����JFIFXX�����    $.' ",#(7),01444'9=82<.342  2!!22222222222222222222222222222222222222222222222222����"��4�� ���,�PG"Z_�4�˷����kjز�Z�,F+��_z�,�© �����zh6�٨�ic�fu���#ډb���_�N�?��wQ���5-�~�I���8����TK<5o�Iv-�����k�_U_�����~b�M��d����Ӝ�U�Hh��?]��E�w��Q���k�{��_}qFW7HTՑ��Y��F�?_�'ϔ��_�Ջt��=||I ��6�έ"�����D���/[�k�9���Y�8ds|\���Ҿp6�Ҵ���]��.����6�z<�v��@]�i%��$j��~�g��J>��no����pM[me�i$[����s�o�ᘨ�˸ nɜG-�ĨU�ycP�3.DB�li�;��hj���x7Z^�N�h������N3u{�:j�x�힞��#M&��jL P@_���� P��&��o8������9�����@Sz6�t7#O�ߋ �s}Yf�T���lmr����Z)'N��k�۞p����w\�Tȯ?�8`�O��i{wﭹW�[�r�� ��Q4F�׊���3m&L�=��h3����z~��#�\�l :�F,j@�� ʱ�wQT����8�"kJO���6�֚l����}���R�>ډK���]��y����&����p�}b��;N�1�m�r$�|��7�>e�@B�TM*-iH��g�D�)� E�m�|�ؘbҗ�a��Ҿ����t4���o���G��*oCN�rP���Q��@z,|?W[0�����:�n,jWiE��W��$~/�hp\��?��{(�0���+�Y8rΟ�+����>S-S����VN;�}�s?.����� w�9��˟<���Mq4�Wv'��{)0�1mB��V����W[�����8�/<� �%���wT^�5���b��)iM� pg�N�&ݝ��VO~�q���u���9� ����!��J27����$O-���! �:�%H��� ـ����y�ΠM=t{!S�� oK8������t<����è:a������[�����ա�H���~��w��Qz`�po�^ ����Q��n� �,uu�C�$ ^���,������8�#��:�6��e�|~���!�3�3.�\0��q��o�4`.|� ����y�Q�`~;�d�ׯ,��O�Zw�������`73�v�܋�<���Ȏ�� ـ4k��5�K�a�u�=9Yd��$>x�A�&�� j0� ���vF��� Y�|�y��� ~�6�@c��1vOp�Ig����4��l�OD���L����� R���c���j�_�uX6��3?nk��Wy�f;^*B� ��@�~a�`��Eu������+���6�L��.ü>��}y���}_�O�6�͐�:�YrG�X��kG�����l^w���~㒶sy��Iu�!� W ��X��N�7BV��O��!X�2����wvG�R�f�T#�����t�/?���%8�^�W�aT��G�cL�M���I��(J����1~�8�?aT ���]����AS�E��(��*E}� 2��#I/�׍qz��^t�̔���b�Yz4x���t�){ OH��+(E��A&�N�������XT��o��"�XC��'���)}�J�z�p� ��~5�}�^����+�6����w��c��Q�|Lp�d�H��}�(�.|����k��c4^�"�����Z?ȕ ��a<�L�!039C� �Eu�C�F�Ew�ç ;�n?�*o���B�8�bʝ���'#Rqf���M}7����]����s2tcS{�\icTx;�\��7K���P���ʇ Z O-��~��c>"��?�������P��E��O�8��@�8��G��Q�g�a�Վ���󁶠�䧘��_%#r�>�1�z�a��eb��qcPѵ��n���#L��� =��׀t� L�7�`��V���A{�C:�g���e@�w1 Xp3�c3�ġ����p��M"'-�@n4���fG��B3�DJ�8[Jo�ߐ���gK)ƛ��$���� ���8�3�����+���� �����6�ʻ���� ���S�kI�*KZlT _`���?