From 941297f443f871b8c3372feccf27a8733f6ce9e9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Jul 2009 14:03:40 +0200 Subject: netfilter: nf_conntrack: nf_conntrack_alloc() fixes When a slab cache uses SLAB_DESTROY_BY_RCU, we must be careful when allocating objects, since slab allocator could give a freed object still used by lockless readers. In particular, nf_conntrack RCU lookups rely on ct->tuplehash[xxx].hnnode.next being always valid (ie containing a valid 'nulls' value, or a valid pointer to next object in hash chain.) kmem_cache_zalloc() setups object with NULL values, but a NULL value is not valid for ct->tuplehash[xxx].hnnode.next. Fix is to call kmem_cache_alloc() and do the zeroing ourself. As spotted by Patrick, we also need to make sure lookup keys are committed to memory before setting refcount to 1, or a lockless reader could get a reference on the old version of the object. Its key re-check could then pass the barrier. Signed-off-by: Eric Dumazet Signed-off-by: Patrick McHardy --- Documentation/RCU/rculist_nulls.txt | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt index 93cb28d05dc..18f9651ff23 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) -- cgit v1.2.3 From 673325951ef440ebace311bd542a9378d1b3025b Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Fri, 17 Jul 2009 04:47:19 +0000 Subject: Update Andreas Koensgen's email address The kernel has used a stale email address of Andreas for a few years. Signed-off-by: Ralf Baechle Signed-off-by: David S. Miller --- Documentation/networking/6pack.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/networking/6pack.txt b/Documentation/networking/6pack.txt index d0777a1200e..8f339428fdf 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 -- cgit v1.2.3 From acb9c1b2f406d25c381de2b429f65706cc04d3b5 Mon Sep 17 00:00:00 2001 From: Evgeniy Polyakov Date: Tue, 21 Jul 2009 12:43:51 -0700 Subject: connector: maintainer/mail update. Signed-off-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- Documentation/connector/cn_test.c | 4 ++-- Documentation/connector/ucon.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c index f688eba8770..6a5be5d5c8e 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 + * 2004+ Copyright (c) Evgeniy Polyakov * All rights reserved. * * This program is free software; you can redistribute it and/or modify @@ -194,5 +194,5 @@ module_init(cn_test_init); module_exit(cn_test_fini); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Evgeniy Polyakov "); +MODULE_AUTHOR("Evgeniy Polyakov "); MODULE_DESCRIPTION("Connector's test module"); diff --git a/Documentation/connector/ucon.c b/Documentation/connector/ucon.c index d738cde2a8d..c5092ad0ce4 100644 --- a/Documentation/connector/ucon.c +++ b/Documentation/connector/ucon.c @@ -1,7 +1,7 @@ /* * ucon.c * - * Copyright (c) 2004+ Evgeniy Polyakov + * Copyright (c) 2004+ Evgeniy Polyakov * * * This program is free software; you can redistribute it and/or modify -- cgit v1.2.3 From cedb8118e8cef21a2b73fd9cb70660ac19124c16 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 23 Jul 2009 11:04:13 +0200 Subject: ALSA: pcm - Add logging of hwptr updates and interrupt updates Added the logging functionality to xrun_debug to record the hwptr updates via snd_pcm_update_hw_ptr() and snd_pcm_update_hwptr_interrupt(), corresponding to 16 and 8, respectively. For example, # echo 9 > /proc/asound/card0/pcm0p/xrun_debug will record the position and other parameters at each period interrupt together with the normal XRUN debugging. Signed-off-by: Takashi Iwai --- Documentation/sound/alsa/Procfile.txt | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'Documentation') diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt index 381908d8ca4..719a819f8cc 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. -- cgit v1.2.3 From 8b220793d6fd309176438721088515be893630cd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 12 Jul 2009 10:56:21 -0300 Subject: V4L/DVB (12235): em28xx: detects sensors also with the generic em2750/2750 entry Webcams in general don't have eeprom. So, the sensor hint code should be called to properly detect what sensor is inside. Signed-off-by: Mauro Carvalho Chehab --- Documentation/video4linux/CARDLIST.em28xx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx index 014d255231f..68c236c0184 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) -- cgit v1.2.3 From 26e744b6b61066203fd57de0d3962353621e06f8 Mon Sep 17 00:00:00 2001 From: Brian Johnson Date: Sun, 19 Jul 2009 05:52:58 -0300 Subject: V4L/DVB (12283): gspca - sn9c20x: New subdriver for sn9c201 and sn9c202 bridges. Signed-off-by: