From 4e93cb000786b18ffd9929f33055cad2a7cebbcf Mon Sep 17 00:00:00 2001 From: Michael Gernoth Date: Sun, 22 May 2011 12:38:46 +0200 Subject: [PATCH] add initial kexec sources from kexec-prealpha-r2.tar.gz --- CHANGELOG | 13 + COPYING | 340 ++++++++++ Makefile | 30 + README | 111 ++++ abort-ev7.S | 33 + abort-macro.S | 42 ++ cache-v7.S | 266 ++++++++ copypage-v6.c | 63 ++ core.c | 53 ++ driver_sys.c | 86 +++ entry-common.S | 24 + entry-header.S | 66 ++ kexec.c | 1541 +++++++++++++++++++++++++++++++++++++++++++++ machine_kexec.c | 80 +++ mm.h | 36 ++ mmu.c | 61 ++ proc-macros.S | 243 +++++++ proc-v7.S | 281 +++++++++ relocate_kernel.S | 79 +++ sys.c | 101 +++ tlb-v7.S | 91 +++ 21 files changed, 3640 insertions(+) create mode 100644 CHANGELOG create mode 100644 COPYING create mode 100644 Makefile create mode 100644 README create mode 100644 abort-ev7.S create mode 100644 abort-macro.S create mode 100644 cache-v7.S create mode 100644 copypage-v6.c create mode 100644 core.c create mode 100644 driver_sys.c create mode 100644 entry-common.S create mode 100644 entry-header.S create mode 100644 kexec.c create mode 100644 machine_kexec.c create mode 100644 mm.h create mode 100644 mmu.c create mode 100644 proc-macros.S create mode 100644 proc-v7.S create mode 100644 relocate_kernel.S create mode 100644 sys.c create mode 100644 tlb-v7.S diff --git a/CHANGELOG b/CHANGELOG new file mode 100644 index 0000000..771ed31 --- /dev/null +++ b/CHANGELOG @@ -0,0 +1,13 @@ +Release 1 (Revision 29) [19-01-11] + # First Release for the Droid X + +Release 2 (Revision 30) [14-02-11] + # First Release for the Droid 2 and Nexus S + # Removed Nexus One as a target + # Moved Droid X into alpha + # Added Droid 2 Global as a Future Target + # Generic Code Clean-up + # Commented out device_shutdown() on line 66 of sys,c + # Commented out sysdev_shutdown() on line 67 of sys.c + # Added a cross-compiling how-to in the README as per user demand. + diff --git a/COPYING b/COPYING new file mode 100644 index 0000000..3912109 --- /dev/null +++ b/COPYING @@ -0,0 +1,340 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + , 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..43b5487 --- /dev/null +++ b/Makefile @@ -0,0 +1,30 @@ +# In this string we need to use -D__SOME__ command for define which platform we use +# And C preprocessor use only code for platform, we defined +# For example if we use Texas Instruments OMAP 3430 - we should use +# EXTRA_CFLAGS += -D__PLAT_TI_OMAP3430__ +# Else if we need for Freescale i.MX31 - we should use +# EXTRA_CFLAGS += -D__PLAT_FREESCALE_IMX31__ + +# I don't yet have this fully set up for the droid x yet +# This line seems to work on my X, otherwise use the line +# That's commented out. +EXTRA_CFLAGS += -D__PLAT_TI_OMAP3430__ -Wall -march=arm +# EXTRA_CFLAGS += -mfpu=neon + +# Make this match the optimisation values of the kernel you're +# loading this into. Should work without changes, but it seems to +# crash on the Nexus One and Droid Pro. If you're compiling on an +# Evo 4g, set this value to 1 and change the EXTRA_CFLAGS value to +# something appropriate to your phone +# EXTRA_CFLAGS += -O0 + +obj-m += kexec_load.o +kexec_load-objs := kexec.o machine_kexec.o mmu.o sys.o core.o relocate_kernel.o \ + proc-v7.o tlb-v7.o cache-v7.o abort-ev7.o copypage-v6.o entry-common.o driver_sys.o + +all: + make -C kernel/ M=$(PWD) modules + +clean: + make -C kernel/ M=$(PWD) clean + rm -f *.order diff --git a/README b/README new file mode 100644 index 0000000..4378184 --- /dev/null +++ b/README @@ -0,0 +1,111 @@ +Android kexec port +By Matthew Veety, et al. + +Contents: + Synopsis + Cross-compiling on Gentoo and other Linuxes How-to + Troubleshooting + +================================================================================ + +Synopsis: + +This is the kmod from the project trying to unlock the Milestone. It is still +localized to that phone, but, with modification, I got working on the Droid X +and a few others. Currently, this is a work in progress and is not recommended +for mission critical situations. + +To compile: +Place your kernel sources into kernel/ and build the kernel +in that directory. Then run make (or gmake on freebsd) to build +the kernel module. I highly recommend actually doing the build on +the phone you desire to run the kmod on. I use a gentoo stage3 +chroot environment on my Droid X to do the building. + +Targets: +Droid X + +In-progress Targets: +Droid 2 +Nexus S + +Future Targets: +Droid 2 Global +Droid Bionic + +================================================================================ + +Cross-compiling on Gentoo and other Linuxes How-to: + + To set this up you need a cross-compiler. A cross-compiler allows your to +make binaries for something other than your platform. If you've ever built Android +then you've used one. There are two methods to do this; the first method is using +Android's cross-compiler to build. There are tools to set this up and it seems +to be very easy to use, but I've never got that method to work. The method I use +uses a nice tool that is in portage (I'm a gentoo user) called cross dev. + + ~note from palmercurling~ + To set up a cross-compiler in Debian or a Debian fork (Ubuntu, Mint, others) + follow the steps at http://www.scratchbox.org/ + +Your first step should be setting up a stage3 chroot. The Gentoo handbook outlines +how to do this, and the process is pretty simple. It only needs to be very +minimal and doesn't need X or any other sort of graphical environment. +I install mine to /opt because I have a nice 300 GB hard drive mounted there to +hold all of my Android things. + +So after you're chrooted into your cross environment install crossdev by running: +# emerge -avp crossdev # This is to see dependencies +# emerge -av crossdev # This makes sure you want to go through with it + +After crossdev gets done emerging run: +# emerge --sync +to get the latest version of the portage tree. If rsync is blocked choose the http +method outlined in the Gentoo Handbook. + +crossdev has pretty simple options that can be seen by invoking: +$ crossdev +or +# crossdev + +The option you'll be interested in is --target. This allows your to build the specified +gcc, libc, and binutils. --target takes its option as ARCH-VENDOR-OS-LIBC. For +possible choices invoke: +$ crossdev -t help +$ crossdev --target help +# crossdev -t help +or +# crossdev --target help + +Now because Adnroid is Linux and initx requires glibc your tuple for --target +will look something like ARCH-VENDOR-linux-glibc. Also because Android +kexec only supports ARM right now you're going to want either arm or armeb +for ARCH. That is phone dependent. The Droid X seems to run fine with either, +but the Nexus One really doesn't like using arm without compiling the kernel with +softfloat in the vendor. + +TIPS: This doesn't work on Gentoo/FreeBSD yet. No idea why either. Cross +works fine on normal *BSD though. Crossdev is also crazy useful for +compiling Windows apps. crossdev + wine = windows development bliss. + +================================================================================ + +TROUBLESHOOTING: + +1. I'm getting segmentation faults! + Check your cross setup. The common cause for me is adding in softfloat when I + didn't need it. Don't feel bad, it's a common issue. +2. kexec won't load into the kernel! + The cross setup needs to be the same configuration as the one that compiles your + kernel. Check your CHOST after running make menuconfig in your kernel. +3. I'm getting errors on compile! + Read them and fix them, if it's my fault send me a fix for it. +4. How do I actually use this? + You'll need to write a wrapper to make the system call. I did that so inexperienced + users won't damage their phone. kexec is pretty well documented, and you can look + at the i686 sources for a really well done reference, plus the man pages have it pretty + well documented. +5. This file looks funny in my emacs window! + I know, I didn't format it to 80 cols just to be a dick to you :P. Actually, I use + TextEdit.app (it's a GNUstep app because I'm a GNUstep user) which doesn't easily + understand the concepts of "wrap the damn line at 80." diff --git a/abort-ev7.S b/abort-ev7.S new file mode 100644 index 0000000..2e6dc04 --- /dev/null +++ b/abort-ev7.S @@ -0,0 +1,33 @@ +#include +#include +/* + * Function: v7_early_abort + * + * Params : r2 = address of aborted instruction + * : r3 = saved SPSR + * + * Returns : r0 = address of abort + * : r1 = FSR, bit 11 = write + * : r2-r8 = corrupted + * : r9 = preserved + * : sp = pointer to registers + * + * Purpose : obtain information about current aborted instruction. + */ + .align 5 +ENTRY(v7_early_abort) + /* + * The effect of data aborts on on the exclusive access monitor are + * UNPREDICTABLE. Do a CLREX to clear the state + */ + clrex + + mrc p15, 0, r1, c5, c0, 0 @ get FSR + mrc p15, 0, r0, c6, c0, 0 @ get FAR + + /* + * V6 code adjusts the returned DFSR. + * New designs should not need to patch up faults. + */ + mov pc, lr +ENDPROC(v7_early_abort) diff --git a/abort-macro.S b/abort-macro.S new file mode 100644 index 0000000..d7cb1bf --- /dev/null +++ b/abort-macro.S @@ -0,0 +1,42 @@ +/* + * The ARM LDRD and Thumb LDRSB instructions use bit 20/11 (ARM/Thumb) + * differently than every other instruction, so it is set to 0 (write) + * even though the instructions are read instructions. This means that + * during an abort the instructions will be treated as a write and the + * handler will raise a signal from unwriteable locations if they + * fault. We have to specifically check for these instructions + * from the abort handlers to treat them properly. + * + */ + + .macro do_thumb_abort + tst r3, #PSR_T_BIT + beq not_thumb + ldrh r3, [r2] @ Read aborted Thumb instruction + and r3, r3, # 0xfe00 @ Mask opcode field + cmp r3, # 0x5600 @ Is it ldrsb? + orreq r3, r3, #1 << 11 @ Set L-bit if yes + tst r3, #1 << 11 @ L = 0 -> write + orreq r1, r1, #1 << 11 @ yes. + mov pc, lr +not_thumb: + .endm + +/* + * We check for the following insturction encoding for LDRD. + * + * [27:25] == 0 + * [7:4] == 1101 + * [20] == 0 + */ + .macro do_ldrd_abort + tst r3, #0x0e000000 @ [27:25] == 0 + bne not_ldrd + and r2, r3, #0x000000f0 @ [7:4] == 1101 + cmp r2, #0x000000d0 + bne not_ldrd + tst r3, #1 << 20 @ [20] == 0 + moveq pc, lr +not_ldrd: + .endm + diff --git a/cache-v7.S b/cache-v7.S new file mode 100644 index 0000000..bd38e61 --- /dev/null +++ b/cache-v7.S @@ -0,0 +1,266 @@ +/* + * linux/arch/arm/mm/cache-v7.