��K����QK�d����B`�s}�>���`��*�>��,*@J�d�oF*����弝��O}�k��s��]��y�ߘ��c1G�V���<=�7��7����6�q�PT��tXԀ�!9*4�4Tހ3XΛex�46���Y��D ����� �BdemDa����\�_l,��G�/���֌7���Y�](�xTt^%�GE�����4�}bT���ڹ�����;Y)���B�Q��u��>J/J �⮶.�XԄ��j�ݳ�+E��d ��r�5�_D�1 ��o�� �B�x�΢�#���<��W�����8���R6�@g�M�.��� dr�D��>(otU��@x=��~v���2� ӣ�d�oBd��3�eO�6�㣷�����ݜ6��6Y��Qz`��S��{���\P�~z m5{J/L��1������<�e�ͅPu�b�]�ϔ���'������f�b� Zpw��c`"��i���BD@:)ִ�:�]��hv�E�w���T�l��P���"Ju�}��وV J��G6��. J/�Qgl߭�e�����@�z�Zev2u�)]կ�����7x���s�M�-<ɯ�c��r�v�����@��$�ޮ}lk���a���'����>x��O\�ZFu>�����ck#��&:��`�$�ai�>2Δ����l���oF[h��lE�ܺ�Πk:)���`�� $[6�����9�����kOw�\|���8}������ބ:��񶐕��I�A1/�=�2[�,�!��.}gN#�u����b��� ~��݊��}34q����d�E��Lc��$��"�[q�U�硬g^��%B �z���r�pJ�ru%v\h1Y�ne`ǥ:g���pQM~�^�Xi� ��`S�:V29.�P���V�?B�k�� AEvw%�_�9C�Q����wKekPؠ�\�;Io d�{ ߞo�c1eP����\� `����E=���@K<�Y���eڼ�J���w����{av�F�'�M�@/J��+9p���|]�����Iw &`��8���&M�hg��[�{��Xj��%��Ӓ�$��(����ʹN���<>�I���RY���K2�NPlL�ɀ)��&e����B+ь����( � �JTx���_?EZ� }@ 6�U���뙢ط�z��dWI�n` D����噥�[��uV��"�G&Ú����2g�}&m��?ċ�"����Om#��������� ��{�ON��"S�X��Ne��ysQ���@Fn��Vg���dX�~nj�]J�<�K]:��FW��b�������62�=��5f����JKw��bf�X�55��~J �%^����:�-�QIE��P��v�nZum� z � ~ə ���� ���ة����;�f��\v���g�8�1��f24;�V���ǔ�)����9���1\��c��v�/'Ƞ�w�������$�4�R-��t���� e�6�/�ġ �̕Ecy�J���u�B���<�W�ַ~�w[B1L۲�-JS΂�{���΃������A��20�c#��@ 0!1@AP"#2Q`$3V�%45a6�FRUq��� ����^7ׅ,$n�������+��F�`��2X'��0vM��p�L=������5��8������u�p~���.�`r�����\���O��,ư�0oS ��_�M�����l���4�kv\JSd���x���SW�<��Ae�IX����������$I���w�:S���y���›R��9�Q[���,�5�;�@]�%���u�@ *ro�lbI �� ��+���%m:�͇ZV�����u�̉����θau<�fc�.����{�4Ա� �Q����*�Sm��8\ujqs]{kN���)qO�y�_*dJ�b�7���yQqI&9�ԌK!�M}�R�;������S�T���1���i[U�ɵz�]��U)V�S6���3$K{�ߊ<�(� E]Զ[ǼENg�����'�\?#)Dkf��J���o��v���'�%ƞ�&K�u�!��b�35LX�Ϸ��63$K�a�;�9>,R��W��3�3� d�JeTYE.Mϧ��-�o�j3+y��y^�c�������VO�9NV\nd�1 ��!͕_)a�v;����թ�M�lWR1��)El��P;��yوÏ�u 3�k�5Pr6<�⒲l�!