Brian Johnson Signed-off-by: Jean-Francois Moine Signed-off-by: Mauro Carvalho Chehab --- Documentation/video4linux/gspca.txt | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'Documentation') diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt index 2bcf78896e2..573f95b5880 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 @@ -282,6 +284,28 @@ sonixj 0c45:613a Microdia Sonix PC Camera sonixj 0c45:613b Surfer SN-206 sonixj 0c45:613c Sonix Pccam168 sonixj 0c45:6143 Sonix Pccam168 +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 +314,7 @@ 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 +325,11 @@ 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 -- cgit v1.2.3 From a39ea210ec8c8f6ed381f8dafbe755c57b8f30c3 Mon Sep 17 00:00:00 2001 From: Lucian Adrian Grijincu Date: Mon, 27 Jul 2009 09:06:42 -0700 Subject: driver core: documentation: make it clear that sysfs is optional The original text suggested that sysfs is mandatory and always compiled in the kernel. Signed-off-by: Lucian Adrian Grijincu Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- Documentation/filesystems/sysfs.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt index 7e81e37c0b1..b245d524d56 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 -- cgit v1.2.3 From cab8bd3410d448279e3bd0fbf96d31db0bf770fa Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Wed, 29 Jul 2009 15:04:14 -0700 Subject: sysrq, kdump: make sysrq-c consistent commit d6580a9f15238b87e618310c862231ae3f352d2d ("kexec: sysrq: simplify sysrq-c handler") changed the behavior of sysrq-c to unconditional dereference of NULL pointer. So in cases with CONFIG_KEXEC, where crash_kexec() was directly called from sysrq-c before, now it can be said that a step of "real oops" was inserted before starting kdump. However, in contrast to oops via SysRq-c from keyboard which results in panic due to in_interrupt(), oops via "echo c > /proc/sysrq-trigger" will not become panic unless panic_on_oops=1. It means that even if dump is properly configured to be taken on panic, the sysrq-c from proc interface might not start crashdump while the sysrq-c from keyboard can start crashdump. This confuses traditional users of kdump, i.e. people who expect sysrq-c to do common behavior in both of the keyboard and proc interface. This patch brings the keyboard and proc interface behavior of sysrq-c in line, by forcing panic_on_oops=1 before oops in sysrq-c handler. And some updates in documentation are included, to clarify that there is no longer dependency with CONFIG_KEXEC, and that now the system can just crash by sysrq-c if no dump mechanism is configured. Signed-off-by: Hidetoshi Seto Cc: Lai Jiangshan Cc: Ken'ichi Ohmichi Acked-by: Neil Horman Acked-by: Vivek Goyal Cc: Brayan Arraes Cc: Eric W. Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysrq.txt | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index cf42b820ff9..d56a0177542 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 -- cgit v1.2.3 From 8ef562d112c82ec539775698f8b63ac5ec1bd766 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 30 Jul 2009 16:03:43 -0600 Subject: lguest: fix descriptor corruption in example launcher 1d589bb16b825b3a7b4edd34d997f1f1f953033d "Add serial number support for virtio_blk, V4a" extended 'struct virtio_blk_config' to 536 bytes. Lguest and S/390 both use an 8 bit value for the feature length, and this change broke them (if the code is naive). Signed-off-by: Rusty Russell Cc: John Cooper Cc: Christian Borntraeger --- Documentation/lguest/lguest.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 9ebcd6ef361..45d7d6dcae7 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -1105,6 +1105,9 @@ 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 @@ -1515,7 +1518,8 @@ static void setup_block_file(const char *filename) 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)); -- cgit v1.2.3 From 2e04ef76916d1e29a077ea9d0f2003c8fd86724d Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 30 Jul 2009 16:03:45 -0600 Subject: lguest: fix comment style I don't really notice it (except to begrudge the extra vertical space), but Ingo does. And he pointed out that one excuse of lguest is as a teaching tool, it should set a good example. Signed-off-by: Rusty Russell Cc: Ingo Molnar --- Documentation/lguest/lguest.c | 540 +++++++++++++++++++++++++++--------------- 1 file changed, 349 insertions(+), 191 deletions(-) (limited to 'Documentation') diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 45d7d6dcae7..aa66a52b73e 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 @@ -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 