]) usage(); } } - /* After the other arguments we expect memory and kernel image name, - * followed by command line arguments for the kernel. */ + /* + * After the other arguments we expect memory and kernel image name, + * followed by command line arguments for the kernel. + */ if (optind + 2 > argc) usage(); @@ -1733,20 +1970,26 @@ int main(int argc, char *argv[]) /* Map the initrd image if requested (at top of physical memory) */ if (initrd_name) { initrd_size = load_initrd(initrd_name, mem); - /* These are the location in the Linux boot header where the - * start and size of the initrd are expected to be found. */ + /* + * These are the location in the Linux boot header where the + * start and size of the initrd are expected to be found. + */ boot->hdr.ramdisk_image = mem - initrd_size; boot->hdr.ramdisk_size = initrd_size; /* The bootloader type 0xFF means "unknown"; that's OK. */ boot->hdr.type_of_loader = 0xFF; } - /* The Linux boot header contains an "E820" memory map: ours is a - * simple, single region. */ + /* + * The Linux boot header contains an "E820" memory map: ours is a + * simple, single region. + */ boot->e820_entries = 1; boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM }); - /* The boot header contains a command line pointer: we put the command - * line after the boot header. */ + /* + * The boot header contains a command line pointer: we put the command + * line after the boot header. + */ boot->hdr.cmd_line_ptr = to_guest_phys(boot + 1); /* We use a simple helper to copy the arguments separated by spaces. */ concat((char *)(boot + 1), argv+optind+2); @@ -1760,11 +2003,13 @@ int main(int argc, char *argv[]) /* Tell the entry path not to try to reload segment registers. */ boot->hdr.loadflags |= KEEP_SEGMENTS; - /* We tell the kernel to initialize the Guest: this returns the open - * /dev/lguest file descriptor. */ + /* + * We tell the kernel to initialize the Guest: this returns the open + * /dev/lguest file descriptor. + */ tell_kernel(start); - /* Ensure that we terminate if a child dies. */ + /* Ensure that we terminate if a device-servicing child dies. */ signal(SIGCHLD, kill_launcher); /* If we exit via err(), this kills all the threads, restores tty. */ diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 1634c6dcecae..50189bf07d53 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -60,6 +60,8 @@ framerelay.txt - info on using Frame Relay/Data Link Connection Identifier (DLCI). generic_netlink.txt - info on Generic Netlink +ieee802154.txt + - Linux IEEE 802.15.4 implementation, API and drivers ip-sysctl.txt - /proc/sys/net/ipv4/* variables ip_dynaddr.txt diff --git a/Documentation/networking/6pack.txt b/Documentation/networking/6pack.txt index d0777a1200e1..8f339428fdf4 100644 --- a/Documentation/networking/6pack.txt +++ b/Documentation/networking/6pack.txt @@ -1,7 +1,7 @@ This is the 6pack-mini-HOWTO, written by Andreas Könsgen DG3KQ -Internet: ajk@iehk.rwth-aachen.de +Internet: ajk@comnets.uni-bremen.de AMPR-net: dg3kq@db0pra.ampr.org AX.25: dg3kq@db0ach.#nrw.deu.eu diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index a0280ad2edc9..1d4ed66b1b1c 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -69,7 +69,7 @@ We provide an example of simple HardMAC driver at drivers/ieee802154/fakehard.c SoftMAC ======= -We are going to provide intermediate layer impelementing IEEE 802.15.4 MAC +We are going to provide intermediate layer implementing IEEE 802.15.4 MAC in software. This is currently WIP. See header include/net/ieee802154/mac802154.h and several drivers in diff --git a/Documentation/power/power_supply_class.txt b/Documentation/power/power_supply_class.txt index c6cd4956047c..9f16c5178b66 100644 --- a/Documentation/power/power_supply_class.txt +++ b/Documentation/power/power_supply_class.txt @@ -76,6 +76,11 @@ STATUS - this attribute represents operating status (charging, full, discharging (i.e. powering a load), etc.). This corresponds to BATTERY_STATUS_* values, as defined in battery.h. +CHARGE_TYPE - batteries can typically charge at different rates. +This defines trickle and fast charges. For batteries that +are already charged or discharging, 'n/a' can be displayed (or +'unknown', if the status is not known). + HEALTH - represents health of the battery, values corresponds to POWER_SUPPLY_HEALTH_*, defined in battery.h. @@ -108,6 +113,8 @@ relative, time-based measurements. ENERGY_FULL, ENERGY_EMPTY - same as above but for energy. CAPACITY - capacity in percents. +CAPACITY_LEVEL - capacity level. This corresponds to +POWER_SUPPLY_CAPACITY_LEVEL_*. TEMP - temperature of the power supply. TEMP_AMBIENT - ambient temperature. diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 1df7f9cdab05..86eabe6c3419 100644 --- a/Documentation/scheduler/sched-rt-group.txt +++ b/Documentation/scheduler/sched-rt-group.txt @@ -73,7 +73,7 @@ The remaining CPU time will be used for user input and other tasks. Because realtime tasks have explicitly allocated the CPU time they need to perform their tasks, buffer underruns in the graphics or audio can be eliminated. -NOTE: the above example is not fully implemented as of yet (2.6.25). We still +NOTE: the above example is not fully implemented yet. We still lack an EDF scheduler to make non-uniform periods usable. @@ -140,14 +140,15 @@ The other option is: .o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups") -This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_us" -to control the CPU time reserved for each control group instead. +This uses the /cgroup virtual file system and +"/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each +control group instead. For more information on working with control groups, you should read