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2005 ARM Ltd. + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This is the "shell" of the ARMv7 processor support. + */ +#include +#include +#include + +#include "proc-macros.S" + +/* + * v7_flush_dcache_all() + * + * Flush the whole D-cache. + * + * Corrupted registers: r0-r5, r7, r9-r11 + * + * - mm - mm_struct describing address space + */ +ENTRY(v7_flush_dcache_all) + dmb @ ensure ordering with previous memory accesses + mrc p15, 1, r0, c0, c0, 1 @ read clidr + ands r3, r0, #0x7000000 @ extract loc from clidr + mov r3, r3, lsr #23 @ left align loc bit field + beq finished @ if loc is 0, then no need to clean + mov r10, #0 @ start clean at cache level 0 +loop1: + add r2, r10, r10, lsr #1 @ work out 3x current cache level + mov r1, r0, lsr r2 @ extract cache type bits from clidr + and r1, r1, #7 @ mask of the bits for current cache only + cmp r1, #2 @ see what cache we have at this level + blt skip @ skip if no cache, or just i-cache + mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr + isb @ isb to sych the new cssr&csidr + mrc p15, 1, r1, c0, c0, 0 @ read the new csidr + and r2, r1, #7 @ extract the length of the cache lines + add r2, r2, #4 @ add 4 (line length offset) + ldr r4, =0x3ff + ands r4, r4, r1, lsr #3 @ find maximum number on the way size + clz r5, r4 @ find bit position of way size increment + ldr r7, =0x7fff + ands r7, r7, r1, lsr #13 @ extract max number of the index size +loop2: + mov r9, r4 @ create working copy of max way size +loop3: + orr r11, r10, r9, lsl r5 @ factor way and cache number into r11 + orr r11, r11, r7, lsl r2 @ factor index number into r11 + mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way + subs r9, r9, #1 @ decrement the way + bge loop3 + subs r7, r7, #1 @ decrement the index + bge loop2 +skip: + add r10, r10, #2 @ increment cache number + cmp r3, r10 + bgt loop1 +finished: + mov r10, #0 @ swith back to cache level 0 + mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr + dsb + isb + mov pc, lr +ENDPROC(v7_flush_dcache_all) + +/* + * v7_flush_cache_all() + * + * Flush the entire cache system. + * The data cache flush is now achieved using atomic clean / invalidates + * working outwards from L1 cache. This is done using Set/Way based cache + * maintainance instructions. + * The instruction cache can still be invalidated back to the point of + * unification in a single instruction. + * + */ +ENTRY(v7_flush_kern_cache_all) + stmfd sp!, {r4-r5, r7, r9-r11, lr} + bl v7_flush_dcache_all + mov r0, #0 + mcr p15, 0, r0, c7, c5, 0 @ I+BTB cache invalidate + ldmfd sp!, {r4-r5, r7, r9-r11, lr} + mov pc, lr +ENDPROC(v7_flush_kern_cache_all) + +/* + * v7_flush_cache_all() + * + * Flush all TLB entries in a particular address space + * + * - mm - mm_struct describing address space + */ +ENTRY(v7_flush_user_cache_all) + /*FALLTHROUGH*/ + +/* + * v7_flush_cache_range(start, end, flags) + * + * Flush a range of TLB entries in the specified address space. + * + * - start - start address (may not be aligned) + * - end - end address (exclusive, may not be aligned) + * - flags - vm_area_struct flags describing address space + * + * It is assumed that: + * - we have a VIPT cache. + */ +ENTRY(v7_flush_user_cache_range) + mov pc, lr +ENDPROC(v7_flush_user_cache_all) +ENDPROC(v7_flush_user_cache_range) + +/* + * v7_coherent_kern_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7_coherent_kern_range) + /* FALLTHROUGH */ + +/* + * v7_coherent_user_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7_coherent_user_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: mcr p15, 0, r0, c7, c11, 1 @ clean D line to the point of unification + dsb + mcr p15, 0, r0, c7, c5, 1 @ invalidate I line + add r0, r0, r2 + cmp r0, r1 + blo 1b + mov r0, #0 + mcr p15, 0, r0, c7, c5, 6 @ invalidate BTB + dsb + isb + mov pc, lr +ENDPROC(v7_coherent_kern_range) +ENDPROC(v7_coherent_user_range) + +/* + * v7_flush_kern_dcache_page(kaddr) + * + * Ensure that the data held in the page kaddr is written back + * to the page in question. + * + * - kaddr - kernel address (guaranteed to be page aligned) + */ +ENTRY(v7_flush_kern_dcache_page) + dcache_line_size r2, r3 + add r1, r0, #PAGE_SZ +1: + mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D line / unified line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb + mov pc, lr +ENDPROC(v7_flush_kern_dcache_page) + +/* + * v7_dma_inv_range(start,end) + * + * Invalidate the data cache within the specified region; we will + * be performing a DMA operation in this region and we want to + * purge old data in the cache. + * + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(v7_dma_inv_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + tst r0, r3 + bic r0, r0, r3 + mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line + + tst r1, r3 + bic r1, r1, r3 + mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D / U line +1: + mcr p15, 0, r0, c7, c6, 1 @ invalidate D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb + mov pc, lr +ENDPROC(v7_dma_inv_range) + +/* + * v7_dma_clean_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(v7_dma_clean_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + mcr p15, 0, r0, c7, c10, 1 @ clean D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb + mov pc, lr +ENDPROC(v7_dma_clean_range) + +/* + * v7_dma_flush_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(v7_dma_flush_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + mcr p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb + mov pc, lr +ENDPROC(v7_dma_flush_range) + + __INITDATA + + .type v7_cache_fns, #object +ENTRY(v7_cache_fns) + .long v7_flush_kern_cache_all + .long v7_flush_user_cache_all + .long v7_flush_user_cache_range + .long v7_coherent_kern_range + .long v7_coherent_user_range + .long v7_flush_kern_dcache_page + .long v7_dma_inv_range + .long v7_dma_clean_range + .long v7_dma_flush_range + .size v7_cache_fns, . - v7_cache_fns diff --git a/copypage-v6.c b/copypage-v6.c new file mode 100644 index 0000000..9cc8485 --- /dev/null +++ b/copypage-v6.c @@ -0,0 +1,63 @@ +/* + * linux/arch/arm/mm/copypage-v6.c + * + * Copyright (C) 2002 Deep Blue Solutions Ltd, All Rights Reserved. + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "mm.h" + +#if SHMLBA > 16384 +#error FIX ME +#endif + +#define from_address (0xffff8000) +#define to_address (0xffffc000) + +/* + * Copy the user page. No aliasing to deal with so we can just + * attack the kernel's existing mapping of these pages. + */ + +static void v6_copy_user_highpage_nonaliasing(struct page *to, + struct page *from, unsigned long vaddr) +{ + void *kto, *kfrom; + + kfrom = kmap_atomic(from, KM_USER0); + kto = kmap_atomic(to, KM_USER1); + copy_page(kto, kfrom); + kunmap_atomic(kto, KM_USER1); + kunmap_atomic(kfrom, KM_USER0); +} + +/* + * Clear the user page. No aliasing to deal with so we can just + * attack the kernel's existing mapping of this page. + */ +static void v6_clear_user_highpage_nonaliasing(struct page *page, unsigned long vaddr) +{ + void *kaddr = kmap_atomic(page, KM_USER0); + clear_page(kaddr); + kunmap_atomic(kaddr, KM_USER0); +} + + +struct cpu_user_fns v6_user_fns __initdata = { + .cpu_clear_user_highpage = v6_clear_user_highpage_nonaliasing, + .cpu_copy_user_highpage = v6_copy_user_highpage_nonaliasing, +}; diff --git a/core.c b/core.c new file mode 100644 index 0000000..b3a827b --- /dev/null +++ b/core.c @@ -0,0 +1,53 @@ +/* + * drivers/base/core.c - core driver model code (device registration, etc) + * + * Copyright (c) 2002-3 Patrick Mochel + * Copyright (c) 2002-3 Open Source Development Labs + * Copyright (c) 2006 Greg Kroah-Hartman + * Copyright (c) 2006 Novell, Inc. + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This file is released under the GPLv2 + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * device_shutdown - call ->shutdown() on each device to shutdown. + */ +void device_shutdown(void) +{ + struct device *dev, *devn, *dummy_device; + struct kset *devices_kset; + + dummy_device = kzalloc(sizeof(*dummy_device), GFP_KERNEL); + + /* init a dummy device to get to the devices kset */ + device_initialize(dummy_device); + devices_kset=dummy_device->kobj.kset; + put_device(dummy_device); + + list_for_each_entry_safe_reverse(dev, devn, &devices_kset->list, + kobj.entry) { + if (dev->bus && dev->bus->shutdown) { + dev_dbg(dev, "shutdown\n"); + dev->bus->shutdown(dev); + } else if (dev->driver && dev->driver->shutdown) { + dev_dbg(dev, "shutdown\n"); + dev->driver->shutdown(dev); + } + } +} diff --git a/driver_sys.c b/driver_sys.c new file mode 100644 index 0000000..41f9638 --- /dev/null +++ b/driver_sys.c @@ -0,0 +1,86 @@ +/* + * sys.c - pseudo-bus for system 'devices' (cpus, PICs, timers, etc) + * + * Copyright (c) 2002-3 Patrick Mochel + * 2002-3 Open Source Development Lab + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This file is released under the GPLv2 + * + * This exports a 'system' bus type. + * By default, a 'sys' bus gets added to the root of the system. There will + * always be core system devices. Devices can use sysdev_register() to + * add themselves as children of the system bus. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#define to_sysdev(k) container_of(k, struct sys_device, kobj) +#define to_sysdev_attr(a) container_of(a, struct sysdev_attribute, attr) + +static struct sysdev_class dummy_sysclass = { + .name="dummy", +}; + + +/** + * sysdev_shutdown - Shut down all system devices. + * + * Loop over each class of system devices, and the devices in each + * of those classes. For each device, we call the shutdown method for + * each driver registered for the device - the auxillaries, + * and the class driver. + * + * Note: The list is iterated in reverse order, so that we shut down + * child devices before we shut down thier parents. The list ordering + * is guaranteed by virtue of the fact that child devices are registered + * after their parents. + */ +void sysdev_shutdown(void) +{ + struct sysdev_class * cls; + struct kset *system_kset; + + pr_debug("Shutting Down System Devices\n"); + + lock_kernel(); + + sysdev_class_register(&dummy_sysclass); + cls=&dummy_sysclass; + system_kset=cls->kset.kobj.kset; + sysdev_class_unregister(&dummy_sysclass); + + list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) { + struct sys_device * sysdev; + + pr_debug("Shutting down type '%s':\n", + kobject_name(&cls->kset.kobj)); + + list_for_each_entry(sysdev, &cls->kset.list, kobj.entry) { + struct sysdev_driver * drv; + pr_debug(" %s\n", kobject_name(&sysdev->kobj)); + + /* Call auxillary drivers first */ + list_for_each_entry(drv, &cls->drivers, entry) { + if (drv->shutdown) + drv->shutdown(sysdev); + } + + /* Now call the generic one */ + if (cls->shutdown) + cls->shutdown(sysdev); + } + } + unlock_kernel(); +} diff --git a/entry-common.S b/entry-common.S new file mode 100644 index 0000000..6c9c47c --- /dev/null +++ b/entry-common.S @@ -0,0 +1,24 @@ +/* + * linux/arch/arm/kernel/entry-common.S + * + * Copyright (C) 2000 Russell King + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include + +#include "entry-header.S" + +ENTRY(pabort_ifar) + mrc p15, 0, r0, cr6, cr0, 2 +ENTRY(pabort_noifar) + mov pc, lr +ENDPROC(pabort_ifar) +ENDPROC(pabort_noifar) + diff --git a/entry-header.S b/entry-header.S new file mode 100644 index 0000000..87ab4e1 --- /dev/null +++ b/entry-header.S @@ -0,0 +1,66 @@ +#include +#include + +#include +#include +#include +#include + +@ Bad Abort numbers +@ ----------------- +@ +#define BAD_PREFETCH 0 +#define BAD_DATA 1 +#define BAD_ADDREXCPTN 2 +#define BAD_IRQ 3 +#define BAD_UNDEFINSTR 4 + +@ +@ Most of the stack format comes from struct pt_regs, but with +@ the addition of 8 bytes for storing syscall args 5 and 6. +@ This _must_ remain a multiple of 8 for EABI. +@ +#define S_OFF 8 + +/* + * The SWI code relies on the fact that R0 is at the bottom of the stack + * (due to slow/fast restore user regs). + */ +#if S_R0 != 0 +#error "Please fix" +#endif + + .macro zero_fp +#ifdef CONFIG_FRAME_POINTER + mov fp, #0 +#endif + .endm + + .macro get_thread_info, rd + mov \rd, sp, lsr #13 + mov \rd, \rd, lsl #13 + .endm + + .macro alignment_trap, rtemp +#ifdef CONFIG_ALIGNMENT_TRAP + ldr \rtemp, .LCcralign + ldr \rtemp, [\rtemp] + mcr p15, 0, \rtemp, c1, c0 +#endif + .endm + + +/* + * These are the registers used in the syscall handler, and allow us to + * have in theory up to 7 arguments to a function - r0 to r6. + * + * r7 is reserved for the system call number for thumb mode. + * + * Note that tbl == why is intentional. + * + * We must set at least "tsk" and "why" when calling ret_with_reschedule. + */ +scno .req r7 @ syscall number +tbl .req r8 @ syscall table pointer +why .req r8 @ Linux syscall (!= 0) +tsk .req r9 @ current thread_info diff --git a/kexec.c b/kexec.c new file mode 100644 index 0000000..8a437da --- /dev/null +++ b/kexec.c @@ -0,0 +1,1541 @@ +/* + * kexec.c - kexec system call + * Copyright (C) 2002-2004 Eric Biederman + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); + +/* Syscall table */ +void **sys_call_table; + +/* original and new reboot syscall */ +asmlinkage long (*original_reboot)(int magic1, int magic2, unsigned int cmd, void __user *arg); +extern asmlinkage long reboot(int magic1, int magic2, unsigned int cmd, void __user *arg); + +/* Per cpu memory for storing cpu states in case of system crash. */ +note_buf_t* crash_notes; + +/* vmcoreinfo stuff */ +unsigned char vmcoreinfo_data[VMCOREINFO_BYTES]; +u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; +size_t vmcoreinfo_size; +size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data); + +/* Location of the reserved area for the crash kernel */ +struct resource crashk_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +int kexec_should_crash(struct task_struct *p) +{ + if (in_interrupt() || !p->pid || is_global_init(p)) + return 1; + return 0; +} + +/* + * When kexec transitions to the new kernel there is a one-to-one + * mapping between physical and virtual addresses. On processors + * where you can disable the MMU this is trivial, and easy. For + * others it is still a simple predictable page table to setup. + * + * In that environment kexec copies the new kernel to its final + * resting place. This means I can only support memory whose + * physical address can fit in an unsigned long. In particular + * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled. + * If the assembly stub has more restrictive requirements + * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be + * defined more restrictively in . + * + * The code for the transition from the current kernel to the + * the new kernel is placed in the control_code_buffer, whose size + * is given by KEXEC_CONTROL_PAGE_SIZE. In the best case only a single + * page of memory is necessary, but some architectures require more. + * Because this memory must be identity mapped in the transition from + * virtual to physical addresses it must live in the range + * 0 - TASK_SIZE, as only the user space mappings are arbitrarily + * modifiable. + * + * The assembly stub in the control code buffer is passed a linked list + * of descriptor pages detailing the source pages of the new kernel, + * and the destination addresses of those source pages. As this data + * structure is not used in the context of the current OS, it must + * be self-contained. + * + * The code has been made to work with highmem pages and will use a + * destination page in its final resting place (if it happens + * to allocate it). The end product of this is that most of the + * physical address space, and most of RAM can be used. + * + * Future directions include: + * - allocating a page table with the control code buffer identity + * mapped, to simplify machine_kexec and make kexec_on_panic more + * reliable. + */ + +/* + * KIMAGE_NO_DEST is an impossible destination address..., for + * allocating pages whose destination address we do not care about. + */ +#define KIMAGE_NO_DEST (-1UL) + +static int kimage_is_destination_range(struct kimage *image, + unsigned long start, unsigned long end); +static struct page *kimage_alloc_page(struct kimage *image, + gfp_t gfp_mask, + unsigned long dest); + +static int do_kimage_alloc(struct kimage **rimage, unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments) +{ + size_t segment_bytes; + struct kimage *image; + unsigned long i; + int result; + + /* Allocate a controlling structure */ + result = -ENOMEM; + image = kzalloc(sizeof(*image), GFP_KERNEL); + if (!image) + goto out; + + image->head = 0; + image->entry = &image->head; + image->last_entry = &image->head; + image->control_page = ~0; /* By default this does not apply */ + image->start = entry; + image->type = KEXEC_TYPE_DEFAULT; + + /* Initialize the list of control pages */ + INIT_LIST_HEAD(&image->control_pages); + + /* Initialize the list of destination pages */ + INIT_LIST_HEAD(&image->dest_pages); + + /* Initialize the list of unuseable pages */ + INIT_LIST_HEAD(&image->unuseable_pages); + + /* Read in the segments */ + image->nr_segments = nr_segments; + segment_bytes = nr_segments * sizeof(*segments); + result = copy_from_user(image->segment, segments, segment_bytes); + if (result) + goto out; + + /* + * Verify we have good destination addresses. The caller is + * responsible for making certain we don't attempt to load + * the new image into invalid or reserved areas of RAM. This + * just verifies it is an address we can use. + * + * Since the kernel does everything in page size chunks ensure + * the destination addreses are page aligned. Too many + * special cases crop of when we don't do this. The most + * insidious is getting overlapping destination addresses + * simply because addresses are changed to page size + * granularity. + */ + result = -EADDRNOTAVAIL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK)) + goto out; + if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT) + goto out; + } + + /* Verify our destination addresses do not overlap. + * If we alloed overlapping destination addresses + * through very weird things can happen with no + * easy explanation as one segment stops on another. + */ + result = -EINVAL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + unsigned long j; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + for (j = 0; j < i; j++) { + unsigned long pstart, pend; + pstart = image->segment[j].mem; + pend = pstart + image->segment[j].memsz; + /* Do the segments overlap ? */ + if ((mend > pstart) && (mstart < pend)) + goto out; + } + } + + /* Ensure our buffer sizes are strictly less than + * our memory sizes. This should always be the case, + * and it is easier to check up front than to be surprised + * later on. + */ + result = -EINVAL; + for (i = 0; i < nr_segments; i++) { + if (image->segment[i].bufsz > image->segment[i].memsz) + goto out; + } + + result = 0; +out: + if (result == 0) + *rimage = image; + else + kfree(image); + + return result; + +} + +static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments) +{ + int result; + struct kimage *image; + + /* Allocate and initialize a controlling structure */ + image = NULL; + result = do_kimage_alloc(&image, entry, nr_segments, segments); + if (result) + goto out; + + *rimage = image; + + /* + * Find a location for the control code buffer, and add it + * the vector of segments so that it's pages will also be + * counted as destination pages. + */ + result = -ENOMEM; + image->control_code_page = kimage_alloc_control_pages(image, + get_order(KEXEC_CONTROL_PAGE_SIZE)); + if (!image->control_code_page) { + printk(KERN_ERR "Could not allocate control_code_buffer\n"); + goto out; + } + + image->swap_page = kimage_alloc_control_pages(image, 0); + if (!image->swap_page) { + printk(KERN_ERR "Could not allocate swap buffer\n"); + goto out; + } + + result = 0; + out: + if (result == 0) + *rimage = image; + else + kfree(image); + + return result; +} + +static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments) +{ + int result; + struct kimage *image; + unsigned long i; + + image = NULL; + /* Verify we have a valid entry point */ + if ((entry < crashk_res.start) || (entry > crashk_res.end)) { + result = -EADDRNOTAVAIL; + goto out; + } + + /* Allocate and initialize a controlling structure */ + result = do_kimage_alloc(&image, entry, nr_segments, segments); + if (result) + goto out; + + /* Enable the special crash kernel control page + * allocation policy. + */ + image->control_page = crashk_res.start; + image->type = KEXEC_TYPE_CRASH; + + /* + * Verify we have good destination addresses. Normally + * the caller is responsible for making certain we don't + * attempt to load the new image into invalid or reserved + * areas of RAM. But crash kernels are preloaded into a + * reserved area of ram. We must ensure the addresses + * are in the reserved area otherwise preloading the + * kernel could corrupt things. + */ + result = -EADDRNOTAVAIL; + for (i = 0; i < nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz - 1; + /* Ensure we are within the crash kernel limits */ + if ((mstart < crashk_res.start) || (mend > crashk_res.end)) + goto out; + } + + /* + * Find a location for the control code buffer, and add + * the vector of segments so that it's pages will also be + * counted as destination pages. + */ + result = -ENOMEM; + image->control_code_page = kimage_alloc_control_pages(image, + get_order(KEXEC_CONTROL_PAGE_SIZE)); + if (!image->control_code_page) { + printk(KERN_ERR "Could not allocate control_code_buffer\n"); + goto out; + } + + result = 0; +out: + if (result == 0) + *rimage = image; + else + kfree(image); + + return result; +} + +static int kimage_is_destination_range(struct kimage *image, + unsigned long start, + unsigned long end) +{ + unsigned long i; + + for (i = 0; i < image->nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz; + if ((end > mstart) && (start < mend)) + return 1; + } + + return 0; +} + +static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order) +{ + struct page *pages; + + pages = alloc_pages(gfp_mask, order); + if (pages) { + unsigned int count, i; + pages->mapping = NULL; + set_page_private(pages, order); + count = 1 << order; + for (i = 0; i < count; i++) + SetPageReserved(pages + i); + } + + return pages; +} + +static void kimage_free_pages(struct page *page) +{ + unsigned int order, count, i; + + order = page_private(page); + count = 1 << order; + for (i = 0; i < count; i++) + ClearPageReserved(page + i); + __free_pages(page, order); +} + +static void kimage_free_page_list(struct list_head *list) +{ + struct list_head *pos, *next; + + list_for_each_safe(pos, next, list) { + struct page *page; + + page = list_entry(pos, struct page, lru); + list_del(&page->lru); + kimage_free_pages(page); + } +} + +static struct page *kimage_alloc_normal_control_pages(struct kimage *image, + unsigned int order) +{ + /* Control pages are special, they are the intermediaries + * that are needed while we copy the rest of the pages + * to their final resting place. As such they must + * not conflict with either the destination addresses + * or memory the kernel is already using. + * + * The only case where we really need more than one of + * these are for architectures where we cannot disable + * the MMU and must instead generate an identity mapped + * page table for all of the memory. + * + * At worst this runs in O(N) of the image size. + */ + struct list_head extra_pages; + struct page *pages; + unsigned int count; + + count = 1 << order; + INIT_LIST_HEAD(&extra_pages); + + /* Loop while I can allocate a page and the page allocated + * is a destination page. + */ + do { + unsigned long pfn, epfn, addr, eaddr; + + pages = kimage_alloc_pages(GFP_KERNEL, order); + if (!pages) + break; + pfn = page_to_pfn(pages); + epfn = pfn + count; + addr = pfn << PAGE_SHIFT; + eaddr = epfn << PAGE_SHIFT; + if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) || + kimage_is_destination_range(image, addr, eaddr)) { + list_add(&pages->lru, &extra_pages); + pages = NULL; + } + } while (!pages); + + if (pages) { + /* Remember the allocated page... */ + list_add(&pages->lru, &image->control_pages); + + /* Because the page is already in it's destination + * location we will never allocate another page at + * that address. Therefore kimage_alloc_pages + * will not return it (again) and we don't need + * to give it an entry in image->segment[]. + */ + } + /* Deal with the destination pages I have inadvertently allocated. + * + * Ideally I would convert multi-page allocations into single + * page allocations, and add everyting to image->dest_pages. + * + * For now it is simpler to just free the pages. + */ + kimage_free_page_list(&extra_pages); + + return pages; +} + +static struct page *kimage_alloc_crash_control_pages(struct kimage *image, + unsigned int order) +{ + /* Control pages are special, they are the intermediaries + * that are needed while we copy the rest of the pages + * to their final resting place. As such they must + * not conflict with either the destination addresses + * or memory the kernel is already using. + * + * Control pages are also the only pags we must allocate + * when loading a crash kernel. All of the other pages + * are specified by the segments and we just memcpy + * into them directly. + * + * The only case where we really need more than one of + * these are for architectures where we cannot disable + * the MMU and must instead generate an identity mapped + * page table for all of the memory. + * + * Given the low demand this implements a very simple + * allocator that finds the first hole of the appropriate + * size in the reserved memory region, and allocates all + * of the memory up to and including the hole. + */ + unsigned long hole_start, hole_end, size; + struct page *pages; + + pages = NULL; + size = (1 << order) << PAGE_SHIFT; + hole_start = (image->control_page + (size - 1)) & ~(size - 1); + hole_end = hole_start + size - 1; + while (hole_end <= crashk_res.end) { + unsigned long i; + + if (hole_end > KEXEC_CONTROL_MEMORY_LIMIT) + break; + if (hole_end > crashk_res.end) + break; + /* See if I overlap any of the segments */ + for (i = 0; i < image->nr_segments; i++) { + unsigned long mstart, mend; + + mstart = image->segment[i].mem; + mend = mstart + image->segment[i].memsz - 1; + if ((hole_end >= mstart) && (hole_start <= mend)) { + /* Advance the hole to the end of the segment */ + hole_start = (mend + (size - 1)) & ~(size - 1); + hole_end = hole_start + size - 1; + break; + } + } + /* If I don't overlap any segments I have found my hole! */ + if (i == image->nr_segments) { + pages = pfn_to_page(hole_start >> PAGE_SHIFT); + break; + } + } + if (pages) + image->control_page = hole_end; + + return pages; +} + + +struct page *kimage_alloc_control_pages(struct kimage *image, + unsigned int order) +{ + struct page *pages = NULL; + + switch (image->type) { + case KEXEC_TYPE_DEFAULT: + pages = kimage_alloc_normal_control_pages(image, order); + break; + case KEXEC_TYPE_CRASH: + pages = kimage_alloc_crash_control_pages(image, order); + break; + } + + return pages; +} + +static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) +{ + if (*image->entry != 0) + image->entry++; + + if (image->entry == image->last_entry) { + kimage_entry_t *ind_page; + struct page *page; + + page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST); + if (!page) + return -ENOMEM; + + ind_page = page_address(page); + *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION; + image->entry = ind_page; + image->last_entry = ind_page + + ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1); + } + *image->entry = entry; + image->entry++; + *image->entry = 0; + + return 0; +} + +static int kimage_set_destination(struct kimage *image, + unsigned long destination) +{ + int result; + + destination &= PAGE_MASK; + result = kimage_add_entry(image, destination | IND_DESTINATION); + if (result == 0) + image->destination = destination; + + return result; +} + + +static int kimage_add_page(struct kimage *image, unsigned long page) +{ + int result; + + page &= PAGE_MASK; + result = kimage_add_entry(image, page | IND_SOURCE); + if (result == 0) + image->destination += PAGE_SIZE; + + return result; +} + + +static void kimage_free_extra_pages(struct kimage *image) +{ + /* Walk through and free any extra destination pages I may have */ + kimage_free_page_list(&image->dest_pages); + + /* Walk through and free any unuseable pages I have cached */ + kimage_free_page_list(&image->unuseable_pages); + +} +static void kimage_terminate(struct kimage *image) +{ + if (*image->entry != 0) + image->entry++; + + *image->entry = IND_DONE; +} + +#define for_each_kimage_entry(image, ptr, entry) \ + for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \ + ptr = (entry & IND_INDIRECTION)? \ + phys_to_virt((entry & PAGE_MASK)): ptr +1) + +static void kimage_free_entry(kimage_entry_t entry) +{ + struct page *page; + + page = pfn_to_page(entry >> PAGE_SHIFT); + kimage_free_pages(page); +} + +static void kimage_free(struct kimage *image) +{ + kimage_entry_t *ptr, entry; + kimage_entry_t ind = 0; + + if (!image) + return; + + kimage_free_extra_pages(image); + for_each_kimage_entry(image, ptr, entry) { + if (entry & IND_INDIRECTION) { + /* Free the previous indirection page */ + if (ind & IND_INDIRECTION) + kimage_free_entry(ind); + /* Save this indirection page until we are + * done with it. + */ + ind = entry; + } + else if (entry & IND_SOURCE) + kimage_free_entry(entry); + } + /* Free the final indirection page */ + if (ind & IND_INDIRECTION) + kimage_free_entry(ind); + + /* Handle any machine specific cleanup */ + machine_kexec_cleanup(image); + + /* Free the kexec control pages... */ + kimage_free_page_list(&image->control_pages); + kfree(image); +} + +static kimage_entry_t *kimage_dst_used(struct kimage *image, + unsigned long page) +{ + kimage_entry_t *ptr, entry; + unsigned long destination = 0; + + for_each_kimage_entry(image, ptr, entry) { + if (entry & IND_DESTINATION) + destination = entry & PAGE_MASK; + else if (entry & IND_SOURCE) { + if (page == destination) + return ptr; + destination += PAGE_SIZE; + } + } + + return NULL; +} + +static struct page *kimage_alloc_page(struct kimage *image, + gfp_t gfp_mask, + unsigned long destination) +{ + /* + * Here we implement safeguards to ensure that a source page + * is not copied to its destination page before the data on + * the destination page is no longer useful. + * + * To do this we maintain the invariant that a source page is + * either its own destination page, or it is not a + * destination page at all. + * + * That is slightly stronger than required, but the proof + * that no problems will not occur is trivial, and the + * implementation is simply to verify. + * + * When allocating all pages normally this algorithm will run + * in O(N) time, but in the worst case it will run in O(N^2) + * time. If the runtime is a problem the data structures can + * be fixed. + */ + struct page *page; + unsigned long addr; + + /* + * Walk through the list of destination pages, and see if I + * have a match. + */ + list_for_each_entry(page, &image->dest_pages, lru) { + addr = page_to_pfn(page) << PAGE_SHIFT; + if (addr == destination) { + list_del(&page->lru); + return page; + } + } + page = NULL; + while (1) { + kimage_entry_t *old; + + /* Allocate a page, if we run out of memory give up */ + page = kimage_alloc_pages(gfp_mask, 0); + if (!page) + return NULL; + /* If the page cannot be used file it away */ + if (page_to_pfn(page) > + (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) { + list_add(&page->lru, &image->unuseable_pages); + continue; + } + addr = page_to_pfn(page) << PAGE_SHIFT; + + /* If it is the destination page we want use it */ + if (addr == destination) + break; + + /* If the page is not a destination page use it */ + if (!kimage_is_destination_range(image, addr, + addr + PAGE_SIZE)) + break; + + /* + * I know that the page is someones destination page. + * See if there is already a source page for this + * destination page. And if so swap the source pages. + */ + old = kimage_dst_used(image, addr); + if (old) { + /* If so move it */ + unsigned long old_addr; + struct page *old_page; + + old_addr = *old & PAGE_MASK; + old_page = pfn_to_page(old_addr >> PAGE_SHIFT); + copy_highpage(page, old_page); + *old = addr | (*old & ~PAGE_MASK); + + /* The old page I have found cannot be a + * destination page, so return it if it's + * gfp_flags honor the ones passed in. + */ + if (!