diff options
Diffstat (limited to 'Documentation')
-rw-r--r-- | Documentation/DocBook/mac80211.tmpl | 2 | ||||
-rw-r--r-- | Documentation/RCU/rculist_nulls.txt | 7 | ||||
-rw-r--r-- | Documentation/block/data-integrity.txt | 4 | ||||
-rw-r--r-- | Documentation/connector/cn_test.c | 4 | ||||
-rw-r--r-- | Documentation/connector/ucon.c | 2 | ||||
-rw-r--r-- | Documentation/driver-model/driver.txt | 4 | ||||
-rw-r--r-- | Documentation/dvb/get_dvb_firmware | 53 | ||||
-rw-r--r-- | Documentation/feature-removal-schedule.txt | 10 | ||||
-rw-r--r-- | Documentation/kernel-parameters.txt | 4 | ||||
-rw-r--r-- | Documentation/networking/6pack.txt | 2 | ||||
-rw-r--r-- | Documentation/scheduler/sched-rt-group.txt | 13 | ||||
-rw-r--r-- | Documentation/video4linux/CARDLIST.em28xx | 1 | ||||
-rw-r--r-- | Documentation/x86/00-INDEX | 2 | ||||
-rw-r--r-- | Documentation/x86/exception-tables.txt (renamed from Documentation/exception.txt) | 202 |
14 files changed, 189 insertions, 121 deletions
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl index e3698666357..f3f37f141db 100644 --- a/Documentation/DocBook/mac80211.tmpl +++ b/Documentation/DocBook/mac80211.tmpl @@ -184,8 +184,6 @@ usage should require reading the full document. !Finclude/net/mac80211.h ieee80211_ctstoself_get !Finclude/net/mac80211.h ieee80211_ctstoself_duration !Finclude/net/mac80211.h ieee80211_generic_frame_duration -!Finclude/net/mac80211.h ieee80211_get_hdrlen_from_skb -!Finclude/net/mac80211.h ieee80211_hdrlen !Finclude/net/mac80211.h ieee80211_wake_queue !Finclude/net/mac80211.h ieee80211_stop_queue !Finclude/net/mac80211.h ieee80211_wake_queues 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) diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt index e8ca040ba2c..2d735b0ae38 100644 --- a/Documentation/block/data-integrity.txt +++ b/Documentation/block/data-integrity.txt @@ -50,7 +50,7 @@ encouraged them to allow separation of the data and integrity metadata scatter-gather lists. The controller will interleave the buffers on write and split them on -read. This means that the Linux can DMA the data buffers to and from +read. This means that Linux can DMA the data buffers to and from host memory without changes to the page cache. Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs @@ -66,7 +66,7 @@ software RAID5). The IP checksum is weaker than the CRC in terms of detecting bit errors. However, the strength is really in the separation of the data -buffers and the integrity metadata. These two distinct buffers much +buffers and the integrity metadata. These two distinct buffers must match up for an I/O to complete. The separation of the data and integrity metadata buffers as well as 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 <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 @@ -194,5 +194,5 @@ 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/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 <johnpol@2ka.mipt.ru> + * Copyright (c) 2004+ Evgeniy Polyakov <zbr@ioremap.net> * * * This program is free software; you can redistribute it and/or modify diff --git a/Documentation/driver-model/driver.txt b/Documentation/driver-model/driver.txt index 82132169d47..60120fb3b96 100644 --- a/Documentation/driver-model/driver.txt +++ b/Documentation/driver-model/driver.txt @@ -207,8 +207,8 @@ Attributes ~~~~~~~~~~ struct driver_attribute { struct attribute attr; - ssize_t (*show)(struct device_driver *, char * buf, size_t count, loff_t off); - ssize_t (*store)(struct device_driver *, const char * buf, size_t count, loff_t off); + ssize_t (*show)(struct device_driver *driver, char *buf); + ssize_t (*store)(struct device_driver *, const char * buf, size_t count); }; Device drivers can export attributes via their sysfs directories. diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware index a52adfc9a57..3d1b0ab70c8 100644 --- a/Documentation/dvb/get_dvb_firmware +++ b/Documentation/dvb/get_dvb_firmware @@ -25,7 +25,7 @@ use IO::Handle; "tda10046lifeview", "av7110", "dec2000t", "dec2540t", "dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004", "or51211", "or51132_qam", "or51132_vsb", "bluebird", - "opera1", "cx231xx", "cx18", "cx23885", "pvrusb2" ); + "opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718" ); # Check args syntax() if (scalar(@ARGV) != 1); @@ -381,6 +381,57 @@ sub cx18 { $allfiles; } +sub mpc718 { + my $archive = 'Yuan MPC718 TV Tuner Card 2.13.10.1016.zip'; + my $url = "ftp://ftp.work.acer-euro.com/desktop/aspire_idea510/vista/Drivers/$archive"; + my $fwfile = "dvb-cx18-mpc718-mt352.fw"; + my $tmpdir = tempdir(DIR => "/tmp", CLEANUP => 1); + + checkstandard(); + wgetfile($archive, $url); + unzip($archive, $tmpdir); + + my $sourcefile = "$tmpdir/Yuan MPC718 TV Tuner Card 2.13.10.1016/mpc718_32bit/yuanrap.sys"; + my $found = 0; + + open IN, '<', $sourcefile or die "Couldn't open $sourcefile to extract $fwfile data\n"; + binmode IN; + open OUT, '>', $fwfile; + binmode OUT; + { + # Block scope because we change the line terminator variable $/ + my $prevlen = 0; + my $currlen; + + # Buried in the data segment are 3 runs of almost identical + # register-value pairs that end in 0x5d 0x01 which is a "TUNER GO" + # command for the MT352. + # Pull out the middle run (because it's easy) of register-value + # pairs to make the "firmware" file. + + local $/ = "\x5d\x01"; # MT352 "TUNER GO" + + while (<IN>) { + $currlen = length($_); + if ($prevlen == $currlen && $currlen <= 64) { + chop; chop; # Get rid of "TUNER GO" + s/^\0\0//; # get rid of leading 00 00 if it's there + printf OUT "$_"; + $found = 1; + last; + } + $prevlen = $currlen; + } + } + close OUT; + close IN; + if (!$found) { + unlink $fwfile; + die "Couldn't find valid register-value sequence in $sourcefile for $fwfile\n"; + } + $fwfile; +} + sub cx23885 { my $url = "http://linuxtv.org/downloads/firmware/"; diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index f8cd450be9a..09e031c5588 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -458,3 +458,13 @@ Why: Remove the old legacy 32bit machine check code. This has been but the old version has been kept around for easier testing. Note this doesn't impact the old P5 and WinChip machine check handlers. Who: Andi Kleen <andi@firstfloor.org> + +---------------------------- + +What: lock_policy_rwsem_* and unlock_policy_rwsem_* will not be + exported interface anymore. +When: 2.6.33 +Why: cpu_policy_rwsem has a new cleaner definition making it local to + cpufreq core and contained inside cpufreq.c. Other dependent + drivers should not use it in order to safely avoid lockdep issues. +Who: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index d77fbd8b79a..dd1a6d4bb74 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1720,8 +1720,8 @@ and is between 256 and 4096 characters. It is defined in the file oprofile.cpu_type= Force an oprofile cpu type This might be useful if you have an older oprofile userland or if you want common events. - Format: { archperfmon } - archperfmon: [X86] Force use of architectural + Format: { arch_perfmon } + arch_perfmon: [X86] Force use of architectural perfmon on Intel CPUs instead of the CPU specific event set. 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 diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt index 1df7f9cdab0..86eabe6c341 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/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx index 873630e7e53..014d255231f 100644 --- a/Documentation/video4linux/CARDLIST.em28xx +++ b/Documentation/video4linux/CARDLIST.em28xx @@ -66,3 +66,4 @@ 68 -> Terratec AV350 (em2860) [0ccd:0084] 69 -> KWorld ATSC 315U HDTV TV Box (em2882) [eb1a:a313] 70 -> Evga inDtube (em2882) + 71 -> Silvercrest Webcam 1.3mpix (em2820/em2840) diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX index dbe3377754a..f37b46d3486 100644 --- a/Documentation/x86/00-INDEX +++ b/Documentation/x86/00-INDEX @@ -2,3 +2,5 @@ - this file mtrr.txt - how to use x86 Memory Type Range Registers to increase performance +exception-tables.txt + - why and how Linux kernel uses exception tables on x86 diff --git a/Documentation/exception.txt b/Documentation/x86/exception-tables.txt index 2d5aded6424..32901aa36f0 100644 --- a/Documentation/exception.txt +++ b/Documentation/x86/exception-tables.txt @@ -1,123 +1,123 @@ - Kernel level exception handling in Linux 2.1.8 + Kernel level exception handling in Linux Commentary by Joerg Pommnitz <joerg@raleigh.ibm.com> -When a process runs in kernel mode, it often has to access user -mode memory whose address has been passed by an untrusted program. +When a process runs in kernel mode, it often has to access user +mode memory whose address has been passed by an untrusted program. To protect itself the kernel has to verify this address. -In older versions of Linux this was done with the -int verify_area(int type, const void * addr, unsigned long size) +In older versions of Linux this was done with the +int verify_area(int type, const void * addr, unsigned long size) function (which has since been replaced by access_ok()). -This function verified that the memory area starting at address +This function verified that the memory area starting at address 'addr' and of size 'size' was accessible for the operation specified -in type (read or write). To do this, verify_read had to look up the -virtual memory area (vma) that contained the address addr. In the -normal case (correctly working program), this test was successful. +in type (read or write). To do this, verify_read had to look up the +virtual memory area (vma) that contained the address addr. In the +normal case (correctly working program), this test was successful. It only failed for a few buggy programs. In some kernel profiling tests, this normally unneeded verification used up a considerable amount of time. -To overcome this situation, Linus decided to let the virtual memory +To overcome this situation, Linus decided to let the virtual memory hardware present in every Linux-capable CPU handle this test. How does this work? -Whenever the kernel tries to access an address that is currently not -accessible, the CPU generates a page fault exception and calls the -page fault handler +Whenever the kernel tries to access an address that is currently not +accessible, the CPU generates a page fault exception and calls the +page fault handler void do_page_fault(struct pt_regs *regs, unsigned long error_code) -in arch/i386/mm/fault.c. The parameters on the stack are set up by -the low level assembly glue in arch/i386/kernel/entry.S. The parameter -regs is a pointer to the saved registers on the stack, error_code +in arch/x86/mm/fault.c. The parameters on the stack are set up by +the low level assembly glue in arch/x86/kernel/entry_32.S. The parameter +regs is a pointer to the saved registers on the stack, error_code contains a reason code for the exception. -do_page_fault first obtains the unaccessible address from the CPU -control register CR2. If the address is within the virtual address -space of the process, the fault probably occurred, because the page -was not swapped in, write protected or something similar. However, -we are interested in the other case: the address is not valid, there -is no vma that contains this address. In this case, the kernel jumps -to the bad_area label. - -There it uses the address of the instruction that caused the exception -(i.e. regs->eip) to find an address where the execution can continue -(fixup). If this search is successful, the fault handler modifies the -return address (again regs->eip) and returns. The execution will +do_page_fault first obtains the unaccessible address from the CPU +control register CR2. If the address is within the virtual address +space of the process, the fault probably occurred, because the page +was not swapped in, write protected or