Documentation/cgroups/cgroups.txt as well. -Group settings are checked against the following limits in order to keep the configuration -schedulable: +Group settings are checked against the following limits in order to keep the +configuration schedulable: \Sum_{i} runtime_{i} / global_period <= global_runtime / global_period @@ -189,7 +190,7 @@ Implementing SCHED_EDF might take a while to complete. Priority Inheritance is the biggest challenge as the current linux PI infrastructure is geared towards the limited static priority levels 0-99. With deadline scheduling you need to do deadline inheritance (since priority is inversely proportional to the -deadline delta (deadline - now). +deadline delta (deadline - now)). This means the whole PI machinery will have to be reworked - and that is one of the most complex pieces of code we have. diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt index 4252697a95d6..f9d11140af91 100644 --- a/Documentation/sound/alsa/ALSA-Configuration.txt +++ b/Documentation/sound/alsa/ALSA-Configuration.txt @@ -768,6 +768,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. bdl_pos_adj - Specifies the DMA IRQ timing delay in samples. Passing -1 will make the driver to choose the appropriate value based on the controller chip. + patch - Specifies the early "patch" files to modify the HD-audio + setup before initializing the codecs. This option is + available only when CONFIG_SND_HDA_PATCH_LOADER=y is set. + See HD-Audio.txt for details. [Single (global) options] single_cmd - Use single immediate commands to communicate with diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt index a1a830f7b24e..0fe1cd95eb45 100644 --- a/Documentation/sound/alsa/HD-Audio-Models.txt +++ b/Documentation/sound/alsa/HD-Audio-Models.txt @@ -114,8 +114,8 @@ ALC662/663/272 samsung-nc10 Samsung NC10 mini notebook auto auto-config reading BIOS (default) -ALC882/885 -========== +ALC882/883/885/888/889 +====================== 3stack-dig 3-jack with SPDIF I/O 6stack-dig 6-jack digital with SPDIF I/O arima Arima W820Di1 @@ -127,12 +127,8 @@ ALC882/885 mbp3 Macbook Pro rev3 imac24 iMac 24'' with jack detection w2jc ASUS W2JC - auto auto-config reading BIOS (default) - -ALC883/888 -========== - 3stack-dig 3-jack with SPDIF I/O - 6stack-dig 6-jack digital with SPDIF I/O + 3stack-2ch-dig 3-jack with SPDIF I/O (ALC883) + alc883-6stack-dig 6-jack digital with SPDIF I/O (ALC883) 3stack-6ch 3-jack 6-channel 3stack-6ch-dig 3-jack 6-channel with SPDIF I/O 6stack-dig-demo 6-jack digital for Intel demo board @@ -159,6 +155,8 @@ ALC883/888 fujitsu-pi2515 Fujitsu AMILO Pi2515 fujitsu-xa3530 Fujitsu AMILO XA3530 3stack-6ch-intel Intel DG33* boards + intel-alc889a Intel IbexPeak with ALC889A + intel-x58 Intel DX58 with ALC889 asus-p5q ASUS P5Q-EM boards mb31 MacBook 3,1 sony-vaio-tt Sony VAIO TT @@ -385,3 +383,7 @@ STAC9872 ======== vaio VAIO laptop without SPDIF auto BIOS setup (default) + +Cirrus Logic CS4206/4207 +======================== + mbp55 MacBook Pro 5,5 diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt index 71ac995b1915..7b8a5f947d1d 100644 --- a/Documentation/sound/alsa/HD-Audio.txt +++ b/Documentation/sound/alsa/HD-Audio.txt @@ -139,6 +139,10 @@ The driver checks PCI SSID and looks through the static configuration table until any matching entry is found. If you have a new machine, you may see a message like below: ------------------------------------------------------------------------ + hda_codec: ALC880: BIOS auto-probing. +------------------------------------------------------------------------ +Meanwhile, in the earlier versions, you would see a message like: +------------------------------------------------------------------------ hda_codec: Unknown model for ALC880, trying auto-probe from BIOS... ------------------------------------------------------------------------ Even if you see such a message, DON'T PANIC. Take a deep breath and @@ -403,6 +407,66 @@ re-configure based on that state, run like below: ------------------------------------------------------------------------ +Early Patching +~~~~~~~~~~~~~~ +When CONFIG_SND_HDA_PATCH_LOADER=y is set, you can pass a "patch" as a +firmware file for modifying the HD-audio setup before initializing the +codec. This can work basically like the reconfiguration via sysfs in +the above, but it does it before the first codec configuration. + +A patch file is a plain text file which looks like below: + +------------------------------------------------------------------------ + [codec] + 0x12345678 0xabcd1234 2 + + [model] + auto + + [pincfg] + 0x12 0x411111f0 + + [verb] + 0x20 0x500 0x03 + 0x20 0x400 0xff + + [hint] + hp_detect = yes +------------------------------------------------------------------------ + +The file needs to have a line `[codec]`. The next line should contain +three numbers indicating the codec vendor-id (0x12345678 in the +example), the codec subsystem-id (0xabcd1234) and the address (2) of +the codec. The rest patch entries are applied to this specified codec +until another codec entry is given. + +The `[model]` line allows to change the model name of the each codec. +In the example above, it will be changed to model=auto. +Note that this overrides the module option. + +After the `[pincfg]` line, the contents are parsed as the initial +default pin-configurations just like `user_pin_configs` sysfs above. +The values can be shown in user_pin_configs sysfs file, too. + +Similarly, the lines after `[verb]` are parsed as `init_verbs` +sysfs entries, and the lines after `[hint]` are parsed as `hints` +sysfs entries, respectively. + +The hd-audio driver reads the file via request_firmware(). Thus, +a patch file has to be located on the appropriate firmware path, +typically, /lib/firmware. For