Author: Adam <git@apiote.tk>
calculate checksums
LICENSE | 674 ++++++++++++++++++++++++++++++++++++++++ meow_hash_x64_aesni.h | 744 ++++++++++++++++++++++++++++++++++++++++++++ meowsum.c | 186 +++++++++++ mkfile | 2
diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000000000000000000000000000000000000..f288702d2fa16d3cdf0035b15a9fcbc552cd88e7 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/> + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. 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 +them 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 prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. 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. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey 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; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If 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 convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU 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 that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + 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. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +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. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + 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 +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + 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 3 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, see <https://www.gnu.org/licenses/>. + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + <program> Copyright (C) <year> <name of author> + This program 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, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +<https://www.gnu.org/licenses/>. + + The GNU 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 Lesser General +Public License instead of this License. But first, please read +<https://www.gnu.org/licenses/why-not-lgpl.html>. diff --git a/README.asciidoc b/README.asciidoc new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 Binary files /dev/null and b/README.asciidoc differ diff --git a/meow_hash_x64_aesni.h b/meow_hash_x64_aesni.h new file mode 100644 index 0000000000000000000000000000000000000000..966557d45c13fb2023384995fc9bf2c32afedf00 --- /dev/null +++ b/meow_hash_x64_aesni.h @@ -0,0 +1,744 @@ +/* ======================================================================== + + Meow - A Fast Non-cryptographic Hash + (C) Copyright 2018-2019 by Molly Rocket, Inc. (https://mollyrocket.com) + + See https://mollyrocket.com/meowhash for details. + + ======================================================================== + + zlib License + + (C) Copyright 2018-2019 Molly Rocket, Inc. + + This software is provided 'as-is', without any express or implied + warranty. In no event will the authors be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + ======================================================================== + + FAQ + + Q: What is it? + + A: Meow is a 128-bit Level 3 hash taking 128 bytes of seed. It operates + at very high speeds on x64 processors, and potentially other processors + that provide accelerated AES instructions. + + Q: What is it GOOD for? + + A: Quickly hashing any amount of data for comparison purposes such as + block deduplication or change detection. It is fast on all buffer + sizes, and can generally be used anywhere you need fast Level 3 + hashing without worrying about how big or small the inputs tend to be. + + However, substantial speed improvements could be made over Meow + if you either a) know you are always hashing an exact, small number of bytes, + or b) can always supply a small number of bytes in a buffer padded to some + fixed multiple of 16. + + Q: What is it BAD for? + + A: Anything requiring Level 4 or Level 5 security guarantees (see + http://nohatcoder.dk/2019-05-19-1.html#level3). Also, note that + Meow is a new hash and has not had the extensive community + cryptanalysis necessary to ensure that it is not breakable down to + a lower level of hash, so you must do your due diligence in + deciding when and where to use Meow instead of a slower but + more extensively studied existing hash. We have tried to design + it to provide Level 3 security, but the possibility of the hash + being broken in the future always exists. + + Q: Why is it called the "Meow hash"? + + A: It is named after a character in Meow the Infinite + (https://meowtheinfinite.com) + + Q: Who wrote it? + + A: The final Meow Hash was created as a collaboration between + JACOB CHRISTIAN MUNCH-ANDERSEN (https://twitter.com/nohatcoder) and + CASEY MURATORI (https://caseymuratori.com). Casey wrote the original + implementation for use in processing large-footprint assets for the + game 1935 (https://molly1935.com). Jacob was the first to analyze + that implementation and determine the adversarial bit strength, which + was weaker than they would have liked. + + Following that, the two collaborated to figure out how the hash + could be strengthened without reducing Meow's 16 bytes/cycle + maximum theoretical throughput. Jacob created the hash candidates + and Casey did the performance validation. After a long and + exhaustive effort, Jacob found the unaligned aes/add/xor formulation + that forms the current Meow hash core. + + A number of valuable additions to Meow Hash were also contributed + by other great folks along the way: + + JEFF ROBERTS (https://radgametools.com) provided a super slick + way to handle the residual end-of-buffer bytes that dramatically + improved Meow's small hash performance. + + MARTINS MOZEIKO (https://matrins.ninja) ported Meow to ARM and + ANSI-C, and added the proper preprocessor dressing for clean + compilation on a variety of compiler configurations. + + FABIAN GIESEN (https://fgiesen.wordpress.com) analyzed many + performance oddities that came up during development, and + helped get the benchmarking working properly across a number + of platforms. + + ARAS PRANCKEVICIUS (https://aras-p.info) provided the allocation + shim for compilation on Mac OS X. + + ======================================================================== */ + +// +// IMPORTANT(casey): We are currently evaluating this hash construction as +// the final one for Meow Hash. If you find a way to produce collisions +// that should not be possible with a Level 3 hash, find significant performance +// problems, or see any bugs in this version, please be sure to report them +// to the Meow Hash GitHub as soon as possible. We would like to know as +// much as we can about the robustness and performance before committing to +// it as the final construction. +// + +#if !defined(MEOW_HASH_X64_AESNI_H) + +#define MEOW_HASH_VERSION 5 +#define MEOW_HASH_VERSION_NAME "0.5/calico" + +#if !defined(meow_u8) + +#if _MSC_VER +#if !defined(__clang__) +#define INSTRUCTION_REORDER_BARRIER _ReadWriteBarrier() +#else +#endif +#include <intrin.h> +#else +#include <x86intrin.h> +#endif + +#define meow_u8 char unsigned +#define meow_u64 long long unsigned +#define meow_u128 __m128i + +#if __x86_64__ || _M_AMD64 +#define meow_umm long long unsigned +#define MeowU64From(A, I) (_mm_extract_epi64((A), (I))) +#elif __i386__ || _M_IX86 +#define meow_umm int unsigned +#define MeowU64From(A, I) (*(meow_u64 *)&(A)) +#else +#error Cannot determine architecture to use! +#endif + +#define MeowU32From(A, I) (_mm_extract_epi32((A), (I))) +#define MeowHashesAreEqual(A, B) (_mm_movemask_epi8(_mm_cmpeq_epi8((A), (B))) == 0xFFFF) + +#if !defined INSTRUCTION_REORDER_BARRIER +#define INSTRUCTION_REORDER_BARRIER +#endif + +#if !defined MEOW_PAGESIZE +#define MEOW_PAGESIZE 4096 +#endif + +#if !defined MEOW_PREFETCH +#define MEOW_PREFETCH 4096 +#endif + +#if !defined MEOW_PREFETCH_LIMIT +#define MEOW_PREFETCH_LIMIT 0x3ff +#endif + +#endif + +#define prefetcht0(A) _mm_prefetch((char *)(A), _MM_HINT_T0) +#define movdqu(A, B) A = _mm_loadu_si128((__m128i *)(B)) +#define movdqu_mem(A, B) _mm_storeu_si128((__m128i *)(A), B) +#define movq(A, B) A = _mm_set_epi64x(0, B); +#define aesdec(A, B) A = _mm_aesdec_si128(A, B) +#define pshufb(A, B) A = _mm_shuffle_epi8(A, B) +#define pxor(A, B) A = _mm_xor_si128(A, B) +#define paddq(A, B) A = _mm_add_epi64(A, B) +#define pand(A, B) A = _mm_and_si128(A, B) +#define palignr(A, B, i) A = _mm_alignr_epi8(A, B, i) +#define pxor_clear(A, B) A = _mm_setzero_si128(); // NOTE(casey): pxor_clear is a nonsense thing that is only here because compilers don't detect xor(a, a) is clearing a :( + +#define MEOW_MIX_REG(r1, r2, r3, r4, r5, i1, i2, i3, i4) \ +aesdec(r1, r2); \ +INSTRUCTION_REORDER_BARRIER; \ +paddq(r3, i1); \ +pxor(r2, i2); \ +aesdec(r2, r4); \ +INSTRUCTION_REORDER_BARRIER; \ +paddq(r5, i3); \ +pxor(r4, i4); + +#define MEOW_MIX(r1, r2, r3, r4, r5, ptr) \ +MEOW_MIX_REG(r1, r2, r3, r4, r5, _mm_loadu_si128( (__m128i *) ((ptr) + 15) ), _mm_loadu_si128( (__m128i *) ((ptr) + 0) ), _mm_loadu_si128( (__m128i *) ((ptr) + 1) ), _mm_loadu_si128( (__m128i *) ((ptr) + 16) )) + +#define MEOW_SHUFFLE(r1, r2, r3, r4, r5, r6) \ +aesdec(r1, r4); \ +paddq(r2, r5); \ +pxor(r4, r6); \ +aesdec(r4, r2); \ +paddq(r5, r6); \ +pxor(r2, r3) + +#if MEOW_DUMP +struct meow_dump +{ + meow_u128 xmm[8]; + void *Ptr; + char const *Title; +}; +extern "C" meow_dump *MeowDumpTo; +meow_dump *MeowDumpTo; +#define MEOW_DUMP_STATE(T, xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, ptr) \ +if(MeowDumpTo) \ +{ \ + MeowDumpTo->xmm[0] = xmm0; \ + MeowDumpTo->xmm[1] = xmm1; \ + MeowDumpTo->xmm[2] = xmm2; \ + MeowDumpTo->xmm[3] = xmm3; \ + MeowDumpTo->xmm[4] = xmm4; \ + MeowDumpTo->xmm[5] = xmm5; \ + MeowDumpTo->xmm[6] = xmm6; \ + MeowDumpTo->xmm[7] = xmm7; \ + MeowDumpTo->Ptr = ptr; \ + MeowDumpTo->Title = T; \ + ++MeowDumpTo; \ +} +#else +#define MEOW_DUMP_STATE(...) +#endif + +static meow_u8 MeowShiftAdjust[32] = {0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15}; +static meow_u8 MeowMaskLen[32] = {255,255,255,255, 255,255,255,255, 255,255,255,255, 255,255,255,255, 0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0}; + +// NOTE(casey): The default seed is now a "nothing-up-our-sleeves" number for good measure. You may verify that it is just an encoding of Pi. +static meow_u8 MeowDefaultSeed[128] = +{ + 0x32, 0x43, 0xF6, 0xA8, 0x88, 0x5A, 0x30, 0x8D, + 0x31, 0x31, 0x98, 0xA2, 0xE0, 0x37, 0x07, 0x34, + 0x4A, 0x40, 0x93, 0x82, 0x22, 0x99, 0xF3, 0x1D, + 0x00, 0x82, 0xEF, 0xA9, 0x8E, 0xC4, 0xE6, 0xC8, + 0x94, 0x52, 0x82, 0x1E, 0x63, 0x8D, 0x01, 0x37, + 0x7B, 0xE5, 0x46, 0x6C, 0xF3, 0x4E, 0x90, 0xC6, + 0xCC, 0x0A, 0xC2, 0x9B, 0x7C, 0x97, 0xC5, 0x0D, + 0xD3, 0xF8, 0x4D, 0x5B, 0x5B, 0x54, 0x70, 0x91, + 0x79, 0x21, 0x6D, 0x5D, 0x98, 0x97, 0x9F, 0xB1, + 0xBD, 0x13, 0x10, 0xBA, 0x69, 0x8D, 0xFB, 0x5A, + 0xC2, 0xFF, 0xD7, 0x2D, 0xBD, 0x01, 0xAD, 0xFB, + 0x7B, 0x8E, 0x1A, 0xFE, 0xD6, 0xA2, 0x67, 0xE9, + 0x6B, 0xA7, 0xC9, 0x04, 0x5F, 0x12, 0xC7, 0xF9, + 0x92, 0x4A, 0x19, 0x94, 0x7B, 0x39, 0x16, 0xCF, + 0x70, 0x80, 0x1F, 0x2E, 0x28, 0x58, 0xEF, 0xC1, + 0x66, 0x36, 0x92, 0x0D, 0x87, 0x15, 0x74, 0xE6 +}; + +// +// NOTE(casey): Single block version +// + +static meow_u128 +MeowHash(void *Seed128Init, meow_umm Len, void *SourceInit) +{ + meow_u128 xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7; // NOTE(casey): xmm0-xmm7 are the hash accumulation lanes + meow_u128 xmm8, xmm9, xmm10, xmm11, xmm12, xmm13, xmm14, xmm15; // NOTE(casey): xmm8-xmm15 hold values to be appended (residual, length) + + meow_u8 *rax = (meow_u8 *)SourceInit; + meow_u8 *rcx = (meow_u8 *)Seed128Init; + + // + // NOTE(casey): Seed the eight hash registers + // + + movdqu(xmm0, rcx + 0x00); + movdqu(xmm1, rcx + 0x10); + movdqu(xmm2, rcx + 0x20); + movdqu(xmm3, rcx + 0x30); + + movdqu(xmm4, rcx + 0x40); + movdqu(xmm5, rcx + 0x50); + movdqu(xmm6, rcx + 0x60); + movdqu(xmm7, rcx + 0x70); + + MEOW_DUMP_STATE("Seed", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + // + // NOTE(casey): Hash all full 256-byte blocks + // + + meow_umm BlockCount = (Len >> 8); + if(BlockCount > MEOW_PREFETCH_LIMIT) + { + // NOTE(casey): For large input, modern Intel x64's can't hit full speed without prefetching, so we use this loop + while(BlockCount--) + { + prefetcht0(rax + MEOW_PREFETCH + 0x00); + prefetcht0(rax + MEOW_PREFETCH + 0x40); + prefetcht0(rax + MEOW_PREFETCH + 0x80); + prefetcht0(rax + MEOW_PREFETCH + 0xc0); + + MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0x00); + MEOW_MIX(xmm1,xmm5,xmm7,xmm2,xmm3, rax + 0x20); + MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x40); + MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x60); + MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x80); + MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0xa0); + MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0xc0); + MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xe0); + + rax += 0x100; + } + } + else + { + // NOTE(casey): For small input, modern Intel x64's can't hit full speed _with_ prefetching (because of port pressure), so we use this loop. + while(BlockCount--) + { + MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0x00); + MEOW_MIX(xmm1,xmm5,xmm7,xmm2,xmm3, rax + 0x20); + MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x40); + MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x60); + MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x80); + MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0xa0); + MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0xc0); + MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xe0); + + rax += 0x100; + } + } + + MEOW_DUMP_STATE("PostBlocks", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + // + // NOTE(casey): Load any less-than-32-byte residual + // + + pxor_clear(xmm9, xmm9); + pxor_clear(xmm11, xmm11); + + // + // TODO(casey): I need to put more thought into how the end-of-buffer stuff is actually working out here, + // because I _think_ it may be possible to remove the first branch (on Len8) and let the mask zero out the + // result, but it would take a little thought to make sure it couldn't read off the end of the buffer due + // to the & 0xf on the align computation. + // + + // NOTE(casey): First, we have to load the part that is _not_ 16-byte aligned + meow_u8 *Last = (meow_u8 *)SourceInit + (Len & ~0xf); + int unsigned Len8 = (Len & 0xf); + if(Len8) + { + // NOTE(casey): Load the mask early + movdqu(xmm8, &MeowMaskLen[0x10 - Len8]); + + meow_u8 *LastOk = (meow_u8*)((((meow_umm)(((meow_u8 *)SourceInit)+Len - 1)) | (MEOW_PAGESIZE - 1)) - 16); + int Align = (Last > LastOk) ? ((int)(meow_umm)Last) & 0xf : 0; + movdqu(xmm10, &MeowShiftAdjust[Align]); + movdqu(xmm9, Last - Align); + pshufb(xmm9, xmm10); + + // NOTE(jeffr): and off the extra bytes + pand(xmm9, xmm8); + } + + // NOTE(casey): Next, we have to load the part that _is_ 16-byte aligned + if(Len & 0x10) + { + xmm11 = xmm9; + movdqu(xmm9, Last - 0x10); + } + + // + // NOTE(casey): Construct the residual and length injests + // + + xmm8 = xmm9; + xmm10 = xmm9; + palignr(xmm8, xmm11, 15); + palignr(xmm10, xmm11, 1); + + // NOTE(casey): We have room for a 128-bit nonce and a 64-bit none here, but + // the decision was made to leave them zero'd so as not to confuse people + // about hwo to use them or what security implications