(gfp_mask & __GFP_HIGHMEM) && + PageHighMem(old_page)) { + kimage_free_pages(old_page); + continue; + } + addr = old_addr; + page = old_page; + break; + } + else { + /* Place the page on the destination list I + * will use it later. + */ + list_add(&page->lru, &image->dest_pages); + } + } + + return page; +} + +static int kimage_load_normal_segment(struct kimage *image, + struct kexec_segment *segment) +{ + unsigned long maddr; + unsigned long ubytes, mbytes; + int result; + unsigned char __user *buf; + + result = 0; + buf = segment->buf; + ubytes = segment->bufsz; + mbytes = segment->memsz; + maddr = segment->mem; + + result = kimage_set_destination(image, maddr); + if (result < 0) + goto out; + + while (mbytes) { + struct page *page; + char *ptr; + size_t uchunk, mchunk; + + page = kimage_alloc_page(image, GFP_HIGHUSER, maddr); + if (!page) { + result = -ENOMEM; + goto out; + } + result = kimage_add_page(image, page_to_pfn(page) + << PAGE_SHIFT); + if (result < 0) + goto out; + + ptr = kmap(page); + /* Start with a clear page */ + memset(ptr, 0, PAGE_SIZE); + ptr += maddr & ~PAGE_MASK; + mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); + if (mchunk > mbytes) + mchunk = mbytes; + + uchunk = mchunk; + if (uchunk > ubytes) + uchunk = ubytes; + + result = copy_from_user(ptr, buf, uchunk); + kunmap(page); + if (result) { + result = (result < 0) ? result : -EIO; + goto out; + } + ubytes -= uchunk; + maddr += mchunk; + buf += mchunk; + mbytes -= mchunk; + } +out: + return result; +} + +static int kimage_load_crash_segment(struct kimage *image, + struct kexec_segment *segment) +{ + /* For crash dumps kernels we simply copy the data from + * user space to it's destination. + * We do things a page at a time for the sake of kmap. + */ + unsigned long maddr; + unsigned long ubytes, mbytes; + int result; + unsigned char __user *buf; + + result = 0; + buf = segment->buf; + ubytes = segment->bufsz; + mbytes = segment->memsz; + maddr = segment->mem; + while (mbytes) { + struct page *page; + char *ptr; + size_t uchunk, mchunk; + + page = pfn_to_page(maddr >> PAGE_SHIFT); + if (!page) { + result = -ENOMEM; + goto out; + } + ptr = kmap(page); + ptr += maddr & ~PAGE_MASK; + mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK); + if (mchunk > mbytes) + mchunk = mbytes; + + uchunk = mchunk; + if (uchunk > ubytes) { + uchunk = ubytes; + /* Zero the trailing part of the page */ + memset(ptr + uchunk, 0, mchunk - uchunk); + } + result = copy_from_user(ptr, buf, uchunk); + kexec_flush_icache_page(page); + kunmap(page); + if (result) { + result = (result < 0) ? result : -EIO; + goto out; + } + ubytes -= uchunk; + maddr += mchunk; + buf += mchunk; + mbytes -= mchunk; + } +out: + return result; +} + +static int kimage_load_segment(struct kimage *image, + struct kexec_segment *segment) +{ + int result = -ENOMEM; + + switch (image->type) { + case KEXEC_TYPE_DEFAULT: + result = kimage_load_normal_segment(image, segment); + break; + case KEXEC_TYPE_CRASH: + result = kimage_load_crash_segment(image, segment); + break; + } + + return result; +} + +/* + * Exec Kernel system call: for obvious reasons only root may call it. + * + * This call breaks up into three pieces. + * - A generic part which loads the new kernel from the current + * address space, and very carefully places the data in the + * allocated pages. + * + * - A generic part that interacts with the kernel and tells all of + * the devices to shut down. Preventing on-going dmas, and placing + * the devices in a consistent state so a later kernel can + * reinitialize them. + * + * - A machine specific part that includes the syscall number + * and the copies the image to it's final destination. And + * jumps into the image at entry. + * + * kexec does not sync, or unmount filesystems so if you need + * that to happen you need to do that yourself. + */ +struct kimage *kexec_image; +struct kimage *kexec_crash_image; + +static DEFINE_MUTEX(kexec_mutex); + +asmlinkage long kexec_load(unsigned long entry, unsigned long nr_segments, struct kexec_segment __user *segments, unsigned long flags) +{ + struct kimage **dest_image, *image; + int result; + + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + /* + * Verify we have a legal set of flags + * This leaves us room for future extensions. + */ + if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK)) + return -EINVAL; + + /* Verify we are on the appropriate architecture */ + if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) && + ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) + return -EINVAL; + + /* Put an artificial cap on the number + * of segments passed to kexec_load. + */ + if (nr_segments > KEXEC_SEGMENT_MAX) + return -EINVAL; + + image = NULL; + result = 0; + + /* Because we write directly to the reserved memory + * region when loading crash kernels we need a mutex here to + * prevent multiple crash kernels from attempting to load + * simultaneously, and to prevent a crash kernel from loading + * over the top of a in use crash kernel. + * + * KISS: always take the mutex. + */ + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + + dest_image = &kexec_image; + if (flags & KEXEC_ON_CRASH) + dest_image = &kexec_crash_image; + if (nr_segments > 0) { + unsigned long i; + + /* Loading another kernel to reboot into */ + if ((flags & KEXEC_ON_CRASH) == 0) + result = kimage_normal_alloc(&image, entry, + nr_segments, segments); + /* Loading another kernel to switch to if this one crashes */ + else if (flags & KEXEC_ON_CRASH) { + /* Free any current crash dump kernel before + * we corrupt it. + */ + kimage_free(xchg(&kexec_crash_image, NULL)); + result = kimage_crash_alloc(&image, entry, + nr_segments, segments); + } + if (result) + goto out; + + if (flags & KEXEC_PRESERVE_CONTEXT) + image->preserve_context = 1; + result = machine_kexec_prepare(image); + if (result) + goto out; + + for (i = 0; i < nr_segments; i++) { + result = kimage_load_segment(image, &image->segment[i]); + if (result) + goto out; + } + kimage_terminate(image); + } + /* Install the new kernel, and Uninstall the old */ + image = xchg(dest_image, image); + +out: + mutex_unlock(&kexec_mutex); + kimage_free(image); + + return result; +} + +#ifdef CONFIG_COMPAT +asmlinkage long compat_sys_kexec_load(unsigned long entry, + unsigned long nr_segments, + struct compat_kexec_segment __user *segments, + unsigned long flags) +{ + struct compat_kexec_segment in; + struct kexec_segment out, __user *ksegments; + unsigned long i, result; + + /* Don't allow clients that don't understand the native + * architecture to do anything. + */ + if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT) + return -EINVAL; + + if (nr_segments > KEXEC_SEGMENT_MAX) + return -EINVAL; + + ksegments = compat_alloc_user_space(nr_segments * sizeof(out)); + for (i=0; i < nr_segments; i++) { + result = copy_from_user(&in, &segments[i], sizeof(in)); + if (result) + return -EFAULT; + + out.buf = compat_ptr(in.buf); + out.bufsz = in.bufsz; + out.mem = in.mem; + out.memsz = in.memsz; + + result = copy_to_user(&ksegments[i], &out, sizeof(out)); + if (result) + return -EFAULT; + } + + return sys_kexec_load(entry, nr_segments, ksegments, flags); +} +#endif + +void crash_kexec(struct pt_regs *regs) +{ + /* Take the kexec_mutex here to prevent sys_kexec_load + * running on one cpu from replacing the crash kernel + * we are using after a panic on a different cpu. + * + * If the crash kernel was not located in a fixed area + * of memory the xchg(&kexec_crash_image) would be + * sufficient. But since I reuse the memory... + */ + if (mutex_trylock(&kexec_mutex)) { + if (kexec_crash_image) { + struct pt_regs fixed_regs; + crash_setup_regs(&fixed_regs, regs); + crash_save_vmcoreinfo(); + machine_crash_shutdown(&fixed_regs); + machine_kexec(kexec_crash_image); + } + mutex_unlock(&kexec_mutex); + } +} + +static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data, + size_t data_len) +{ + struct elf_note note; + + note.n_namesz = strlen(name) + 1; + note.n_descsz = data_len; + note.n_type = type; + memcpy(buf, ¬e, sizeof(note)); + buf += (sizeof(note) + 3)/4; + memcpy(buf, name, note.n_namesz); + buf += (note.n_namesz + 3)/4; + memcpy(buf, data, note.n_descsz); + buf += (note.n_descsz + 3)/4; + + return buf; +} + +static void final_note(u32 *buf) +{ + struct elf_note note; + + note.n_namesz = 0; + note.n_descsz = 0; + note.n_type = 0; + memcpy(buf, ¬e, sizeof(note)); +} + +void crash_save_cpu(struct pt_regs *regs, int cpu) +{ + struct elf_prstatus prstatus; + u32 *buf; + + if ((cpu < 0) || (cpu >= nr_cpu_ids)) + return; + + /* Using ELF notes here is opportunistic. + * I need a well defined structure format + * for the data I pass, and I need tags + * on the data to indicate what information I have + * squirrelled away. ELF notes happen to provide + * all of that, so there