example, when you pass the option +`patch=hda-init.fw`, the file /lib/firmware/hda-init-fw must be +present. + +The patch module option is specific to each card instance, and you +need to give one file name for each instance, separated by commas. +For example, if you have two cards, one for an on-board analog and one +for an HDMI video board, you may pass patch option like below: +------------------------------------------------------------------------ + options snd-hda-intel patch=on-board-patch,hdmi-patch +------------------------------------------------------------------------ + + Power-Saving ~~~~~~~~~~~~ The power-saving is a kind of auto-suspend of the device. When the diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt index 381908d8ca42..719a819f8cc2 100644 --- a/Documentation/sound/alsa/Procfile.txt +++ b/Documentation/sound/alsa/Procfile.txt @@ -101,6 +101,8 @@ card*/pcm*/xrun_debug bit 0 = Enable XRUN/jiffies debug messages bit 1 = Show stack trace at XRUN / jiffies check bit 2 = Enable additional jiffies check + bit 3 = Log hwptr update at each period interrupt + bit 4 = Log hwptr update at each snd_pcm_update_hw_ptr() When the bit 0 is set, the driver will show the messages to kernel log when an xrun is detected. The debug message is @@ -117,6 +119,9 @@ card*/pcm*/xrun_debug buggy) hardware that doesn't give smooth pointer updates. This feature is enabled via the bit 2. + Bits 3 and 4 are for logging the hwptr records. Note that + these will give flood of kernel messages. + card*/pcm*/sub*/info The general information of this PCM sub-stream. diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index cf42b820ff9d..d56a01775423 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -66,7 +66,8 @@ On all - write a character to /proc/sysrq-trigger. e.g.: 'b' - Will immediately reboot the system without syncing or unmounting your disks. -'c' - Will perform a kexec reboot in order to take a crashdump. +'c' - Will perform a system crash by a NULL pointer dereference. + A crashdump will be taken if configured. 'd' - Shows all locks that are held. @@ -141,8 +142,8 @@ useful when you want to exit a program that will not let you switch consoles. re'B'oot is good when you're unable to shut down. But you should also 'S'ync and 'U'mount first. -'C'rashdump can be used to manually trigger a crashdump when the system is hung. -The kernel needs to have been built with CONFIG_KEXEC enabled. +'C'rash can be used to manually trigger a crashdump when the system is hung. +Note that this just triggers a crash if there is no dump mechanism available. 'S'ync is great when your system is locked up, it allows you to sync your disks and will certainly lessen the chance of data loss and fscking. Note diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885 index 450b8f8c389b..525edb37c758 100644 --- a/Documentation/video4linux/CARDLIST.cx23885 +++ b/Documentation/video4linux/CARDLIST.cx23885 @@ -21,3 +21,5 @@ 20 -> Hauppauge WinTV-HVR1255 [0070:2251] 21 -> Hauppauge WinTV-HVR1210 [0070:2291,0070:2295] 22 -> Mygica X8506 DMB-TH [14f1:8651] + 23 -> Magic-Pro ProHDTV Extreme 2 [14f1:8657] + 24 -> Hauppauge WinTV-HVR1850 [0070:8541] diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx index 014d255231fc..084a7b62451e 100644 --- a/Documentation/video4linux/CARDLIST.em28xx +++ b/Documentation/video4linux/CARDLIST.em28xx @@ -20,7 +20,7 @@ 19 -> EM2860/SAA711X Reference Design (em2860) 20 -> AMD ATI TV Wonder HD 600 (em2880) [0438:b002] 21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800) [eb1a:2801] - 22 -> Unknown EM2750/EM2751 webcam grabber (em2750) [eb1a:2750,eb1a:2751] + 22 -> EM2710/EM2750/EM2751 webcam grabber (em2750) [eb1a:2750,eb1a:2751] 23 -> Huaqi DLCW-130 (em2750) 24 -> D-Link DUB-T210 TV Tuner (em2820/em2840) [2001:f112] 25 -> Gadmei UTV310 (em2820/em2840) @@ -33,7 +33,7 @@ 34 -> Terratec Cinergy A Hybrid XS (em2860) [0ccd:004f] 35 -> Typhoon DVD Maker (em2860) 36 -> NetGMBH Cam (em2860) - 37 -> Gadmei UTV330 (em2860) + 37 -> Gadmei UTV330 (em2860) [eb1a:50a6] 38 -> Yakumo MovieMixer (em2861) 39 -> KWorld PVRTV 300U (em2861) [eb1a:e300] 40 -> Plextor ConvertX PX-TV100U (em2861) [093b:a005] diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner index be67844074dd..ba9fa679e2d3 100644 --- a/Documentation/video4linux/CARDLIST.tuner +++ b/Documentation/video4linux/CARDLIST.tuner @@ -78,3 +78,4 @@ tuner=77 - TCL tuner MF02GIP-5N-E tuner=78 - Philips FMD1216MEX MK3 Hybrid Tuner tuner=79 - Philips PAL/SECAM multi (FM1216 MK5) tuner=80 - Philips FQ1216LME MK3 PAL/SECAM w/active loopthrough +tuner=81 - Partsnic (Daewoo) PTI-5NF05 diff --git a/Documentation/video4linux/CQcam.txt b/Documentation/video4linux/CQcam.txt index 04986efb731c..d230878e473e 100644 --- a/Documentation/video4linux/CQcam.txt +++ b/Documentation/video4linux/CQcam.txt @@ -18,8 +18,8 @@ Table of Contents 1.0 Introduction - The file ../drivers/char/c-qcam.c is a device driver for the -Logitech (nee Connectix) parallel port interface color CCD camera. + The file ../../drivers/media/video/c-qcam.c is a device driver for +the Logitech (nee Connectix) parallel port interface color CCD camera. This is a fairly inexpensive device for capturing images. Logitech does not currently provide information for developers, but many people have engineered several solutions for non-Microsoft use of the Color diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt index 2bcf78896e22..b43702470130 100644 --- a/Documentation/video4linux/gspca.txt +++ b/Documentation/video4linux/gspca.txt @@ -44,7 +44,9 @@ zc3xx 0458:7007 Genius VideoCam V2 zc3xx 0458:700c Genius VideoCam V3 zc3xx 0458:700f Genius VideoCam Web V2 sonixj 0458:7025 Genius Eye 311Q +sn9c20x 0458:7029 Genius