something similar. However, +we are interested in the other case: the address is not valid, there +is no vma that contains this address. In this case, the kernel jumps +to the bad_area label. + +There it uses the address of the instruction that caused the exception +(i.e. regs->eip) to find an address where the execution can continue +(fixup). If this search is successful, the fault handler modifies the +return address (again regs->eip) and returns. The execution will continue at the address in fixup. Where does fixup point to? -Since we jump to the contents of fixup, fixup obviously points -to executable code. This code is hidden inside the user access macros. -I have picked the get_user macro defined in include/asm/uaccess.h as an -example. The definition is somewhat hard to follow, so let's peek at +Since we jump to the contents of fixup, fixup obviously points +to executable code. This code is hidden inside the user access macros. +I have picked the get_user macro defined in arch/x86/include/asm/uaccess.h +as an example. The definition is somewhat hard to follow, so let's peek at the code generated by the preprocessor and the compiler. I selected -the get_user call in drivers/char/console.c for a detailed examination. +the get_user call in drivers/char/sysrq.c for a detailed examination. -The original code in console.c line 1405: +The original code in sysrq.c line 587: get_user(c, buf); The preprocessor output (edited to become somewhat readable): ( - { - long __gu_err = - 14 , __gu_val = 0; - const __typeof__(*( ( buf ) )) *__gu_addr = ((buf)); - if (((((0 + current_set[0])->tss.segment) == 0x18 ) || - (((sizeof(*(buf))) <= 0xC0000000UL) && - ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf))))))) + { + long __gu_err = - 14 , __gu_val = 0; + const __typeof__(*( ( buf ) )) *__gu_addr = ((buf)); + if (((((0 + current_set[0])->tss.segment) == 0x18 ) || + (((sizeof(*(buf))) <= 0xC0000000UL) && + ((unsigned long)(__gu_addr ) <= 0xC0000000UL - (sizeof(*(buf))))))) do { - __gu_err = 0; - switch ((sizeof(*(buf)))) { - case 1: - __asm__ __volatile__( - "1: mov" "b" " %2,%" "b" "1\n" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl %3,%0\n" - " xor" "b" " %" "b" "1,%" "b" "1\n" - " jmp 2b\n" - ".section __ex_table,\"a\"\n" - " .align 4\n" - " .long 1b,3b\n" + __gu_err = 0; + switch ((sizeof(*(buf)))) { + case 1: + __asm__ __volatile__( + "1: mov" "b" " %2,%" "b" "1\n" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl %3,%0\n" + " xor" "b" " %" "b" "1,%" "b" "1\n" + " jmp 2b\n" + ".section __ex_table,\"a\"\n" + " .align 4\n" + " .long 1b,3b\n" ".text" : "=r"(__gu_err), "=q" (__gu_val): "m"((*(struct __large_struct *) - ( __gu_addr )) ), "i"(- 14 ), "0"( __gu_err )) ; - break; - case 2: + ( __gu_addr )) ), "i"(- 14 ), "0"( __gu_err )) ; + break; + case 2: __asm__ __volatile__( - "1: mov" "w" " %2,%" "w" "1\n" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl %3,%0\n" - " xor" "w" " %" "w" "1,%" "w" "1\n" - " jmp 2b\n" - ".section __ex_table,\"a\"\n" - " .align 4\n" - " .long 1b,3b\n" + "1: mov" "w" " %2,%" "w" "1\n" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl %3,%0\n" + " xor" "w" " %" "w" "1,%" "w" "1\n" + " jmp 2b\n" + ".section __ex_table,\"a\"\n" + " .align 4\n" + " .long 1b,3b\n" ".text" : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *) - ( __gu_addr )) ), "i"(- 14 ), "0"( __gu_err )); - break; - case 4: - __asm__ __volatile__( - "1: mov" "l" " %2,%" "" "1\n" - "2:\n" - ".section .fixup,\"ax\"\n" - "3: movl %3,%0\n" - " xor" "l" " %" "" "1,%" "" "1\n" - " jmp 2b\n" - ".section __ex_table,\"a\"\n" - " .align 4\n" " .long 1b,3b\n" + ( __gu_addr )) ), "i"(- 14 ), "0"( __gu_err )); + break; + case 4: + __asm__ __volatile__( + "1: mov" "l" " %2,%" "" "1\n" + "2:\n" + ".section .fixup,\"ax\"\n" + "3: movl %3,%0\n" + " xor" "l" " %" "" "1,%" "" "1\n" + " jmp 2b\n" + ".section __ex_table,\"a\"\n" + " .align 4\n" " .long 1b,3b\n" ".text" : "=r"(__gu_err), "=r" (__gu_val) : "m"((*(struct __large_struct *) - ( __gu_addr )) ), "i"(- 14 ), "0"(__gu_err)); - break; - default: - (__gu_val) = __get_user_bad(); - } - } while (0) ; - ((c)) = (__typeof__(*((buf))))__gu_val; + ( __gu_addr )) ), "i"(- 14 ), "0"(__gu_err)); + break; + default: + (__gu_val) = __get_user_bad(); + } + } while (0) ; + ((c)) = (__typeof__(*((buf))))__gu_val; __gu_err; } ); @@ -127,12 +127,12 @@ see what code gcc generates: > xorl %edx,%edx > movl current_set,%eax - > cmpl $24,788(%eax) - > je .L1424 + > cmpl $24,788(%eax) + > je .L1424 > cmpl $-1073741825,64(%esp) - > ja .L1423 + > ja .L1423 > .L1424: - > movl %edx,%eax + > movl %edx,%eax > movl 64(%esp),%ebx > #APP > 1: movb (%ebx),%dl /* this is the actual user access */ @@ -149,17 +149,17 @@ see what code gcc generates: > .L1423: > movzbl %dl,%esi -The optimizer does a good job and gives us something we can actually -understand. Can we? The actual user access is quite obvious. Thanks -to the unified address space we can just access the address in user +The optimizer does a good job and gives us something we can actually +understand. Can we? The actual user access is quite obvious. Thanks +to the unified address space we can just access the address in user memory. But what does the .section stuff do????? To understand this we have to look at the final kernel: > objdump --section-headers vmlinux - > + > > vmlinux: file format elf32-i386 - > + > > Sections: > Idx Name Size VMA LMA File off Algn > 0 .text 00098f40 c0100000 c0100000 00001000 2**4 @@ -198,18 +198,18 @@ final kernel executable: The whole user memory access is reduced to 10 x86 machine instructions. The instructions bracketed in the .section directives are no longer -in the normal execution path. They are located in a different section +in the normal execution path. They are located in a different section of the executable file: > objdump --disassemble --section=.fixup vmlinux - > + > > c0199ff5 <.fixup+10b5> movl $0xfffffff2,%eax > c0199ffa <.fixup+10ba> xorb %dl,%dl > c0199ffc <.fixup+10bc> jmp c017e7a7 <do_con_write+e3> And finally: > objdump --full-contents --section=__ex_table vmlinux - > + > > c01aa7c4 93c017c0 e09f19c0 97c017c0 99c017c0 ................ > c01aa7d4 f6c217c0 e99f19c0 a5e717c0 f59f19c0 ................ > c01aa7e4 080a18c0 01a019c0 0a0a18c0 04a019c0 ................ @@ -235,8 +235,8 @@ sections in the ELF object file. So the instructions ended up in the .fixup section of the object file and the addresses .long 1b,3b ended up in the __ex_table section of the object file. 1b and 3b -are local labels. The local label 1b (1b stands for next label 1 -backward) is the address of the instruction that might fault, i.e. +are local labels. The local label 1b (1b stands for next label 1 +backward) is the address of the instruction that might fault, i.e. in our case the address of the label 1 is c017e7a5: the original assembly code: > 1: movb (%ebx),%dl and linked in vmlinux : > c017e7a5 <do_con_write+e1> movb (%ebx),%dl @@ -254,7 +254,7 @@ The assembly code becomes the value pair > c01aa7d4 c017c2f6 c0199fe9 c017e7a5 c0199ff5 ................ ^this is ^this is - 1b 3b + 1b 3b c017e7a5,c0199ff5 in the exception table of the kernel. So, what actually happens if a fault from kernel mode with no suitable @@ -266,9 +266,9 @@ vma occurs? 3.) CPU calls do_page_fault 4.) do page fault calls search_exception_table (regs->eip == c017e7a5); 5.) search_exception_table looks up the address c017e7a5 in the - exception table (i.e. the contents of the ELF section __ex_table) + exception table (i.e. the contents of the ELF section __ex_table) and returns the address of the associated fault handle code c0199ff5. -6.) do_page_fault modifies its own return address to point to the fault +6.) do_page_fault modifies its own return address to point to the fault handle code and returns. 7.) execution continues in the fault handling code. 8.) 8a) EAX becomes -EFAULT (== -14) |