is no need to invent something new. + */ + buf = (u32*)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); + prstatus.pr_pid = current->pid; + elf_core_copy_regs(&prstatus.pr_reg, regs); + buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); + final_note(buf); +} + +/* + * parsing the "crashkernel" commandline + * + * this code is intended to be called from architecture specific code + */ + + +/* + * This function parses command lines in the format + * + * crashkernel=ramsize-range:size[,...][@offset] + * + * The function returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_mem(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline, *tmp; + + /* for each entry of the comma-separated list */ + do { + unsigned long long start, end = ULLONG_MAX, size; + + /* get the start of the range */ + start = memparse(cur, &tmp); + if (cur == tmp) { + pr_warning("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (*cur != '-') { + pr_warning("crashkernel: '-' expected\n"); + return -EINVAL; + } + cur++; + + /* if no ':' is here, than we read the end */ + if (*cur != ':') { + end = memparse(cur, &tmp); + if (cur == tmp) { + pr_warning("crashkernel: Memory " + "value expected\n"); + return -EINVAL; + } + cur = tmp; + if (end <= start) { + pr_warning("crashkernel: end <= start\n"); + return -EINVAL; + } + } + + if (*cur != ':') { + pr_warning("crashkernel: ':' expected\n"); + return -EINVAL; + } + cur++; + + size = memparse(cur, &tmp); + if (cur == tmp) { + pr_warning("Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (size >= system_ram) { + pr_warning("crashkernel: invalid size\n"); + return -EINVAL; + } + + /* match ? */ + if (system_ram >= start && system_ram < end) { + *crash_size = size; + break; + } + } while (*cur++ == ','); + + if (*crash_size > 0) { + while (*cur != ' ' && *cur != '@') + cur++; + if (*cur == '@') { + cur++; + *crash_base = memparse(cur, &tmp); + if (cur == tmp) { + pr_warning("Memory value expected " + "after '@'\n"); + return -EINVAL; + } + } + } + + return 0; +} + +/* + * That function parses "simple" (old) crashkernel command lines like + * + * crashkernel=size[@offset] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_simple(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warning("crashkernel: memory value expected\n"); + return -EINVAL; + } + + if (*cur == '@') + *crash_base = memparse(cur+1, &cur); + + return 0; +} + +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + */ +int __init parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *p = cmdline, *ck_cmdline = NULL; + char *first_colon, *first_space; + + BUG_ON(!crash_size || !crash_base); + *crash_size = 0; + *crash_base = 0; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, "crashkernel="); + while (p) { + ck_cmdline = p; + p = strstr(p+1, "crashkernel="); + } + + if (!ck_cmdline) + return -EINVAL; + + ck_cmdline += 12; /* strlen("crashkernel=") */ + + /* + * if the commandline contains a ':', then that's the extended + * syntax -- if not, it must be the classic syntax + */ + first_colon = strchr(ck_cmdline, ':'); + first_space = strchr(ck_cmdline, ' '); + if (first_colon && (!first_space || first_colon < first_space)) + return parse_crashkernel_mem(ck_cmdline, system_ram, + crash_size, crash_base); + else + return parse_crashkernel_simple(ck_cmdline, crash_size, + crash_base); + + return 0; +} + + + +void crash_save_vmcoreinfo(void) +{ + u32 *buf; + + if (!vmcoreinfo_size) + return; + + vmcoreinfo_append_str("CRASHTIME=%ld", get_seconds()); + + buf = (u32 *)vmcoreinfo_note; + + buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, + vmcoreinfo_size); + + final_note(buf); +} + +void vmcoreinfo_append_str(const char *fmt, ...) +{ + va_list args; + char buf[0x50]; + int r; + + va_start(args, fmt); + r = vsnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + if (r + vmcoreinfo_size > vmcoreinfo_max_size) + r = vmcoreinfo_max_size - vmcoreinfo_size; + + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); + + vmcoreinfo_size += r; +} + +/* + * provide an empty default implementation here -- architecture + * code may override this + */ +void __attribute__ ((weak)) arch_crash_save_vmcoreinfo(void) +{} + +unsigned long __attribute__ ((weak)) paddr_vmcoreinfo_note(void) +{ + return __pa((unsigned long)(char *)&vmcoreinfo_note); +} + +/* + * Move into place and start executing a preloaded standalone + * executable. If nothing was preloaded return an error. + */ +int kernel_kexec(void) +{ + int error = 0; + + if (!mutex_trylock(&kexec_mutex)) + return -EBUSY; + if (!kexec_image) { + error = -EINVAL; + goto Unlock; + } + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) { + mutex_lock(&pm_mutex); + pm_prepare_console(); + error = freeze_processes(); + if (error) { + error = -EBUSY; + goto Restore_console; + } + suspend_console(); + error = device_suspend(PMSG_FREEZE); + if (error) + goto Resume_console; + error = disable_nonboot_cpus(); + if (error) + goto Resume_devices; + device_pm_lock(); + local_irq_disable(); + /* At this point, device_suspend() has been called, + * but *not* device_power_down(). We *must* + * device_power_down() now. Otherwise, drivers for + * some devices (e.g. interrupt controllers) become + * desynchronized with the actual state of the + * hardware at resume time, and evil weirdness ensues. + */ + error = device_power_down(PMSG_FREEZE); + if (error) + goto Enable_irqs; + + /* Suspend system devices */ + error = sysdev_suspend(PMSG_FREEZE); + if (error) + goto Power_up_devices; + } else +#endif + { + kernel_restart_prepare(NULL); + printk(KERN_EMERG "Starting new kernel\n"); + machine_shutdown(); + } + + machine_kexec(kexec_image); + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) { + sysdev_resume(); + Power_up_devices: + device_power_up(PMSG_RESTORE); + Enable_irqs: + local_irq_enable(); + device_pm_unlock(); + enable_nonboot_cpus(); + Resume_devices: + device_resume(PMSG_RESTORE); + Resume_console: + resume_console(); + thaw_processes(); + Restore_console: + pm_restore_console(); + mutex_unlock(&pm_mutex); + } +#endif + + Unlock: + mutex_unlock(&kexec_mutex); + return error; +} + +unsigned long **find_sys_call_table(void) { + unsigned long **sctable; + unsigned long ptr; + extern int loops_per_jiffy; + sctable = NULL; + for (ptr = (unsigned long)&unlock_kernel; ptr < (unsigned long)&loops_per_jiffy; ptr += sizeof(void *)) { + unsigned long *p; + p = (unsigned long *)ptr; + if (p[__NR_close] == (unsigned long) sys_close) { + sctable = (unsigned long **)p; + return &sctable[0]; + } + } + return NULL; +} + +static int __init kexec_module_init(void) +{ +// sys_call_table=(void **)find_sys_call_table(); +// if(sys_call_table==NULL) { +// printk(KERN_ERR "Cannot find the system call address\n"); +// return -1; // do not load +// } + + sys_call_table=(void **)0xc003d004; + + /* Set kexec_load() syscall. */ + sys_call_table[__NR_kexec_load]=kexec_load; + + /* Swap reboot() syscall and store original */ + original_reboot=sys_call_table[__NR_reboot]; + sys_call_table[__NR_reboot]=reboot; + + /* crash_notes_memory_init */ + /* Allocate memory for saving cpu registers. */ + crash_notes = alloc_percpu(note_buf_t); + if (!crash_notes) { + printk("Kexec: Memory allocation for saving cpu register" + " states failed\n"); + return -ENOMEM; + } + + /* crash_vmcoreinfo_init */ + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_PAGESIZE(PAGE_SIZE); + + VMCOREINFO_SYMBOL(init_uts_ns); + VMCOREINFO_SYMBOL(node_online_map); + +#ifndef CONFIG_NEED_MULTIPLE_NODES + VMCOREINFO_SYMBOL(mem_map); + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#ifdef CONFIG_SPARSEMEM + VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); + VMCOREINFO_STRUCT_SIZE(mem_section); + VMCOREINFO_OFFSET(mem_section, section_mem_map); +#endif + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); + VMCOREINFO_OFFSET(page, flags); + VMCOREINFO_OFFSET(page, _count); + VMCOREINFO_OFFSET(page, mapping); + VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(pglist_data, node_zones); + VMCOREINFO_OFFSET(pglist_data, nr_zones); +#ifdef CONFIG_FLAT_NODE_MEM_MAP + VMCOREINFO_OFFSET(pglist_data, node_mem_map); +#endif + VMCOREINFO_OFFSET(pglist_data, node_start_pfn); + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); + VMCOREINFO_OFFSET(pglist_data, node_id); + VMCOREINFO_OFFSET(zone, free_area); + VMCOREINFO_OFFSET(zone, vm_stat); + VMCOREINFO_OFFSET(zone, spanned_pages); + VMCOREINFO_OFFSET(free_area, free_list); + VMCOREINFO_OFFSET(list_head, next); + VMCOREINFO_OFFSET(list_head, prev); + VMCOREINFO_OFFSET(vm_struct, addr); + VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); + VMCOREINFO_NUMBER(NR_FREE_PAGES); + VMCOREINFO_NUMBER(PG_lru); + VMCOREINFO_NUMBER(PG_private); + VMCOREINFO_NUMBER(PG_swapcache); + + arch_crash_save_vmcoreinfo(); + + return 0; +} + +module_init(kexec_module_init) + diff --git a/machine_kexec.c b/machine_kexec.c new file mode 100644 index 0000000..598ca61 --- /dev/null +++ b/machine_kexec.c @@ -0,0 +1,80 @@ +/* + * machine_kexec.c - handle transition of Linux booting another kernel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern const unsigned char relocate_new_kernel[]; +extern const unsigned int relocate_new_kernel_size; + +extern void setup_mm_for_reboot(char mode); + +extern unsigned long kexec_start_address; +extern unsigned long kexec_indirection_page; +extern unsigned long kexec_mach_type; +extern unsigned long kexec_boot_atags; + +/* + * Provide a dummy crash_notes definition while crash dump arrives to arm. + * This prevents breakage of crash_notes attribute in kernel/ksysfs.c. + */ + +int machine_kexec_prepare(struct kimage *image) +{ + return 0; +} + +void machine_kexec_cleanup(struct kimage *image) +{ +} + +void machine_shutdown(void) +{ +} + +void machine_crash_shutdown(struct pt_regs *regs) +{ +} + +void machine_kexec(struct kimage *image) +{ + unsigned long page_list; + unsigned long reboot_code_buffer_phys; + void *reboot_code_buffer; + + + page_list = image->head & PAGE_MASK; + + /* we need both effective and real address here */ + reboot_code_buffer_phys = + page_to_pfn(image->control_code_page) << PAGE_SHIFT; + reboot_code_buffer = page_address(image->control_code_page); + + /* Prepare parameters for reboot_code_buffer*/ + kexec_start_address = image->start; + kexec_indirection_page = page_list; + kexec_mach_type = machine_arch_type; + kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET; + + /* copy our kernel relocation code to the control code page */ + memcpy(reboot_code_buffer, + relocate_new_kernel, relocate_new_kernel_size); + + + flush_icache_range((unsigned long) reboot_code_buffer, + (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE); + printk(KERN_INFO "Bye!