Look 320s sonixj 0458:702e Genius Slim 310 NB +sn9c20x 045e:00f4 LifeCam VX-6000 (SN9C20x + OV9650) sonixj 045e:00f5 MicroSoft VX3000 sonixj 045e:00f7 MicroSoft VX1000 ov519 045e:028c Micro$oft xbox cam @@ -138,6 +140,7 @@ spca500 04fc:7333 PalmPixDC85 sunplus 04fc:ffff Pure DigitalDakota spca501 0506:00df 3Com HomeConnect Lite sunplus 052b:1513 Megapix V4 +sunplus 052b:1803 MegaImage VI tv8532 0545:808b Veo Stingray tv8532 0545:8333 Veo Stingray sunplus 0546:3155 Polaroid PDC3070 @@ -233,6 +236,7 @@ pac7311 093a:2621 PAC731x pac7311 093a:2622 Genius Eye 312 pac7311 093a:2624 PAC7302 pac7311 093a:2626 Labtec 2200 +pac7311 093a:2629 Genious iSlim 300 pac7311 093a:262a Webcam 300k pac7311 093a:262c Philips SPC 230 NC zc3xx 0ac8:0302 Z-star Vimicro zc0302 @@ -245,6 +249,7 @@ zc3xx 0ac8:305b Z-star Vimicro zc0305b zc3xx 0ac8:307b Ldlc VC302+Ov7620 vc032x 0ac8:c001 Sony embedded vimicro vc032x 0ac8:c002 Sony embedded vimicro +vc032x 0ac8:c301 Samsung Q1 Ultra Premium spca508 0af9:0010 Hama USB Sightcam 100 spca508 0af9:0011 Hama USB Sightcam 100 sonixb 0c45:6001 Genius VideoCAM NB @@ -282,6 +287,29 @@ sonixj 0c45:613a Microdia Sonix PC Camera sonixj 0c45:613b Surfer SN-206 sonixj 0c45:613c Sonix Pccam168 sonixj 0c45:6143 Sonix Pccam168 +sonixj 0c45:6148 Digitus DA-70811/ZSMC USB PC Camera ZS211/Microdia +sn9c20x 0c45:6240 PC Camera (SN9C201 + MT9M001) +sn9c20x 0c45:6242 PC Camera (SN9C201 + MT9M111) +sn9c20x 0c45:6248 PC Camera (SN9C201 + OV9655) +sn9c20x 0c45:624e PC Camera (SN9C201 + SOI968) +sn9c20x 0c45:624f PC Camera (SN9C201 + OV9650) +sn9c20x 0c45:6251 PC Camera (SN9C201 + OV9650) +sn9c20x 0c45:6253 PC Camera (SN9C201 + OV9650) +sn9c20x 0c45:6260 PC Camera (SN9C201 + OV7670) +sn9c20x 0c45:6270 PC Camera (SN9C201 + MT9V011/MT9V111/MT9V112) +sn9c20x 0c45:627b PC Camera (SN9C201 + OV7660) +sn9c20x 0c45:627c PC Camera (SN9C201 + HV7131R) +sn9c20x 0c45:627f PC Camera (SN9C201 + OV9650) +sn9c20x 0c45:6280 PC Camera (SN9C202 + MT9M001) +sn9c20x 0c45:6282 PC Camera (SN9C202 + MT9M111) +sn9c20x 0c45:6288 PC Camera (SN9C202 + OV9655) +sn9c20x 0c45:628e PC Camera (SN9C202 + SOI968) +sn9c20x 0c45:628f PC Camera (SN9C202 + OV9650) +sn9c20x 0c45:62a0 PC Camera (SN9C202 + OV7670) +sn9c20x 0c45:62b0 PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112) +sn9c20x 0c45:62b3 PC Camera (SN9C202 + OV9655) +sn9c20x 0c45:62bb PC Camera (SN9C202 + OV7660) +sn9c20x 0c45:62bc PC Camera (SN9C202 + HV7131R) sunplus 0d64:0303 Sunplus FashionCam DXG etoms 102c:6151 Qcam Sangha CIF etoms 102c:6251 Qcam xxxxxx VGA @@ -290,6 +318,7 @@ spca561 10fd:7e50 FlyCam Usb 100 zc3xx 10fd:8050 Typhoon Webshot II USB 300k ov534 1415:2000 Sony HD Eye for PS3 (SLEH 00201) pac207 145f:013a Trust WB-1300N +sn9c20x 145f:013d Trust WB-3600R vc032x 15b8:6001 HP 2.0 Megapixel vc032x 15b8:6002 HP 2.0 Megapixel rz406aa spca501 1776:501c Arowana 300K CMOS Camera @@ -300,4 +329,11 @@ spca500 2899:012c Toptro Industrial spca508 8086:0110 Intel Easy PC Camera spca500 8086:0630 Intel Pocket PC Camera spca506 99fa:8988 Grandtec V.cap +sn9c20x a168:0610 Dino-Lite Digital Microscope (SN9C201 + HV7131R) +sn9c20x a168:0611 Dino-Lite Digital Microscope (SN9C201 + HV7131R) +sn9c20x a168:0613 Dino-Lite Digital Microscope (SN9C201 + HV7131R) +sn9c20x a168:0618 Dino-Lite Digital Microscope (SN9C201 + HV7131R) +sn9c20x a168:0614 Dino-Lite Digital Microscope (SN9C201 + MT9M111) +sn9c20x a168:0615 Dino-Lite Digital Microscope (SN9C201 + MT9M111) +sn9c20x a168:0617 Dino-Lite Digital Microscope (SN9C201 + MT9M111) spca561 abcd:cdee Petcam diff --git a/Documentation/vm/slqbinfo.c b/Documentation/vm/slqbinfo.c new file mode 100644 index 000000000000..3146d3d7c856 --- /dev/null +++ b/Documentation/vm/slqbinfo.c @@ -0,0 +1,1047 @@ +/* + * Slabinfo: Tool to get reports about slabs + * + * (C) 2007 sgi, Christoph Lameter + * + * Reworked by Lin Ming <ming.m.lin@intel.com> for SLQB + * + * Compile by: + * + * gcc -o slabinfo slabinfo.c + */ +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <dirent.h> +#include <strings.h> +#include <string.h> +#include <unistd.h> +#include <stdarg.h> +#include <getopt.h> +#include <regex.h> +#include <errno.h> + +#define MAX_SLABS 500 +#define MAX_ALIASES 500 +#define MAX_NODES 1024 + +struct slabinfo { + char *name; + int align, cache_dma, destroy_by_rcu; + int hwcache_align, object_size, objs_per_slab; + int slab_size, store_user; + int order, poison, reclaim_account, red_zone; + int batch; + unsigned long objects, slabs, total_objects; + unsigned long alloc, alloc_slab_fill, alloc_slab_new; + unsigned long free, free_remote; + unsigned long claim_remote_list, claim_remote_list_objects; + unsigned long flush_free_list, flush_free_list_objects, flush_free_list_remote; + unsigned long flush_rfree_list, flush_rfree_list_objects; + unsigned long flush_slab_free, flush_slab_partial; + int numa[MAX_NODES]; + int numa_partial[MAX_NODES]; +} slabinfo[MAX_SLABS]; + +int slabs = 0; +int actual_slabs = 0; +int highest_node = 0; + +char buffer[4096]; + +int show_empty = 0; +int show_report = 0; +int show_slab = 0; +int skip_zero = 1; +int show_numa = 0; +int show_track = 0; +int validate = 0; +int shrink = 0; +int show_inverted = 0; +int show_totals = 0; +int sort_size = 0; +int sort_active = 0; +int set_debug = 0; +int show_ops = 0; +int show_activity = 0; + +/* Debug options */ +int sanity = 0; +int redzone = 0; +int poison = 0; +int tracking = 0; +int tracing = 0; + +int page_size; + +regex_t pattern; + +void fatal(const char *x, ...) +{ + va_list ap; + + va_start(ap, x); + vfprintf(stderr, x, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + +void usage(void) +{ + printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n" + "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n" + "-A|--activity