they had. + pxor_clear(xmm12, xmm12); + pxor_clear(xmm13, xmm13); + pxor_clear(xmm14, xmm14); + movq(xmm15, Len); + palignr(xmm12, xmm15, 15); + palignr(xmm14, xmm15, 1); + + MEOW_DUMP_STATE("Residuals", xmm8, xmm9, xmm10, xmm11, xmm12, xmm13, xmm14, xmm15, 0); + + // NOTE(casey): To maintain the mix-down pattern, we always Meow Mix the less-than-32-byte residual, even if it was empty + MEOW_MIX_REG(xmm0, xmm4, xmm6, xmm1, xmm2, xmm8, xmm9, xmm10, xmm11); + + // NOTE(casey): Append the length, to avoid problems with our 32-byte padding + MEOW_MIX_REG(xmm1, xmm5, xmm7, xmm2, xmm3, xmm12, xmm13, xmm14, xmm15); + + MEOW_DUMP_STATE("PostAppend", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + // + // NOTE(casey): Hash all full 32-byte blocks + // + int unsigned LaneCount = (Len >> 5) & 0x7; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x00); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x20); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x40); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0x60); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0x80); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xa0); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0xc0); --LaneCount; + + // + // NOTE(casey): Mix the eight lanes down to one 128-bit hash + // + + MixDown: + + MEOW_DUMP_STATE("PostLanes", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + MEOW_SHUFFLE(xmm0, xmm1, xmm2, xmm4, xmm5, xmm6); + MEOW_SHUFFLE(xmm1, xmm2, xmm3, xmm5, xmm6, xmm7); + MEOW_SHUFFLE(xmm2, xmm3, xmm4, xmm6, xmm7, xmm0); + MEOW_SHUFFLE(xmm3, xmm4, xmm5, xmm7, xmm0, xmm1); + MEOW_SHUFFLE(xmm4, xmm5, xmm6, xmm0, xmm1, xmm2); + MEOW_SHUFFLE(xmm5, xmm6, xmm7, xmm1, xmm2, xmm3); + MEOW_SHUFFLE(xmm6, xmm7, xmm0, xmm2, xmm3, xmm4); + MEOW_SHUFFLE(xmm7, xmm0, xmm1, xmm3, xmm4, xmm5); + MEOW_SHUFFLE(xmm0, xmm1, xmm2, xmm4, xmm5, xmm6); + MEOW_SHUFFLE(xmm1, xmm2, xmm3, xmm5, xmm6, xmm7); + MEOW_SHUFFLE(xmm2, xmm3, xmm4, xmm6, xmm7, xmm0); + MEOW_SHUFFLE(xmm3, xmm4, xmm5, xmm7, xmm0, xmm1); + + MEOW_DUMP_STATE("PostMix", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + paddq(xmm0, xmm2); + paddq(xmm1, xmm3); + paddq(xmm4, xmm6); + paddq(xmm5, xmm7); + pxor(xmm0, xmm1); + pxor(xmm4, xmm5); + paddq(xmm0, xmm4); + + MEOW_DUMP_STATE("PostFold", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + return(xmm0); +} + +// +// NOTE(casey): Streaming construction +// + +typedef struct meow_state +{ + meow_u128 xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7; + meow_u64 TotalLengthInBytes; + + int unsigned BufferLen; + + meow_u8 Buffer[256]; + meow_u128 Pad[2]; // NOTE(casey): So we know we can over-read Buffer as necessary +} meow_state; + +static void +MeowBegin(meow_state *State, void *Seed128) +{ + meow_u8 *rcx = (meow_u8 *)Seed128; + + movdqu(State->xmm0, rcx + 0x00); + movdqu(State->xmm1, rcx + 0x10); + movdqu(State->xmm2, rcx + 0x20); + movdqu(State->xmm3, rcx + 0x30); + movdqu(State->xmm4, rcx + 0x40); + movdqu(State->xmm5, rcx + 0x50); + movdqu(State->xmm6, rcx + 0x60); + movdqu(State->xmm7, rcx + 0x70); + + MEOW_DUMP_STATE("Seed", State->xmm0, State->xmm1, State->xmm2, State->xmm3, State->xmm4, State->xmm5, State->xmm6, State->xmm7, 0); + + State->BufferLen = 0; + State->TotalLengthInBytes = 0; +} + +static void +MeowAbsorbBlocks(meow_state *State, meow_umm BlockCount, meow_u8 *rax) +{ + meow_u128 xmm0 = State->xmm0; + meow_u128 xmm1 = State->xmm1; + meow_u128 xmm2 = State->xmm2; + meow_u128 xmm3 = State->xmm3; + meow_u128 xmm4 = State->xmm4; + meow_u128 xmm5 = State->xmm5; + meow_u128 xmm6 = State->xmm6; + meow_u128 xmm7 = State->xmm7; + + if(BlockCount > MEOW_PREFETCH_LIMIT) + { + while(BlockCount--) + { + prefetcht0(rax + MEOW_PREFETCH + 0x00); + prefetcht0(rax + MEOW_PREFETCH + 0x40); + prefetcht0(rax + MEOW_PREFETCH + 0x80); + prefetcht0(rax + MEOW_PREFETCH + 0xc0); + + MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0x00); + MEOW_MIX(xmm1,xmm5,xmm7,xmm2,xmm3, rax + 0x20); + MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x40); + MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x60); + MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x80); + MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0xa0); + MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0xc0); + MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xe0); + + rax += 0x100; + } + } + else + { + while(BlockCount--) + { + MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0x00); + MEOW_MIX(xmm1,xmm5,xmm7,xmm2,xmm3, rax + 0x20); + MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x40); + MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x60); + MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x80); + MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0xa0); + MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0xc0); + MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xe0); + + rax += 0x100; + } + } + + State->xmm0 = xmm0; + State->xmm1 = xmm1; + State->xmm2 = xmm2; + State->xmm3 = xmm3; + State->xmm4 = xmm4; + State->xmm5 = xmm5; + State->xmm6 = xmm6; + State->xmm7 = xmm7; +} + +static void +MeowAbsorb(meow_state *State, meow_umm Len, void *SourceInit) +{ + State->TotalLengthInBytes += Len; + meow_u8 *Source = (meow_u8 *)SourceInit; + + // NOTE(casey): Handle any buffered residual + if(State->BufferLen) + { + int unsigned Fill = (sizeof(State->Buffer) - State->BufferLen); + if(Fill > Len) + { + Fill = (int unsigned)Len; + } + + Len -= Fill; + while(Fill--) + { + State->Buffer[State->BufferLen++] = *Source++; + } + + if(State->BufferLen == sizeof(State->Buffer)) + { + MeowAbsorbBlocks(State, 1, State->Buffer); + State->BufferLen = 0; + } + } + + // NOTE(casey): Handle any full blocks + meow_u64 BlockCount = (Len >> 8); + meow_u64 Advance = (BlockCount << 8); + MeowAbsorbBlocks(State, BlockCount, Source); + + Len -= Advance; + Source += Advance; + + // NOTE(casey): Store residual + while(Len--) + { + State->Buffer[State->BufferLen++] = *Source++; + } +} + +static meow_u128 +MeowEnd(meow_state *State, meow_u8 *Store128) +{ + meow_umm Len = State->TotalLengthInBytes; + + meow_u128 xmm0 = State->xmm0; + meow_u128 xmm1 = State->xmm1; + meow_u128 xmm2 = State->xmm2; + meow_u128 xmm3 = State->xmm3; + meow_u128 xmm4 = State->xmm4; + meow_u128 xmm5 = State->xmm5; + meow_u128 xmm6 = State->xmm6; + meow_u128 xmm7 = State->xmm7; + + meow_u128 xmm8, xmm9, xmm10, xmm11, xmm12, xmm13, xmm14, xmm15; + + meow_u8 *rax = State->Buffer; + + pxor_clear(xmm9, xmm9); + pxor_clear(xmm11, xmm11); + + meow_u8 *Last = (meow_u8 *)rax + (Len & 0xf0); + int unsigned Len8 = (Len & 0xf); + if(Len8) + { + movdqu(xmm8, &MeowMaskLen[0x10 - Len8]); + movdqu(xmm9, Last); + pand(xmm9, xmm8); + } + + if(Len & 0x10) + { + xmm11 = xmm9; + movdqu(xmm9, Last - 0x10); + } + + xmm8 = xmm9; + xmm10 = xmm9; + palignr(xmm8, xmm11, 15); + palignr(xmm10, xmm11, 1); + + pxor_clear(xmm12, xmm12); + pxor_clear(xmm13, xmm13); + pxor_clear(xmm14, xmm14); + movq(xmm15, Len); + palignr(xmm12, xmm15, 15); + palignr(xmm14, xmm15, 1); + + MEOW_DUMP_STATE("PostBlocks", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + MEOW_DUMP_STATE("Residuals", xmm8, xmm9, xmm10, xmm11, xmm12, xmm13, xmm14, xmm15, 0); + + // NOTE(casey): To maintain the mix-down pattern, we always Meow Mix the less-than-32-byte residual, even if it was empty + MEOW_MIX_REG(xmm0, xmm4, xmm6, xmm1, xmm2, xmm8, xmm9, xmm10, xmm11); + + // NOTE(casey): Append the length, to avoid problems with our 32-byte padding + MEOW_MIX_REG(xmm1, xmm5, xmm7, xmm2, xmm3, xmm12, xmm13, xmm14, xmm15); + + MEOW_DUMP_STATE("PostAppend", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + // + // NOTE(casey): Hash all full 32-byte blocks + // + int unsigned LaneCount = (Len >> 5) & 0x7; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm2,xmm6,xmm0,xmm3,xmm4, rax + 0x00); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm3,xmm7,xmm1,xmm4,xmm5, rax + 0x20); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm4,xmm0,xmm2,xmm5,xmm6, rax + 0x40); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm5,xmm1,xmm3,xmm6,xmm7, rax + 0x60); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm6,xmm2,xmm4,xmm7,xmm0, rax + 0x80); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm7,xmm3,xmm5,xmm0,xmm1, rax + 0xa0); --LaneCount; + if(LaneCount == 0) goto MixDown; MEOW_MIX(xmm0,xmm4,xmm6,xmm1,xmm2, rax + 0xc0); --LaneCount; + + // + // NOTE(casey): Mix the eight lanes down to one 128-bit hash + // + + MixDown: + + MEOW_DUMP_STATE("PostLanes", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + MEOW_SHUFFLE(xmm0, xmm1, xmm2, xmm4, xmm5, xmm6); + MEOW_SHUFFLE(xmm1, xmm2, xmm3, xmm5, xmm6, xmm7); + MEOW_SHUFFLE(xmm2, xmm3, xmm4, xmm6, xmm7, xmm0); + MEOW_SHUFFLE(xmm3, xmm4, xmm5, xmm7, xmm0, xmm1); + MEOW_SHUFFLE(xmm4, xmm5, xmm6, xmm0, xmm1, xmm2); + MEOW_SHUFFLE(xmm5, xmm6, xmm7, xmm1, xmm2, xmm3); + MEOW_SHUFFLE(xmm6, xmm7, xmm0, xmm2, xmm3, xmm4); + MEOW_SHUFFLE(xmm7, xmm0, xmm1, xmm3, xmm4, xmm5); + MEOW_SHUFFLE(xmm0, xmm1, xmm2, xmm4, xmm5, xmm6); + MEOW_SHUFFLE(xmm1, xmm2, xmm3, xmm5, xmm6, xmm7); + MEOW_SHUFFLE(xmm2, xmm3, xmm4, xmm6, xmm7, xmm0); + MEOW_SHUFFLE(xmm3, xmm4, xmm5, xmm7, xmm0, xmm1); + + MEOW_DUMP_STATE("PostMix", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + if(Store128) + { + movdqu_mem(Store128 + 0x00, xmm0); + movdqu_mem(Store128 + 0x10, xmm1); + movdqu_mem(Store128 + 0x20, xmm2); + movdqu_mem(Store128 + 0x30, xmm3); + movdqu_mem(Store128 + 0x40, xmm4); + movdqu_mem(Store128 + 0x50, xmm5); + movdqu_mem(Store128 + 0x60, xmm6); + movdqu_mem(Store128 + 0x70, xmm7); + } + + paddq(xmm0, xmm2); + paddq(xmm1, xmm3); + paddq(xmm4, xmm6); + paddq(xmm5, xmm7); + pxor(xmm0, xmm1); + pxor(xmm4, xmm5); + paddq(xmm0, xmm4); + + MEOW_DUMP_STATE("PostFold", xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, 0); + + return(xmm0); +} + +#undef INSTRUCTION_REORDER_BARRIER +#undef prefetcht0 +#undef movdqu +#undef movdqu_mem +#undef movq +#undef aesdec +#undef pshufb +#undef pxor +#undef paddq +#undef pand +#undef palignr +#undef pxor_clear +#undef MEOW_MIX +#undef MEOW_MIX_REG +#undef MEOW_SHUFFLE +#undef MEOW_DUMP_STATE + +// +// NOTE(casey): If you need to create your own seed from non-random data, you can use MeowExpandSeed +// to create a seed which you then store for repeated use. It is _expensive_ to generate the seed, +// so you do not want to do this every time you hash. You _only_ want to do it when you actually +// need to create a new seed. +// + +static void +MeowExpandSeed(meow_umm InputLen, void *Input, meow_u8 *SeedResult) +{ + meow_state State; + meow_u64 LengthTab = (meow_u64)InputLen; // NOTE(casey): We need to always injest 8-byte lengths exactly, even on 32-bit builds, to ensure identical results + meow_umm InjestCount = (256 / InputLen) + 2; + + MeowBegin(&State, MeowDefaultSeed); + MeowAbsorb(&State, sizeof(LengthTab), &LengthTab); + while(InjestCount--) + { + MeowAbsorb(&State, InputLen, Input); + } + MeowEnd(&State, SeedResult); +} + +#define MEOW_HASH_X64_AESNI_H +#endif diff --git a/meowsum.c b/meowsum.c new file mode 100644 index 0000000000000000000000000000000000000000..0bd1788390e02a54b7f4f3ddb6b00fd3dd934f03 --- /dev/null +++ b/meowsum.c @@ -0,0 +1,186 @@ +#include "meow_hash_x64_aesni.h" + +#define BUFFER_SIZE 8192 +#define HASH_SIZE 128 +#define MODE_SUM 0 +#define MODE_CHECK 1 + +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +void print_usage() { + printf("usage: meowsum [OPTION]... [FILE]...