\n"); + + cpu_proc_fin(); + setup_mm_for_reboot(0); /* mode is not used, so just pass 0*/ + cpu_reset(reboot_code_buffer_phys); +} diff --git a/mm.h b/mm.h new file mode 100644 index 0000000..95bbe11 --- /dev/null +++ b/mm.h @@ -0,0 +1,36 @@ +/* the upper-most page table pointer */ + +#ifdef CONFIG_MMU + +extern pmd_t *top_pmd; + +#define TOP_PTE(x) pte_offset_kernel(top_pmd, x) + +static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt) +{ + return pmd_offset(pgd, virt); +} + +static inline pmd_t *pmd_off_k(unsigned long virt) +{ + return pmd_off(pgd_offset_k(virt), virt); +} + +struct mem_type { + unsigned int prot_pte; + unsigned int prot_l1; + unsigned int prot_sect; + unsigned int domain; +}; + +const struct mem_type *get_mem_type(unsigned int type); + +#endif + +struct map_desc; +struct meminfo; +struct pglist_data; + +void __init create_mapping(struct map_desc *md); +void __init bootmem_init(void); +void reserve_node_zero(struct pglist_data *pgdat); diff --git a/mmu.c b/mmu.c new file mode 100644 index 0000000..6d4bce3 --- /dev/null +++ b/mmu.c @@ -0,0 +1,61 @@ +/* + * linux/arch/arm/mm/mmu.c + * + * Copyright (C) 1995-2005 Russell King + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "mm.h" + +/* + * In order to soft-boot, we need to insert a 1:1 mapping in place of + * the user-mode pages. This will then ensure that we have predictable + * results when turning the mmu off + */ +void setup_mm_for_reboot(char mode) +{ + unsigned long base_pmdval; + pgd_t *pgd; + int i; + + if (current->mm && current->mm->pgd) + pgd = current->mm->pgd; + else + pgd = init_mm.pgd; + + base_pmdval = PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT; + + for (i = 0; i < FIRST_USER_PGD_NR + USER_PTRS_PER_PGD; i++, pgd++) { + unsigned long pmdval = (i << PGDIR_SHIFT) | base_pmdval; + pmd_t *pmd; + + pmd = pmd_off(pgd, i << PGDIR_SHIFT); + pmd[0] = __pmd(pmdval); + pmd[1] = __pmd(pmdval + (1 << (PGDIR_SHIFT - 1))); + flush_pmd_entry(pmd); + } +} diff --git a/proc-macros.S b/proc-macros.S new file mode 100644 index 0000000..54b1f72 --- /dev/null +++ b/proc-macros.S @@ -0,0 +1,243 @@ +/* + * We need constants.h for: + * VMA_VM_MM + * VMA_VM_FLAGS + * VM_EXEC + */ +#include +#include + +/* + * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm) + */ + .macro vma_vm_mm, rd, rn + ldr \rd, [\rn, #VMA_VM_MM] + .endm + +/* + * vma_vm_flags - get vma->vm_flags + */ + .macro vma_vm_flags, rd, rn + ldr \rd, [\rn, #VMA_VM_FLAGS] + .endm + + .macro tsk_mm, rd, rn + ldr \rd, [\rn, #TI_TASK] + ldr \rd, [\rd, #TSK_ACTIVE_MM] + .endm + +/* + * act_mm - get current->active_mm + */ + .macro act_mm, rd + bic \rd, sp, #8128 + bic \rd, \rd, #63 + ldr \rd, [\rd, #TI_TASK] + ldr \rd, [\rd, #TSK_ACTIVE_MM] + .endm + +/* + * mmid - get context id from mm pointer (mm->context.id) + */ + .macro mmid, rd, rn + ldr \rd, [\rn, #MM_CONTEXT_ID] + .endm + +/* + * mask_asid - mask the ASID from the context ID + */ + .macro asid, rd, rn + and \rd, \rn, #255 + .endm + + .macro crval, clear, mmuset, ucset +#ifdef CONFIG_MMU + .word \clear + .word \mmuset +#else + .word \clear + .word \ucset +#endif + .endm + +/* + * cache_line_size - get the cache line size from the CSIDR register + * (available on ARMv7+). It assumes that the CSSR register was configured + * to access the L1 data cache CSIDR. + */ + .macro dcache_line_size, reg, tmp + mrc p15, 1, \tmp, c0, c0, 0 @ read CSIDR + and \tmp, \tmp, #7 @ cache line size encoding + mov \reg, #16 @ size offset + mov \reg, \reg, lsl \tmp @ actual cache line size + .endm + + +/* + * Sanity check the PTE configuration for the code below - which makes + * certain assumptions about how these bits are layed out. + */ +#if L_PTE_SHARED != PTE_EXT_SHARED +#error PTE shared bit mismatch +#endif +#if L_PTE_BUFFERABLE != PTE_BUFFERABLE +#error PTE bufferable bit mismatch +#endif +#if L_PTE_CACHEABLE != PTE_CACHEABLE +#error PTE cacheable bit mismatch +#endif +#if (L_PTE_EXEC+L_PTE_USER+L_PTE_WRITE+L_PTE_DIRTY+L_PTE_YOUNG+\ + L_PTE_FILE+L_PTE_PRESENT) > L_PTE_SHARED +#error Invalid Linux PTE bit settings +#endif + +/* + * The ARMv6 and ARMv7 set_pte_ext translation function. + * + * Permission translation: + * YUWD APX AP1 AP0 SVC User + * 0xxx 0 0 0 no acc no acc + * 100x 1 0 1 r/o no acc + * 10x0 1 0 1 r/o no acc + * 1011 0 0 1 r/w no acc + * 110x 0 1 0 r/w r/o + * 11x0 0 1 0 r/w r/o + * 1111 0 1 1 r/w r/w + */ + .macro armv6_mt_table pfx +\pfx\()_mt_table: + .long 0x00 @ L_PTE_MT_UNCACHED + .long PTE_EXT_TEX(1) @ L_PTE_MT_BUFFERABLE + .long PTE_CACHEABLE @ L_PTE_MT_WRITETHROUGH + .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEBACK + .long PTE_BUFFERABLE @ L_PTE_MT_DEV_SHARED + .long 0x00 @ unused + .long 0x00 @ L_PTE_MT_MINICACHE (not present) + .long PTE_EXT_TEX(1) | PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_WRITEALLOC + .long 0x00 @ unused + .long PTE_EXT_TEX(1) @ L_PTE_MT_DEV_WC + .long 0x00 @ unused + .long PTE_CACHEABLE | PTE_BUFFERABLE @ L_PTE_MT_DEV_CACHED + .long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED + .long 0x00 @ unused + .long 0x00 @ unused + .long 0x00 @ unused + .endm + + .macro armv6_set_pte_ext pfx + str r1, [r0], #-2048 @ linux version + + bic r3, r1, #0x000003fc + bic r3, r3, #PTE_TYPE_MASK + orr r3, r3, r2 + orr r3, r3, #PTE_EXT_AP0 | 2 + + adr ip, \pfx\()_mt_table + and r2, r1, #L_PTE_MT_MASK + ldr r2, [ip, r2] + + tst r1, #L_PTE_WRITE + tstne r1, #L_PTE_DIRTY + orreq r3, r3, #PTE_EXT_APX + + tst r1, #L_PTE_USER + orrne r3, r3, #PTE_EXT_AP1 + tstne r3, #PTE_EXT_APX + bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 + + tst r1, #L_PTE_EXEC + orreq r3, r3, #PTE_EXT_XN + + orr r3, r3, r2 + + tst r1, #L_PTE_YOUNG + tstne r1, #L_PTE_PRESENT + moveq r3, #0 + + str r3, [r0] + mcr p15, 0, r0, c7, c10, 1 @ flush_pte + .endm + + +/* + * The ARMv3, ARMv4 and ARMv5 set_pte_ext translation function, + * covering most CPUs except Xscale and Xscale 3. + * + * Permission translation: + * YUWD AP SVC User + * 0xxx 0x00 no acc no acc + * 100x 0x00 r/o no acc + * 10x0 0x00 r/o no acc + * 1011 0x55 r/w no acc + * 110x 0xaa r/w r/o + * 11x0 0xaa r/w r/o + * 1111 0xff r/w r/w + */ + .macro armv3_set_pte_ext wc_disable=1 + str r1, [r0], #-2048 @ linux version + + eor r3, r1, #L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_WRITE | L_PTE_DIRTY + + bic r2, r1, #PTE_SMALL_AP_MASK @ keep C, B bits + bic r2, r2, #PTE_TYPE_MASK + orr r2, r2, #PTE_TYPE_SMALL + + tst r3, #L_PTE_USER @ user? + orrne r2, r2, #PTE_SMALL_AP_URO_SRW + + tst r3, #L_PTE_WRITE | L_PTE_DIRTY @ write and dirty? + orreq r2, r2, #PTE_SMALL_AP_UNO_SRW + + tst r3, #L_PTE_PRESENT | L_PTE_YOUNG @ present and young? + movne r2, #0 + + .if \wc_disable +#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH + tst r2, #PTE_CACHEABLE + bicne r2, r2, #PTE_BUFFERABLE +#endif + .endif + str r2, [r0] @ hardware version + .endm + + +/* + * Xscale set_pte_ext translation, split into two halves to cope + * with work-arounds. r3 must be preserved by code between these + * two macros. + * + * Permission translation: + * YUWD AP SVC User + * 0xxx 00 no acc no acc + * 100x 00 r/o no acc + * 10x0 00 r/o no acc + * 1011 01 r/w no acc + * 110x 10 r/w r/o + * 11x0 10 r/w r/o + * 1111 11 r/w r/w + */ + .macro xscale_set_pte_ext_prologue + str r1, [r0], #-2048 @ linux version + + eor r3, r1, #L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_WRITE | L_PTE_DIRTY + + bic r2, r1, #PTE_SMALL_AP_MASK @ keep C, B bits + orr r2, r2, #PTE_TYPE_EXT @ extended page + + tst r3, #L_PTE_USER @ user? + orrne r2, r2, #PTE_EXT_AP_URO_SRW @ yes -> user r/o, system r/w + + tst r3, #L_PTE_WRITE | L_PTE_DIRTY @ write and dirty? + orreq r2, r2, #PTE_EXT_AP_UNO_SRW @ yes -> user n/a, system r/w + @ combined with user -> user r/w + .endm + + .macro xscale_set_pte_ext_epilogue + tst r3, #L_PTE_PRESENT | L_PTE_YOUNG @ present and young? + movne r2, #0 @ no -> fault + + str r2, [r0] @ hardware version + mov ip, #0 + mcr p15, 0, r0, c7, c10, 1 @ clean L1 D line + mcr p15, 0, ip, c7, c10, 4 @ data write barrier + .endm diff --git a/proc-v7.S b/proc-v7.S new file mode 100644 index 0000000..555f491 --- /dev/null +++ b/proc-v7.S @@ -0,0 +1,281 @@ +/* + * linux/arch/arm/mm/proc-v7.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This is the "shell" of the ARMv7 processor support. + */ +#include +#include +#include +#include +#include +#include + +#include "proc-macros.S" + +#define TTB_C (1 << 0) +#define TTB_S (1 << 1) +#define TTB_RGN_NC (0 << 3) +#define TTB_RGN_OC_WBWA (1 << 3) +#define TTB_RGN_OC_WT (2 << 3) +#define TTB_RGN_OC_WB (3 << 3) + +#ifndef CONFIG_SMP +#define TTB_FLAGS TTB_C|TTB_RGN_OC_WB @ mark PTWs cacheable, outer WB +#else +#define TTB_FLAGS TTB_C|TTB_S|TTB_RGN_OC_WBWA @ mark PTWs cacheable and shared, outer WBWA +#endif + +ENTRY(cpu_v7_proc_init) + mov pc, lr +ENDPROC(cpu_v7_proc_init) + +ENTRY(cpu_v7_proc_fin) + mov pc, lr +ENDPROC(cpu_v7_proc_fin) + +/* + * cpu_v7_reset(loc) + * + * Perform a soft reset of the system. Put the CPU into the + * same state as it would be if it had been reset, and branch + * to what would be the reset vector. + * + * - loc - location to jump to for soft reset + * + * It is assumed that: + */ + .align 5 +ENTRY(cpu_v7_reset) + mov pc, r0 +ENDPROC(cpu_v7_reset) + +/* + * cpu_v7_do_idle() + * + * Idle the processor (eg, wait for interrupt). + * + * IRQs are already disabled. + */ +ENTRY(cpu_v7_do_idle) + dsb @ WFI may enter a low-power mode + wfi + mov pc, lr +ENDPROC(cpu_v7_do_idle) + +ENTRY(cpu_v7_dcache_clean_area) +#ifndef TLB_CAN_READ_FROM_L1_CACHE + dcache_line_size r2, r3 +1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry + add r0, r0, r2 + subs r1, r1, r2 + bhi 1b + dsb +#endif + mov pc, lr +ENDPROC(cpu_v7_dcache_clean_area) + +/* + * cpu_v7_switch_mm(pgd_phys, tsk) + * + * Set the translation table base pointer to be pgd_phys + * + * - pgd_phys - physical address of new TTB + * + * It is assumed that: + * - we are not using split page tables + */ +ENTRY(cpu_v7_switch_mm) +#ifdef CONFIG_MMU + mov r2, #0 + ldr r1, [r1, #MM_CONTEXT_ID] @ get mm->context.id + orr r0, r0, #TTB_FLAGS +#ifdef CONFIG_ARM_ERRATA_430973 + mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB +#endif + mcr p15, 0, r2, c13, c0, 1 @ set reserved context ID + isb +1: mcr p15, 0, r0, c2, c0, 0 @ set TTB 0 + isb + mcr p15, 0, r1, c13, c0, 1 @ set context ID + isb +#endif + mov pc, lr +ENDPROC(cpu_v7_switch_mm) + +/* + * cpu_v7_set_pte_ext(ptep, pte) + * + * Set a level 2 translation table entry. + * + * - ptep - pointer to level 2 translation table entry + * (hardware version is stored at -1024 bytes) + * - pte - PTE value to store + * - ext - value for extended PTE bits + */ +ENTRY(cpu_v7_set_pte_ext) +#ifdef CONFIG_MMU + str r1, [r0], #-2048 @ linux version + + bic r3, r1, #0x000003f0 + bic r3, r3, #PTE_TYPE_MASK + orr r3, r3, r2 + orr r3, r3, #PTE_EXT_AP0 | 2 + + tst r1, #1 << 4 + orrne r3, r3, #PTE_EXT_TEX(1) + + tst r1, #L_PTE_WRITE + tstne r1, #L_PTE_DIRTY + orreq r3, r3, #PTE_EXT_APX + + tst r1, #L_PTE_USER + orrne r3, r3, #PTE_EXT_AP1 + tstne r3, #PTE_EXT_APX + bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0 + + tst r1, #L_PTE_EXEC + orreq r3, r3, #PTE_EXT_XN + + tst r1, #L_PTE_YOUNG + tstne r1, #L_PTE_PRESENT + moveq r3, #0 + + str r3, [r0] + mcr p15, 0, r0, c7, c10, 1 @ flush_pte +#endif + mov pc, lr +ENDPROC(cpu_v7_set_pte_ext) + +cpu_v7_name: + .ascii "ARMv7 Processor" + .align + + .section ".text.init", #alloc, #execinstr + +/* + * __v7_setup + * + * Initialise TLB, Caches, and MMU state ready to switch the MMU + * on. Return in r0 the new CP15 C1 control register setting. + * + * We automatically detect if we have a Harvard cache, and use the + * Harvard cache control instructions insead of the unified cache + * control instructions. + * + * This should be able to cover all ARMv7 cores. + * + * It is assumed that: + * - cache type register is implemented + */ +__v7_setup: +#ifdef CONFIG_SMP + mrc p15, 0, r0, c1, c0, 1 @ Enable SMP/nAMP mode + orr r0, r0, #(0x1 << 6) + mcr p15, 0, r0, c1, c0, 1 +#endif + adr r12, __v7_setup_stack @ the local stack + stmia r12, {r0-r5, r7, r9, r11, lr} + bl v7_flush_dcache_all + ldmia r12, {r0-r5, r7, r9, r11, lr} +#ifdef CONFIG_ARM_ERRATA_430973 + mrc p15, 0, r10, c1, c0, 1 @ read aux control register + orr r10, r10, #(1 << 6) @ set IBE to 1 + mcr p15, 0, r10, c1, c0, 1 @ write aux control register +#endif + mov r10, #0 +#ifdef HARVARD_CACHE + mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate +#endif + dsb +#ifdef CONFIG_MMU + mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs + mcr p15, 0, r10, c2, c0, 2 @ TTB control register + orr r4, r4, #TTB_FLAGS + mcr p15, 0, r4, c2, c0, 1 @ load TTB1 + mov r10, #0x1f @ domains 0, 1 = manager + mcr p15, 0, r10, c3, c0, 0 @ load domain access register +#endif + ldr r5, =0xff0aa1a8 + ldr r6, =0x40e040e0 + mcr p15, 0, r5, c10, c2, 0 @ write PRRR + mcr p15, 0, r6, c10, c2, 1 @ write NMRR + adr r5, v7_crval + ldmia r5, {r5, r6} + mrc p15, 0, r0, c1, c0, 0 @ read control register + bic r0, r0, r5 @ clear bits them + orr r0, r0, r6 @ set them + mov pc, lr @ return to head.S:__ret +ENDPROC(__v7_setup) + + /* AT + * TFR EV X F I D LR + * .EEE ..EE PUI. .T.T 4RVI ZFRS BLDP WCAM + * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced + * 1 0 110 0011 1.00 .111 1101 < we want + */ + .type v7_crval, #object +v7_crval: + crval clear=0x0120c302, mmuset=0x10c0387d, ucset=0x00c0187c + +__v7_setup_stack: + .space 4 * 11 @ 11 registers + + .type v7_processor_functions, #object +ENTRY(v7_processor_functions) + .word v7_early_abort + .word pabort_ifar + .word cpu_v7_proc_init + .word cpu_v7_proc_fin + .word cpu_v7_reset + .word cpu_v7_do_idle + .word cpu_v7_dcache_clean_area + .word cpu_v7_switch_mm + .word cpu_v7_set_pte_ext + .size v7_processor_functions, . - v7_processor_functions + + .type cpu_arch_name, #object +cpu_arch_name: + .asciz "armv7" + .size cpu_arch_name, . - cpu_arch_name + + .type cpu_elf_name, #object +cpu_elf_name: + .asciz "v7" + .size cpu_elf_name, . - cpu_elf_name + .align + + .section ".proc.info.init", #alloc, #execinstr + + /* + * Match any ARMv7 processor core. + */ + .type __v7_proc_info, #object +__v7_proc_info: + .long 0x000f0000 @ Required ID value + .long 0x000f0000 @ Mask for ID + .long PMD_TYPE_SECT | \ + PMD_SECT_BUFFERABLE | \ + PMD_SECT_CACHEABLE | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + .long PMD_TYPE_SECT | \ + PMD_SECT_XN | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + b __v7_setup + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP + .long cpu_v7_name + .long v7_processor_functions + .long v7wbi_tlb_fns + .long v6_user_fns + .long v7_cache_fns + .size __v7_proc_info, . - __v7_proc_info diff --git a/relocate_kernel.S b/relocate_kernel.S new file mode 100644 index 0000000..61930eb --- /dev/null +++ b/relocate_kernel.S @@ -0,0 +1,79 @@ +/* + * relocate_kernel.S - put the kernel image in place to boot + */ + +#include + + .globl relocate_new_kernel +relocate_new_kernel: + + ldr r0,kexec_indirection_page + ldr r1,kexec_start_address + + +0: /* top, read another word for the indirection page */ + ldr r3, [r0],#4 + + /* Is it a destination page. Put destination address to r4 */ + tst r3,#1,0 + beq 1f + bic r4,r3,#1 + b 0b +1: + /* Is it an indirection page */ + tst r3,#2,0 + beq 1f + bic r0,r3,#2 + b 0b +1: + + /* are we done ? */ + tst r3,#4,0 + beq 1f + b 2f + +1: + /* is it source ? */ + tst r3,#8,0 + beq 0b + bic r3,r3,#8 + mov r6,#1024 +9: + ldr r5,[r3],#4 + str r5,[r4],#4 + subs r6,r6,#1 + bne 9b + b 0b + +2: + /* Jump to relocated kernel */ + mov lr,r1 + mov r0,#0 + ldr r1,kexec_mach_type + ldr r2,kexec_boot_atags + mov pc,lr + + .globl kexec_start_address +kexec_start_address: + .long 0x0 + + .globl kexec_indirection_page +kexec_indirection_page: + .long 0x0 + + .globl kexec_mach_type +kexec_mach_type: + .long 0x0 + + /* phy addr of the atags for the new kernel */ + .globl kexec_boot_atags +kexec_boot_atags: + .long 0x0 + +relocate_new_kernel_end: + + .globl relocate_new_kernel_size +relocate_new_kernel_size: + .long relocate_new_kernel_end - relocate_new_kernel + + diff --git a/sys.c b/sys.c new file mode 100644 index 0000000..611276b --- /dev/null +++ b/sys.c @@ -0,0 +1,101 @@ +/* + * linux/kernel/sys.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include +#include +#include + +extern asmlinkage long (*original_reboot)(int magic1, int magic2, unsigned int cmd, void __user *arg); + +static struct notifier_block dummy_notifier_reboot = { + .notifier_call = NULL, + .next = NULL, + .priority = INT_MAX +}; + +BLOCKING_NOTIFIER_HEAD(notifier_head); + + +void kernel_restart_prepare(char *cmd) +{ + register_reboot_notifier(&dummy_notifier_reboot); + notifier_head.head=dummy_notifier_reboot.next; + unregister_reboot_notifier(&dummy_notifier_reboot); + + blocking_notifier_call_chain(¬ifier_head, SYS_RESTART, cmd); + system_state = SYSTEM_RESTART; +// device_shutdown(); +// sysdev_shutdown(); +} + +/* + * Reboot system call: for obvious reasons only root may call it, + * and even root needs to set up some magic numbers in the registers + * so that some mistake won't make this reboot the whole machine. + * You can also set the meaning of the ctrl-alt-del-key here. + * + * reboot doesn't sync: do that yourself before calling this. + */ +asmlinkage long reboot(int magic1, int magic2, unsigned int cmd, void __user *arg) +{ + int ret; + if(cmd==LINUX_REBOOT_CMD_KEXEC) { + /* We only trust the superuser with rebooting the system. */ + if (!capable(CAP_SYS_BOOT)) + return -EPERM; + + /* For safety, we require "magic" arguments. */ + if (magic1 != LINUX_REBOOT_MAGIC1 || + (magic2 != LINUX_REBOOT_MAGIC2 && + magic2 != LINUX_REBOOT_MAGIC2A && + magic2 != LINUX_REBOOT_MAGIC2B && + magic2 != LINUX_REBOOT_MAGIC2C)) + return -EINVAL; + + lock_kernel(); + ret = kernel_kexec(); + unlock_kernel(); + return ret; + } else { + return original_reboot(magic1, magic2, cmd, arg); + } +} diff --git a/tlb-v7.S b/tlb-v7.S new file mode 100644 index 0000000..12e3bfe --- /dev/null +++ b/tlb-v7.S @@ -0,0 +1,91 @@ +/* + * linux/arch/arm/mm/tlb-v7.S + * + * Copyright (C) 1997-2002 Russell King + * Modified for ARMv7 by Catalin Marinas + * This Edition is maintained by Matthew Veety (aliasxerog) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * ARM architecture version 6 TLB handling functions. + * These assume a split I/D TLB. + */ +#include +#include +#include +#include +#include "proc-macros.S" + +/* + * v7wbi_flush_user_tlb_range(start, end, vma) + * + * Invalidate a range of TLB entries in the specified address space. + * + * - start - start address (may not be aligned) + * - end - end address (exclusive, may not be aligned) + * - vma - vma_struct describing address range + * + * It is assumed that: + * - the "Invalidate single entry" instruction will invalidate + * both the I and the D TLBs on Harvard-style TLBs + */ +ENTRY(v7wbi_flush_user_tlb_range) + vma_vm_mm r3, r2 @ get vma->vm_mm + mmid r3, r3 @ get vm_mm->context.id + dsb + mov r0, r0, lsr #PAGE_SHIFT @ align address + mov r1, r1, lsr #PAGE_SHIFT + asid r3, r3 @ mask ASID + orr r0, r3, r0, lsl #PAGE_SHIFT @ Create initial MVA + mov r1, r1, lsl #PAGE_SHIFT + vma_vm_flags r2, r2 @ get vma->vm_flags +1: + mcr p15, 0, r0, c8, c6, 1 @ TLB invalidate D MVA (was 1) + tst r2, #VM_EXEC @ Executable area ? + mcrne p15, 0, r0, c8, c5, 1 @ TLB invalidate I MVA (was 1) + add r0, r0, #PAGE_SZ + cmp r0, r1 + blo 1b + mov ip, #0 + mcr p15, 0, ip, c7, c5, 6 @ flush BTAC/BTB + dsb + mov pc, lr +ENDPROC(v7wbi_flush_user_tlb_range) + +/* + * v7wbi_flush_kern_tlb_range(start,end) + * + * Invalidate a range of kernel TLB entries + * + * - start - start address (may not be aligned) + * - end - end address (exclusive, may not be aligned) + */ +ENTRY(v7wbi_flush_kern_tlb_range) + dsb + mov r0, r0, lsr #PAGE_SHIFT @ align address + mov r1, r1, lsr #PAGE_SHIFT + mov r0, r0, lsl #PAGE_SHIFT + mov r1, r1, lsl #PAGE_SHIFT +1: + mcr p15, 0, r0, c8, c6, 1 @ TLB invalidate D MVA + mcr p15, 0, r0, c8, c5, 1 @ TLB invalidate I MVA + add r0, r0, #PAGE_SZ + cmp r0, r1 + blo 1b + mov r2, #0 + mcr p15, 0, r2, c7, c5, 6 @ flush BTAC/BTB + dsb + isb + mov pc, lr +ENDPROC(v7wbi_flush_kern_tlb_range) + + .section ".text.init", #alloc, #execinstr + + .type v7wbi_tlb_fns, #object +ENTRY(v7wbi_tlb_fns) + .long v7wbi_flush_user_tlb_range + .long v7wbi_flush_kern_tlb_range + .long v6wbi_tlb_flags + .size v7wbi_tlb_fns, . - v7wbi_tlb_fns -- 2.39.5