Most active slabs first\n" + "-d<options>|--debug=<options> Set/Clear Debug options\n" + "-D|--display-active Switch line format to activity\n" + "-e|--empty Show empty slabs\n" + "-h|--help Show usage information\n" + "-i|--inverted Inverted list\n" + "-l|--slabs Show slabs\n" + "-n|--numa Show NUMA information\n" + "-o|--ops Show kmem_cache_ops\n" + "-s|--shrink Shrink slabs\n" + "-r|--report Detailed report on single slabs\n" + "-S|--Size Sort by size\n" + "-t|--tracking Show alloc/free information\n" + "-T|--Totals Show summary information\n" + "-v|--validate Validate slabs\n" + "-z|--zero Include empty slabs\n" + "\nValid debug options (FZPUT may be combined)\n" + "a / A Switch on all debug options (=FZUP)\n" + "- Switch off all debug options\n" + "f / F Sanity Checks (SLAB_DEBUG_FREE)\n" + "z / Z Redzoning\n" + "p / P Poisoning\n" + "u / U Tracking\n" + "t / T Tracing\n" + ); +} + +unsigned long read_obj(const char *name) +{ + FILE *f = fopen(name, "r"); + + if (!f) + buffer[0] = 0; + else { + if (!fgets(buffer, sizeof(buffer), f)) + buffer[0] = 0; + fclose(f); + if (buffer[strlen(buffer)] == '\n') + buffer[strlen(buffer)] = 0; + } + return strlen(buffer); +} + + +/* + * Get the contents of an attribute + */ +unsigned long get_obj(const char *name) +{ + if (!read_obj(name)) + return 0; + + return atol(buffer); +} + +unsigned long get_obj_and_str(const char *name, char **x) +{ + unsigned long result = 0; + char *p; + + *x = NULL; + + if (!read_obj(name)) { + x = NULL; + return 0; + } + result = strtoul(buffer, &p, 10); + while (*p == ' ') + p++; + if (*p) + *x = strdup(p); + return result; +} + +void set_obj(struct slabinfo *s, const char *name, int n) +{ + char x[100]; + FILE *f; + + snprintf(x, 100, "%s/%s", s->name, name); + f = fopen(x, "w"); + if (!f) + fatal("Cannot write to %s\n", x); + + fprintf(f, "%d\n", n); + fclose(f); +} + +unsigned long read_slab_obj(struct slabinfo *s, const char *name) +{ + char x[100]; + FILE *f; + size_t l; + + snprintf(x, 100, "%s/%s", s->name, name); + f = fopen(x, "r"); + if (!f) { + buffer[0] = 0; + l = 0; + } else { + l = fread(buffer, 1, sizeof(buffer), f); + buffer[l] = 0; + fclose(f); + } + return l; +} + + +/* + * Put a size string together + */ +int store_size(char *buffer, unsigned long value) +{ + unsigned long divisor = 1; + char trailer = 0; + int n; + + if (value > 1000000000UL) { + divisor = 100000000UL; + trailer = 'G'; + } else if (value > 1000000UL) { + divisor = 100000UL; + trailer = 'M'; + } else if (value > 1000UL) { + divisor = 100; + trailer = 'K'; + } + + value /= divisor; + n = sprintf(buffer, "%ld",value); + if (trailer) { + buffer[n] = trailer; + n++; + buffer[n] = 0; + } + if (divisor != 1) { + memmove(buffer + n - 2, buffer + n - 3, 4); + buffer[n-2] = '.'; + n++; + } + return n; +} + +void decode_numa_list(int *numa, char *t) +{ + int node; + int nr; + + memset(numa, 0, MAX_NODES * sizeof(int)); + + if (!t) + return; + + while (*t == 'N') { + t++; + node = strtoul(t, &t, 10); + if (*t == '=') { + t++; + nr = strtoul(t, &t, 10); + numa[node] = nr; + if (node > highest_node) + highest_node = node; + } + while (*t == ' ') + t++; + } +} + +void slab_validate(struct slabinfo *s) +{ + if (strcmp(s->name, "*") == 0) + return; + + set_obj(s, "validate", 1); +} + +void slab_shrink(struct slabinfo *s) +{ + if (strcmp(s->name, "*") == 0) + return; + + set_obj(s, "shrink", 1); +} + +int line = 0; + +void first_line(void) +{ + if (show_activity) + printf("Name Objects Alloc Free %%Fill %%New " + "FlushR %%FlushR FlushR_Objs O\n"); + else + printf("Name Objects Objsize Space " + " O/S O %%Ef Batch Flg\n"); +} + +unsigned long slab_size(struct slabinfo *s) +{ + return s->slabs * (page_size << s->order); +} + +unsigned long slab_activity(struct slabinfo *s) +{ + return s->alloc + s->free; +} + +void slab_numa(struct slabinfo *s, int mode) +{ + int node; + + if (strcmp(s->name, "*") == 0) + return; + + if (!highest_node) { + printf("\n%s: No NUMA information available.\n", s->name); + return; + } + + if (skip_zero && !s->slabs) + return; + + if (!line) { + printf("\n%-21s:", mode ? "NUMA nodes" : "Slab"); + for(node = 0; node <= highest_node; node++) + printf(" %4d", node); + printf("\n----------------------"); + for(node = 0; node <= highest_node; node++) + printf("-----"); + printf("\n"); + } + printf("%-21s ", mode ? "All slabs" : s->name); + for(node = 0; node <= highest_node; node++) { + char b[20]; + + store_size(b, s->numa[node]); + printf(" %4s", b); + } + printf("\n"); + if (mode) { + printf("%-21s ", "Partial slabs"); + for(node = 0; node <= highest_node; node++) { + char b[20]; + + store_size(b, s->numa_partial[node]); + printf(" %4s", b); + } + printf("\n"); + } + line++; +} + +void show_tracking(struct slabinfo *s) +{ + printf("\n%s: Kernel object allocation\n", s->name); + printf("-----------------------------------------------------------------------\n"); + if (read_slab_obj(s, "alloc_calls")) + printf(buffer); + else + printf("No Data\n"); + + printf("\n%s: Kernel object freeing\n", s->name); + printf("------------------------------------------------------------------------\n"); + if (read_slab_obj(s, "free_calls")) + printf(buffer); + else + printf("No Data\n"); + +} + +void ops(struct slabinfo *s) +{ + if (strcmp(s->name, "*") == 0) + return; + + if (read_slab_obj(s, "ops")) { + printf("\n%s: kmem_cache operations\n", s->name); + printf("--------------------------------------------\n"); + printf(buffer); + } else + printf("\n%s has no kmem_cache operations\n", s->name); +} + +const char *onoff(int x) +{ + if (x) + return "On "; + return "Off"; +} + +void slab_stats(struct slabinfo *s) +{ + unsigned long total_alloc; + unsigned long