39 include files we need for this program, but I do want + * to draw attention to the use of kernel-style types. * * As Linus said, "C is a Spartan language, and so should your naming be." I * 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) @@ -100,8 +106,7 @@ 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; }; @@ -168,20 +173,24 @@ 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 +207,10 @@ 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 +252,12 @@ 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 +265,8 @@ 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 +281,8 @@ 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); @@ -283,8 +297,10 @@ 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) @@ -305,20 +321,24 @@ 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 +349,8 @@ 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 +358,28 @@ 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 +387,10 @@ 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 +408,15 @@ 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 +424,10 @@ 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 +446,11 @@ 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 +467,28 @@ 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 +500,16 @@ 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 +518,10 @@ 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 +538,12 @@ 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, @@ -522,20 +568,26 @@ 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) { @@ -576,12 +628,14 @@ 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 and 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 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) @@ -599,8 +653,10 @@ static unsigned wait_for_vq_desc(struct virtqueue *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 +676,10 @@ 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 +694,10 @@ 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 +716,10 @@ 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 +733,18 @@ 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 them about it. We'll then + * want to send them an interrupt, using trigger_irq(). + */ 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; @@ -698,7 +764,8 @@ 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. */ + * We associate some data with the console for our exit hack. + */ struct console_abort { /* How many times have they hit ^C? */ @@ -725,20 +792,24 @@ static void console_input(struct virtqueue *vq) 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(); } 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; @@ -809,8 +880,7 @@ 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. */ static void net_input(struct virtqueue *vq) { int len; @@ -842,8 +912,10 @@ 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); @@ -880,9 +952,10 @@ static void reset_device(struct device *dev) 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 and run it. 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 }; @@ -981,8 +1054,11 @@ static void handle_output(unsigned long addr) } } - /* 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 +1074,12 @@ 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 +1087,11 @@ 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 +1112,10 @@ 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 *)) { @@ -1061,10 +1143,12 @@ 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 +1156,18 @@ 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 +1181,11 @@ 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. */ @@ -1110,10 +1200,12 @@ static void set_config(struct device *dev, unsigned len, const void *conf) assert(dev->desc->config_len == len); } -/* This routine does all the creation and setup of a new device, including +/* + * This routine does all the creation and setup of a new device, including * calling new_dev_desc() to allocate the descriptor and device memory. * - * 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)); @@ -1126,10 +1218,12 @@ 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 @@ -1139,8 +1233,10 @@ 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; @@ -1148,8 +1244,10 @@ 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); } @@ -1160,10 +1258,12 @@ 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); @@ -1171,7 +1271,8 @@ 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= option which opens or creates a named pipe. This can be * used to send packets to another guest in a 1:1 manner. * @@ -1185,7 +1286,8 @@ 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) { @@ -1210,11 +1312,13 @@ 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; @@ -1234,9 +1338,11 @@ 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; @@ -1263,10 +1369,12 @@ 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"); @@ -1277,18 +1385,22 @@ 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; @@ -1305,13 +1417,14 @@ 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"); @@ -1366,7 +1479,8 @@ static void setup_tun_net(char *arg) devices.device_num, tapif, arg); } -/* Our block (disk) device should be really simple: the Guest asks for a block +/* + * 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. @@ -1374,7 +1488,9 @@ static void setup_tun_net(char *arg) * 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. */ + * So this was one reason why lguest now does all virtqueue servicing in + * separate threads: it's more efficient and more like a real device. + */ /* This hangs off device->priv. */ struct vblk_info @@ -1412,9 +1528,11 @@ static void blk_request(struct virtqueue *vq) /* Get the next request. */ 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); @@ -1423,33 +1541,41 @@ static void blk_request(struct virtqueue *vq) in = convert(&iov[out_num+in_num-1], u8); 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); @@ -1459,10 +1585,12 @@ 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); @@ -1477,10 +1605,12 @@ 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); @@ -1494,7 +1624,7 @@ 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. */ @@ -1513,8 +1643,10 @@ 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); @@ -1525,16 +1657,18 @@ static void setup_block_file(const char *filename) ++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; @@ -1547,9 +1681,11 @@ 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 + /* + * 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. */ + * fill it. + */ while (!iov_empty(iov, in_num)) { len = readv(rng_info->rfd, iov, in_num); if (len <= 0) @@ -1562,15 +1698,18 @@ 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; @@ -1586,8 +1725,10 @@ 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); @@ -1598,8 +1739,10 @@ 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 (;;) { @@ -1634,7 +1777,7 @@ 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' }, @@ -1655,8 +1798,7 @@ 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; @@ -1668,24 +1810,30 @@ 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; 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; @@ -1718,8 +1866,10 @@ 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(); @@ -1737,20 +1887,26 @@ 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); @@ -1764,8 +1920,10 @@ 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. */ -- cgit v1.2.3 From a91d74a3c4de8115295ee87350c13a329164aaaf Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 30 Jul 2009 16:03:45 -0600 Subject: lguest: update commentry Every so often, after code shuffles, I need to go through and unbitrot the Lguest Journey (see drivers/lguest/README). Since we now use RCU in a simple form in one place I took the opportunity to expand that explanation. Signed-off-by: Rusty Russell Cc: Ingo Molnar Cc: Paul McKenney --- Documentation/lguest/lguest.c | 184 +++++++++++++++++++++++++++++++----------- 1 file changed, 139 insertions(+), 45 deletions(-) (limited to 'Documentation') diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index aa66a52b73e..45163651b51 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -49,7 +49,7 @@ #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 + * 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 @@ -305,6 +305,11 @@ static void *map_zeroed_pages(unsigned int 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; @@ -557,7 +562,7 @@ 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. @@ -608,7 +613,10 @@ 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 }; @@ -629,12 +637,12 @@ static void trigger_irq(struct virtqueue *vq) } /* - * 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[], @@ -644,10 +652,14 @@ 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. */ @@ -734,8 +746,9 @@ static unsigned wait_for_vq_desc(struct virtqueue *vq, } /* - * 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) { @@ -782,12 +795,12 @@ 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? */ @@ -800,6 +813,7 @@ static void console_input(struct virtqueue *vq) pause(); } + /* Tell the Guest we used a buffer. */ add_used_and_trigger(vq, head, len); /* @@ -834,15 +848,23 @@ 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); } @@ -862,15 +884,30 @@ 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; @@ -880,7 +917,11 @@ static bool will_block(int fd) return select(fd+1, &fdset, NULL, NULL, &zero) != 1; } -/* This handles 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; @@ -888,21 +929,38 @@ 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; @@ -950,11 +1008,14 @@ 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 the 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, @@ -966,17 +1027,22 @@ 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); } @@ -1028,7 +1094,10 @@ 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; @@ -1037,18 +1106,32 @@ 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; } @@ -1132,6 +1215,11 @@ 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; @@ -1202,7 +1290,8 @@ static void set_config(struct device *dev, unsigned len, const void *conf) /* * This routine does all the creation and setup of a new device, including - * calling new_dev_desc() to allocate the descriptor and device memory. + * calling new_dev_desc() to allocate the descriptor and device memory. We + * don't actually start the service threads until later. * * See what I mean about userspace being boring? */ @@ -1478,19 +1567,7 @@ 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 this was one reason why lguest now does all virtqueue servicing in - * separate threads: it's more efficient and more like a real device. - */ +/*:*/ /* This hangs off device->priv. */ struct vblk_info @@ -1512,8 +1589,16 @@ struct vblk_info /*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) { @@ -1525,7 +1610,10 @@ 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); /* @@ -1539,6 +1627,10 @@ static void blk_request(struct virtqueue *vq) 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; /* @@ -1614,6 +1706,7 @@ static void blk_request(struct virtqueue *vq) if (out->type & VIRTIO_BLK_T_BARRIER) fdatasync(vblk->fd); + /* Finished that request. */ add_used(vq, head, wlen); } @@ -1682,9 +1775,8 @@ static void rng_input(struct virtqueue *vq) 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); @@ -1818,7 +1910,9 @@ int main(int argc, char *argv[]) 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 * descriptor and memory pages for the devices as we parse the command @@ -1926,7 +2020,7 @@ int main(int argc, char *argv[]) */ 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. */ -- cgit v1.2.3 From 1842f23c05b6a866be831aa60bc8a8731c58ddd0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 30 Jul 2009 16:03:46 -0600 Subject: lguest and virtio: cleanup struct definitions to Linux style. I've been doing this for years, and akpm picked me up on it about 12 months ago. lguest partly serves as example code, so let's do it Right. Also, remove two unused fields in struct vblk_info in the example launcher. Signed-off-by: Rusty Russell Cc: Ingo Molnar --- Documentation/lguest/lguest.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'Documentation') diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 45163651b51..950cde6d6e5 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -93,8 +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; @@ -114,8 +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; @@ -140,8 +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. */ @@ -779,8 +776,7 @@ static void add_used_and_trigger(struct virtqueue *vq, unsigned head, int len) * * We associate some data with the console for our exit hack. */ -struct console_abort -{ +struct console_abort { /* How many times have they hit ^C? */ int count; /* When did they start? */ @@ -1570,20 +1566,13 @@ static void setup_tun_net(char *arg) /*:*/ /* 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 -- cgit v1.2.3 From e624859e7eb6ae2930df3923af73406dc6ccdad8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 27 Jul 2009 22:11:59 +0100 Subject: ARM: 5624/1: Document cache aliasing region Augment the memory.txt file for ARM to list the cache aliasing region ffff4000-fffffff. Signed-off-by: Linus Walleij Signed-off-by: Russell King --- Documentation/arm/memory.txt | 2 ++ 1 file changed, 2 insertions(+) (limited to 'Documentation') diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt index 43cb1004d35..9d58c7c5edd 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. -- cgit v1.2.3 From 2a8aaacda5097fa92a39948da1b4c6614b6e150e Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Thu, 30 Jul 2009 13:10:50 -0700 Subject: docbook: fix printk of ip address Use the %pI4 format string instead of %d.%d.%d.