\n"); + // -c -> read sums from FILE and check them + // -q -> when -c, only return status; do not print OK, FAIL(, MISSING) + // -e -> when -c, fail for missing files + // -s (32|64|*128) -> set hash size +} + +void parse_args(int argc, char *argv[], bool *quiet, bool *strict_error, + int *hash_size, int *first_file_index, int *mode) { + bool expecting_num = false; + + for (int i = 1; i < argc; ++i) { + if (expecting_num) { + *hash_size = atoi(argv[i]); + expecting_num = false; + continue; + } + if (argv[i][0] != '-') { + *first_file_index = i; + break; + } + if (strcmp(argv[i], "--") == 0) { + *first_file_index = i + 1; + break; + } + if (argv[i][0] == '-') { + ssize_t length = strlen(argv[i]); + for (int j = 1; j < length; ++j) { + if (expecting_num) { + *hash_size = atoi(argv[i] + j); + expecting_num = false; + break; + } + switch (argv[i][j]) { + case 'c': + *mode = MODE_CHECK; + break; + case 'q': + *quiet = true; + break; + case 'e': + *strict_error = true; + break; + case 's': + expecting_num = true; + } + } + } + } +} + +bool calculate_checksum(char *path, char *buffer, meow_u128 *hash, + struct stat *stat) { + int fd, r; + meow_state state; + ssize_t read_bytes; + + if (strcmp(path, "-") == 0) { + fd = 0; + } + fd = open(path, 0); + if (fd == -1) { + perror("error: "); + printf("error opening file %s\n", path); + return false; + } + + r = fstat(fd, stat); + if (r == -1) { + perror("error: "); + printf("error stating file %s\n", path); + return false; + } + + MeowBegin(&state, MeowDefaultSeed); + while (true) { + read_bytes = read(fd, buffer, 8192); + if (read_bytes == -1) { + perror("error: "); + printf("error reading file %s\n", path); + close(fd); + return false; + } + if (read_bytes == 0) { + break; + } + MeowAbsorb(&state, read_bytes, buffer); + } + *hash = MeowEnd(&state, NULL); + + if (fd != 0) { + close(fd); + } + return true; +} + +bool sum_files(char *argv[], int start, int argc, char *buffer, int hash_size) { + bool r; + int64_t v64val[2]; + struct stat stat; + + for (int i = start; i < argc; ++i) { + meow_u128 hash; + r = calculate_checksum(argv[i], buffer, &hash, &stat); + if (!r) { + printf("error while calculating %s\n", argv[i]); + return false; + } + + memcpy(v64val, &hash, sizeof(v64val)); + switch (hash_size) { + case 32: + printf("%x %ld %s\n", MeowU32From(hash, 0), stat.st_size, argv[i]); + break; + case 64: + printf("%llx %ld %s\n", MeowU64From(hash, 0), stat.st_size, argv[i]); + break; + case 128: + printf("%lx%lx %ld %s\n", v64val[1], v64val[0], stat.st_size, argv[i]); + break; + } + } + + return true; +} + +bool check_files(char *args[], int start, int argc, int hash_size, bool quiet, + bool stric_errors) { + // todo +} + +int main(int argc, char *argv[]) { + int hash_size = HASH_SIZE, mode = MODE_SUM, first_file_index = -1; + char *buffer = malloc(sizeof(char) * 8192); + bool quiet = false, strict_error = false; + int exit_status = 0; + + if (argc == 1) { + print_usage(); + return 1; + } + + parse_args(argc, argv, &quiet, &strict_error, &hash_size, &first_file_index, + &mode); + + if (hash_size != 32 && hash_size != 64 && hash_size != 128) { + fprintf(stderr, "unknown hash size %d\n", hash_size); + return 1; + } + + if (first_file_index == -1) { + print_usage(); + return 1; + } + + if (mode == MODE_SUM) { + sum_files(argv, first_file_index, argc, buffer, hash_size); + } + if (mode == MODE_CHECK) { + bool check_result = check_files(argv, first_file_index, argc, hash_size, + quiet, strict_error); + if (!check_result) { + exit_status = 1; + } + } + + free(buffer); + return exit_status; +} diff --git a/mkfile b/mkfile new file mode 100644 index 0000000000000000000000000000000000000000..917ebd282012976672706707df5a47583f650f0b --- /dev/null +++ b/mkfile @@ -0,0 +1,2 @@ +meowsum: meowsum.c + clang -O3 -mavx -maes -pedantic -Wall -o meowsum meowsum.c