total_free; + + total_alloc = s->alloc; + total_free = s->free; + + if (!total_alloc) + return; + + printf("\n"); + printf("Slab Perf Counter\n"); + printf("------------------------------------------------------------------------\n"); + printf("Alloc: %8lu, partial %8lu, page allocator %8lu\n", + total_alloc, + s->alloc_slab_fill, s->alloc_slab_new); + printf("Free: %8lu, partial %8lu, page allocator %8lu, remote %5lu\n", + total_free, + s->flush_slab_partial, + s->flush_slab_free, + s->free_remote); + printf("Claim: %8lu, objects %8lu\n", + s->claim_remote_list, + s->claim_remote_list_objects); + printf("Flush: %8lu, objects %8lu, remote: %8lu\n", + s->flush_free_list, + s->flush_free_list_objects, + s->flush_free_list_remote); + printf("FlushR:%8lu, objects %8lu\n", + s->flush_rfree_list, + s->flush_rfree_list_objects); +} + +void report(struct slabinfo *s) +{ + if (strcmp(s->name, "*") == 0) + return; + + printf("\nSlabcache: %-20s Order : %2d Objects: %lu\n", + s->name, s->order, s->objects); + if (s->hwcache_align) + printf("** Hardware cacheline aligned\n"); + if (s->cache_dma) + printf("** Memory is allocated in a special DMA zone\n"); + if (s->destroy_by_rcu) + printf("** Slabs are destroyed via RCU\n"); + if (s->reclaim_account) + printf("** Reclaim accounting active\n"); + + printf("\nSizes (bytes) Slabs Debug Memory\n"); + printf("------------------------------------------------------------------------\n"); + printf("Object : %7d Total : %7ld Sanity Checks : %s Total: %7ld\n", + s->object_size, s->slabs, "N/A", + s->slabs * (page_size << s->order)); + printf("SlabObj: %7d Full : %7s Redzoning : %s Used : %7ld\n", + s->slab_size, "N/A", + onoff(s->red_zone), s->objects * s->object_size); + printf("SlabSiz: %7d Partial: %7s Poisoning : %s Loss : %7ld\n", + page_size << s->order, "N/A", onoff(s->poison), + s->slabs * (page_size << s->order) - s->objects * s->object_size); + printf("Loss : %7d CpuSlab: %7s Tracking : %s Lalig: %7ld\n", + s->slab_size - s->object_size, "N/A", onoff(s->store_user), + (s->slab_size - s->object_size) * s->objects); + printf("Align : %7d Objects: %7d Tracing : %s Lpadd: %7ld\n", + s->align, s->objs_per_slab, "N/A", + ((page_size << s->order) - s->objs_per_slab * s->slab_size) * + s->slabs); + + ops(s); + show_tracking(s); + slab_numa(s, 1); + slab_stats(s); +} + +void slabcache(struct slabinfo *s) +{ + char size_str[20]; + char flags[20]; + char *p = flags; + + if (strcmp(s->name, "*") == 0) + return; + + if (actual_slabs == 1) { + report(s); + return; + } + + if (skip_zero && !show_empty && !s->slabs) + return; + + if (show_empty && s->slabs) + return; + + store_size(size_str, slab_size(s)); + + if (!line++) + first_line(); + + if (s->cache_dma) + *p++ = 'd'; + if (s->hwcache_align) + *p++ = 'A'; + if (s->poison) + *p++ = 'P'; + if (s->reclaim_account) + *p++ = 'a'; + if (s->red_zone) + *p++ = 'Z'; + if (s->store_user) + *p++ = 'U'; + + *p = 0; + if (show_activity) { + unsigned long total_alloc; + unsigned long total_free; + + total_alloc = s->alloc; + total_free = s->free; + + printf("%-21s %8ld %10ld %10ld %5ld %5ld %7ld %5ld %7ld %8d\n", + s->name, s->objects, + total_alloc, total_free, + total_alloc ? (s->alloc_slab_fill * 100 / total_alloc) : 0, + total_alloc ? (s->alloc_slab_new * 100 / total_alloc) : 0, + s->flush_rfree_list, + s->flush_rfree_list * 100 / (total_alloc + total_free), + s->flush_rfree_list_objects, + s->order); + } + else + printf("%-21s %8ld %7d %8s %4d %1d %3ld %4d %s\n", + s->name, s->objects, s->object_size, size_str, + s->objs_per_slab, s->order, + s->slabs ? (s->objects * s->object_size * 100) / + (s->slabs * (page_size << s->order)) : 100, + s->batch, flags); +} + +/* + * Analyze debug options. Return false if something is amiss. + */ +int debug_opt_scan(char *opt) +{ + if (!opt || !opt[0] || strcmp(opt, "-") == 0) + return 1; + + if (strcasecmp(opt, "a") == 0) { + sanity = 1; + poison = 1; + redzone = 1; + tracking = 1; + return 1; + } + + for ( ; *opt; opt++) + switch (*opt) { + case 'F' : case 'f': + if (sanity) + return 0; + sanity = 1; + break; + case 'P' : case 'p': + if (poison) + return 0; + poison = 1; + break; + + case 'Z' : case 'z': + if (redzone) + return 0; + redzone = 1; + break; + + case 'U' : case 'u': + if (tracking) + return 0; + tracking = 1; + break; + + case 'T' : case 't': + if (tracing) + return 0; + tracing = 1; + break; + default: + return 0; + } + return 1; +} + +int slab_empty(struct slabinfo *s) +{ + if (s->objects > 0) + return 0; + + /* + * We may still have slabs even if there are no objects. Shrinking will + * remove them. + */ + if (s->slabs != 0) + set_obj(s, "shrink", 1); + + return 1; +} + +void slab_debug(struct slabinfo *s) +{ + if (strcmp(s->name, "*") == 0) + return; + + if (redzone && !s->red_zone) { + if (slab_empty(s)) + set_obj(s, "red_zone", 1); + else + fprintf(stderr, "%s not empty cannot enable redzoning\n", s->name); + } + if (!redzone && s->red_zone) { + if (slab_empty(s)) + set_obj(s, "red_zone", 0); + else + fprintf(stderr, "%s not empty cannot disable redzoning\n", s->name); + } + if (poison && !s->poison) { + if (slab_empty(s)) + set_obj(s, "poison", 1); + else + fprintf(stderr, "%s not empty cannot enable poisoning\n", s->name); + } + if (!poison && s->poison) { + if (slab_empty(s)) + set_obj(s, "poison", 0); + else + fprintf(stderr, "%s not empty cannot disable poisoning\n", s->name); + } + if (tracking && !s->store_user) { + if (slab_empty(s)) + set_obj(s, "store_user", 1); + else + fprintf(stderr, "%s not empty cannot enable tracking\n", s->name); + } + if (!tracking && s->store_user) { + if (slab_empty(s)) + set_obj(s, "store_user", 0); + else + fprintf(stderr, "%s not empty cannot disable tracking\n", s->name); + } +} + +void