%d and NIPQUAD. Signed-off-by: Tobias Klauser Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- Documentation/DocBook/kernel-hacking.tmpl | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index a50d6cd5857..992e67e6be7 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -449,8 +449,8 @@ printk(KERN_INFO "i = %u\n", i); -__u32 ipaddress; -printk(KERN_INFO "my ip: %d.%d.%d.%d\n", NIPQUAD(ipaddress)); +__be32 ipaddress; +printk(KERN_INFO "my ip: %pI4\n", &ipaddress); -- cgit v1.2.3 From 7e5f5fb09e6fc657f21816b5a18ba645a913368e Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Fri, 31 Jul 2009 11:49:13 -0400 Subject: block: Update topology documentation Update topology comments and sysfs documentation based upon discussions with Neil Brown. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block | 37 ++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 14 deletions(-) (limited to 'Documentation') diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index cbbd3e06994..5f3bedaf8e3 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -94,28 +94,37 @@ What: /sys/block//queue/physical_block_size Date: May 2009 Contact: Martin K. Petersen 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//queue/minimum_io_size Date: April 2009 Contact: Martin K. Petersen 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//queue/optimal_io_size Date: April 2009 Contact: Martin K. Petersen 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. -- cgit v1.2.3 From 1f6fc2de9525e34ee93bd392fa046369a8cfbf1e Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Sat, 1 Aug 2009 12:04:18 -0300 Subject: thinkpad-acpi: remove dock and bay subdrivers The standard ACPI dock driver can handle the hotplug bays and docks of the ThinkPads just fine (including batteries) as of 2.6.27, and the code in thinkpad-acpi for the dock and bay subdrivers is currently broken anyway... Userspace needs some love to support the two-stage ejection nicely, but it is simple enough to do through udev rules (you don't even need HAL) so this wouldn't justify fixing the dock and bay subdrivers, either. That leaves warm-swap bays (_EJ3) support for thinkpad-acpi, as well as support for the weird dock of the model 570, but since such support has never left the "experimental" stage, it is also not a strong enough reason to find a way to fix this code. Users of ThinkPads with warm-swap bays are urged to request that _EJ3 support be added to the regular ACPI dock driver, if such feature is indeed useful for them. Signed-off-by: Henrique de Moraes Holschuh Signed-off-by: Len Brown --- Documentation/laptops/thinkpad-acpi.txt | 127 -------------------------------- 1 file changed, 127 deletions(-) (limited to 'Documentation') diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index f2296ecedb8..e2ddcdeb61b 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 ----------------- -- cgit v1.2.3 From 0e692a94e378628b7d527260ad939894454bcca8 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 7 Aug 2009 15:10:54 +0800 Subject: lockdep: Fix typos in documentation s/head/held Signed-off-by: Li Zefan Cc: Peter Zijlstra LKML-Reference: <4A7BD37E.9060806@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- Documentation/lockdep-design.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index e20d913d591..abf768c681e 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -30,9 +30,9 @@ State The validator tracks lock-class usage history into 4n + 1 separate state bits: - 'ever held in STATE context' -- 'ever head as readlock in STATE context' -- 'ever head with STATE enabled' -- 'ever head as readlock with STATE enabled' +- 'ever held as readlock in STATE context' +- 'ever held with STATE enabled' +- 'ever held as readlock with STATE enabled' Where STATE can be either one of (kernel/lockdep_states.h) - hardirq -- cgit v1.2.3 From 1392e3b33319fd1a2527bebfc56631c2f2d3c7c5 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 8 Aug 2009 17:52:50 +0900 Subject: documentation: register ioctl entry of nilfs2 This will register the ioctl range used by nilfs2 file system to the table listed in Documentation/ioctl/ioctl-number.txt. Signed-off-by: Ryusuke Konishi Signed-off-by: Linus Torvalds --- Documentation/ioctl/ioctl-number.txt | 1 + 1 file changed, 1 insertion(+) (limited to 'Documentation') diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 7bb0d934b6d..dbea4f95fc8 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -139,6 +139,7 @@ Code Seq# Include File Comments 'm' all linux/synclink.h conflict! 'm' 00-1F net/irda/irmod.h conflict! 'n' 00-7F linux/ncp_fs.h +'n' 80-8F linux/nilfs2_fs.h NILFS2 'n' E0-FF video/matrox.h matroxfb 'o' 00-1F fs/ocfs2/ocfs2_fs.h OCFS2 'o' 00-03 include/mtd/ubi-user.h conflict! (OCFS2 and UBI overlaps) -- cgit v1.2.3