totals(void) +{ + struct slabinfo *s; + + int used_slabs = 0; + char b1[20], b2[20], b3[20], b4[20]; + unsigned long long max = 1ULL << 63; + + /* Object size */ + unsigned long long min_objsize = max, max_objsize = 0, avg_objsize; + + /* Number of slabs in a slab cache */ + unsigned long long min_slabs = max, max_slabs = 0, + avg_slabs, total_slabs = 0; + + /* Size of the whole slab */ + unsigned long long min_size = max, max_size = 0, + avg_size, total_size = 0; + + /* Bytes used for object storage in a slab */ + unsigned long long min_used = max, max_used = 0, + avg_used, total_used = 0; + + /* Waste: Bytes used for alignment and padding */ + unsigned long long min_waste = max, max_waste = 0, + avg_waste, total_waste = 0; + /* Number of objects in a slab */ + unsigned long long min_objects = max, max_objects = 0, + avg_objects, total_objects = 0; + /* Waste per object */ + unsigned long long min_objwaste = max, + max_objwaste = 0, avg_objwaste, + total_objwaste = 0; + + /* Memory per object */ + unsigned long long min_memobj = max, + max_memobj = 0, avg_memobj, + total_objsize = 0; + + for (s = slabinfo; s < slabinfo + slabs; s++) { + unsigned long long size; + unsigned long used; + unsigned long long wasted; + unsigned long long objwaste; + + if (!s->slabs || !s->objects) + continue; + + used_slabs++; + + size = slab_size(s); + used = s->objects * s->object_size; + wasted = size - used; + objwaste = s->slab_size - s->object_size; + + if (s->object_size < min_objsize) + min_objsize = s->object_size; + if (s->slabs < min_slabs) + min_slabs = s->slabs; + if (size < min_size) + min_size = size; + if (wasted < min_waste) + min_waste = wasted; + if (objwaste < min_objwaste) + min_objwaste = objwaste; + if (s->objects < min_objects) + min_objects = s->objects; + if (used < min_used) + min_used = used; + if (s->slab_size < min_memobj) + min_memobj = s->slab_size; + + if (s->object_size > max_objsize) + max_objsize = s->object_size; + if (s->slabs > max_slabs) + max_slabs = s->slabs; + if (size > max_size) + max_size = size; + if (wasted > max_waste) + max_waste = wasted; + if (objwaste > max_objwaste) + max_objwaste = objwaste; + if (s->objects > max_objects) + max_objects = s->objects; + if (used > max_used) + max_used = used; + if (s->slab_size > max_memobj) + max_memobj = s->slab_size; + + total_slabs += s->slabs; + total_size += size; + total_waste += wasted; + + total_objects += s->objects; + total_used += used; + + total_objwaste += s->objects * objwaste; + total_objsize += s->objects * s->slab_size; + } + + if (!total_objects) { + printf("No objects\n"); + return; + } + if (!used_slabs) { + printf("No slabs\n"); + return; + } + + /* Per slab averages */ + avg_slabs = total_slabs / used_slabs; + avg_size = total_size / used_slabs; + avg_waste = total_waste / used_slabs; + + avg_objects = total_objects / used_slabs; + avg_used = total_used / used_slabs; + + /* Per object object sizes */ + avg_objsize = total_used / total_objects; + avg_objwaste = total_objwaste / total_objects; + avg_memobj = total_objsize / total_objects; + + printf("Slabcache Totals\n"); + printf("----------------\n"); + printf("Slabcaches : %3d Active: %3d\n", + slabs, used_slabs); + + store_size(b1, total_size);store_size(b2, total_waste); + store_size(b3, total_waste * 100 / total_used); + printf("Memory used: %6s # Loss : %6s MRatio:%6s%%\n", b1, b2, b3); + + store_size(b1, total_objects); + printf("# Objects : %6s\n", b1); + + printf("\n"); + printf("Per Cache Average Min Max Total\n"); + printf("---------------------------------------------------------\n"); + + store_size(b1, avg_objects);store_size(b2, min_objects); + store_size(b3, max_objects);store_size(b4, total_objects); + printf("#Objects %10s %10s %10s %10s\n", + b1, b2, b3, b4); + + store_size(b1, avg_slabs);store_size(b2, min_slabs); + store_size(b3, max_slabs);store_size(b4, total_slabs); + printf("#Slabs %10s %10s %10s %10s\n", + b1, b2, b3, b4); + + store_size(b1, avg_size);store_size(b2, min_size); + store_size(b3, max_size);store_size(b4, total_size); + printf("Memory %10s %10s %10s %10s\n", + b1, b2, b3, b4); + + store_size(b1, avg_used);store_size(b2, min_used); + store_size(b3, max_used);store_size(b4, total_used); + printf("Used %10s %10s %10s %10s\n", + b1, b2, b3, b4); + + store_size(b1, avg_waste);store_size(b2, min_waste); + store_size(b3, max_waste);store_size(b4, total_waste); + printf("Loss %10s %10s %10s %10s\n", + b1, b2, b3, b4); + + printf("\n"); + printf("Per Object Average Min Max\n"); + printf("---------------------------------------------\n"); + + store_size(b1, avg_memobj);store_size(b2, min_memobj); + store_size(b3, max_memobj); + printf("Memory %10s %10s %10s\n", + b1, b2, b3); + store_size(b1, avg_objsize);store_size(b2, min_objsize); + store_size(b3, max_objsize); + printf("User %10s %10s %10s\n", + b1, b2, b3); + + store_size(b1, avg_objwaste);store_size(b2, min_objwaste); + store_size(b3, max_objwaste); + printf("Loss %10s %10s %10s\n", + b1, b2, b3); +} + +void sort_slabs(void) +{ + struct slabinfo *s1,*s2; + + for (s1 = slabinfo; s1 < slabinfo + slabs; s1++) { + for (s2 = s1 + 1; s2 < slabinfo + slabs; s2++) { + int result; + + if (sort_size) + result = slab_size(s1) < slab_size(s2); + else if (sort_active) + result = slab_activity(s1) < slab_activity(s2); + else + result = strcasecmp(s1->name, s2->name); + + if (show_inverted) + result = -result; + + if (result > 0) { + struct slabinfo t; + + memcpy(&t, s1, sizeof(struct slabinfo)); + memcpy(s1, s2, sizeof(struct slabinfo)); + memcpy(s2, &t, sizeof(struct slabinfo)); + } + } + } +} + +int slab_mismatch(char *slab) +{ + return regexec(&pattern, slab, 0, NULL, 0); +} + +void read_slab_dir(void) +{ + DIR *dir; + struct dirent *de; + struct slabinfo *slab = slabinfo; + char *t; + + if (chdir("/sys/kernel/slab") && chdir("/sys/slab")) + fatal("SYSFS support for SLUB not active\n"); + + dir = opendir("."); + while ((de = readdir(dir))) { + if (de->d_name[0] == '.' || + (de->d_name[0] != ':' && slab_mismatch(de->d_name))) + continue; + switch (de->d_type) { + case DT_DIR: + if (chdir(de->d_name)) + fatal("Unable to access slab %s\n", slab->name); + slab->name = strdup(de->d_name); + slab->align = get_obj("align"); + slab->cache_dma = get_obj("cache_dma"); + slab->destroy_by_rcu = get_obj("destroy_by_rcu"); + slab->hwcache_align = get_obj("hwcache_align"); + slab->object_size = get_obj("object_size"); + slab->objects = get_obj("objects"); + slab->total_objects = get_obj("total_objects"); + slab->objs_per_slab = get_obj("objs_per_slab"); + slab->order = get_obj("order"); + slab->poison = get_obj("poison"); + slab->reclaim_account = get_obj("reclaim_account"); + slab->red_zone = get_obj("red_zone"); + slab->slab_size = get_obj("slab_size"); + slab->slabs = get_obj_and_str("slabs", &t); + decode_numa_list(slab->numa, t); + free(t); + slab->store_user = get_obj("store_user"); + slab->batch = get_obj("batch"); + slab->alloc = get_obj("alloc"); + slab->alloc_slab_fill = get_obj("alloc_slab_fill"); + slab->alloc_slab_new = get_obj("alloc_slab_new"); + slab->free = get_obj("free"); + slab->free_remote = get_obj("free_remote"); + slab->claim_remote_list = get_obj("claim_remote_list"); + slab->claim_remote_list_objects = get_obj("claim_remote_list_objects"); + slab->flush_free_list = get_obj("flush_free_list"); + slab->flush_free_list_objects = get_obj("flush_free_list_objects"); + slab->flush_free_list_remote = get_obj("flush_free_list_remote"); + slab->flush_rfree_list = get_obj("flush_rfree_list"); + slab->flush_rfree_list_objects = get_obj("flush_rfree_list_objects"); + slab->flush_slab_free = get_obj("flush_slab_free"); + slab->flush_slab_partial = get_obj("flush_slab_partial"); + + chdir(".."); + slab++; + break; + default : + fatal("Unknown file type %lx\n", de->d_type); + } + } + closedir(dir); + slabs = slab - slabinfo; + actual_slabs = slabs; + if (slabs > MAX_SLABS) + fatal("Too many slabs\n"); +} + +void output_slabs(void) +{ + struct slabinfo *slab; + + for (slab = slabinfo; slab < slabinfo + slabs; slab++) { + + if (show_numa) + slab_numa(slab, 0); + else if (show_track) + show_tracking(slab); + else if (validate) + slab_validate(slab); + else if (shrink) + slab_shrink(slab); + else if (set_debug) + slab_debug(slab); + else if (show_ops) + ops(slab); + else if (show_slab) + slabcache(slab); + else if (show_report) + report(slab); + } +} + +struct option opts[] = { + { "activity", 0, NULL, 'A' }, + { "debug", 2, NULL, 'd' }, + { "display-activity", 0, NULL, 'D' }, + { "empty", 0, NULL, 'e' }, + { "help", 0, NULL, 'h' }, + { "inverted", 0, NULL, 'i'}, + { "numa", 0, NULL, 'n' }, + { "ops", 0, NULL, 'o' }, + { "report", 0, NULL, 'r' }, + { "shrink", 0, NULL, 's' }, + { "slabs", 0, NULL, 'l' }, + { "track", 0, NULL, 't'}, + { "validate", 0, NULL, 'v' }, + { "zero", 0, NULL, 'z' }, + { "1ref", 0, NULL, '1'}, + { NULL, 0, NULL, 0 } +}; + +int main(int argc, char *argv[]) +{ + int c; + int err; + char *pattern_source; + + page_size = getpagesize(); + + while ((c = getopt_long(argc, argv, "Ad::Dehil1noprstvzTS", + opts, NULL)) != -1) + switch (c) { + case 'A': + sort_active = 1; + break; + case 'd': + set_debug = 1; + if (!debug_opt_scan(optarg)) + fatal("Invalid debug option '%s'\n", optarg); + break; + case 'D': + show_activity = 1; + break; + case 'e': + show_empty = 1; + break; + case 'h': + usage(); + return 0; + case 'i': + show_inverted = 1; + break; + case 'n': + show_numa = 1; + break; + case 'o': + show_ops = 1; + break; + case 'r': + show_report = 1; + break; + case 's': + shrink = 1; + break; + case 'l': + show_slab = 1; + break; + case 't': + show_track = 1; + break; + case 'v': + validate = 1; + break; + case 'z': + skip_zero = 0; + break; + case 'T': + show_totals = 1; + break; + case 'S': + sort_size = 1; + break; + + default: + fatal("%s: Invalid option '%c'\n", argv[0], optopt); + + } + + if (!show_slab && !show_track && !show_report + && !validate && !shrink && !set_debug && !show_ops) + show_slab = 1; + + if (argc > optind) + pattern_source = argv[optind]; + else + pattern_source = ".*"; + + err = regcomp(&pattern, pattern_source, REG_ICASE|REG_NOSUB); + if (err) + fatal("%s: Invalid pattern '%s' code %d\n", + argv[0], pattern_source, err); + read_slab_dir(); + if (show_totals) + totals(); + else { + sort_slabs(); + output_slabs(); + } + return 0; +} diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt index bb1f5c6e28b3..510917ff59ed 100644 --- a/Documentation/vm/slub.txt +++ b/Documentation/vm/slub.txt @@ -41,6 +41,8 @@ Possible debug options are P Poisoning (object and padding) U User tracking (free and alloc) T Trace (please only use on single slabs) + O Switch debugging off for caches that would have + caused higher minimum slab orders - Switch all debugging off (useful if the kernel is configured with CONFIG_SLUB_DEBUG_ON) @@ -59,6 +61,14 @@ to the dentry cache with slub_debug=F,dentry +Debugging options may require the minimum possible slab order to increase as +a result of storing the metadata (for example, caches with PAGE_SIZE object +sizes). This has a higher liklihood of resulting in slab allocation errors +in low memory situations or if there's high fragmentation of memory. To +switch off debugging for such caches by default, use + + slub_debug=O + In case you forgot to enable debugging on the kernel command line: It is possible to enable debugging manually when the kernel is up. Look at the contents of: |