˞*��u־�n�!�l:����UNW ��%��Chx8vL'��X�@��*��)���̮��ˍ��� ���D-M�+J�U�kvK����+�x8��cY������?�Ԡ��~3mo��|�u@[XeY�C�\Kp�x8�oC�C�&����N�~3-H���� ��MX�s�u<`���~"WL��$8ξ��3���a�)|:@�m�\���^�`�@ҷ)�5p+��6���p�%i)P M���ngc�����#0Aruz���RL+xSS?���ʮ}()#�t��mˇ!��0}}y����<�e� �-ή�Ԩ��X������ MF���ԙ~l L.3���}�V뽺�v�����멬��Nl�)�2����^�Iq��a��M��qG��T�����c3#������3U�Ǎ���}��לS�|qa��ڃ�+���-��2�f����/��bz��ڐ�� �ݼ[2�ç����k�X�2�* �Z�d���J�G����M*9W���s{��w���T��x��y,�in�O�v��]���n����P�$�JB@=4�OTI�n��e�22a\����q�d���%�$��(���:���: /*�K[PR�fr\nڙdN���F�n�$�4�[�� U�zƶ����� �mʋ���,�ao�u 3�z� �x��Kn����\[��VFmbE;�_U��&V�Gg�]L�۪&#n%�$ɯ�dG���D�TI=�%+AB�Ru#��b4�1�»x�cs�YzڙJG��f��Il��d�eF'T� iA��T���uC�$����Y��H?����[!G`}���ͪ� �纤Hv\������j�Ex�K���!���OiƸ�Yj�+u-<���'q����uN�*�r\��+�]���<�wOZ.fp�ێ��,-*)V?j-kÊ#�`�r��dV����(�ݽBk�����G�ƛk�QmUڗe��Z���f}|����8�8��a���i��3'J�����~G_�^���d�8w������ R�`(�~�.��u���l�s+g�bv���W���lGc}��u���afE~1�Ue������Z�0�8�=e�� f@/�jqEKQQ�J��oN��J���W5~M>$6�Lt�;$ʳ{���^��6�{����v6���ķܰg�V�cnn �~z�x�«�,2�u�?cE+Ș�H؎�%�Za�)���X>uW�Tz�Nyo����s���FQƤ��$��*�&�LLXL)�1�" L��eO��ɟ�9=���:t��Z���c��Ž���Y?�ӭV�wv�~,Y��r�ۗ�|�y��GaF�����C�����.�+� ���v1���fήJ�����]�S��T��B��n5sW}y�$��~z�'�c ��8 ��� ,! �p��VN�S��N�N�q��y8z˱�A��4��*��'������2n<�s���^ǧ˭P�Jޮɏ�U�G�L�J�*#��<�V��t7�8����TĜ>��i}K%,���)[��z�21z ?�N�i�n1?T�I�R#��m-�����������������1����lA�`��fT5+��ܐ�c�q՝��ʐ��,���3�f2U�եmab��#ŠdQ�y>\��)�SLY����w#��.���ʑ�f��� ,"+�w�~�N�'�c�O�3F�������N<���)j��&��,-� �љ���֊�_�zS���TǦ����w�>��?�������n��U仆�V���e�����0���$�C�d���rP �m�׈e�Xm�Vu� �L��.�bֹ��� �[Դaզ���*��\y�8�Է:�Ez\�0�Kq�C b��̘��cө���Q��=0Y��s�N��S.���3.���O�o:���#���v7�[#߫ ��5�܎�L���Er4���9n��COWlG�^��0k�%<���ZB���aB_���������'=��{i�v�l�$�uC���mƎҝ{�c㱼�y]���W�i ��ߧc��m�H� m�"�"�����;Y�ߝ�Z�Ǔ�����:S#��|}�y�,/k�Ld� TA�(�AI$+I3��;Y*���Z��}|��ӧO��d�v��..#:n��f>�>���ȶI�TX��� 8��y����"d�R�|�)0���=���n4��6ⲑ�+��r<�O�܂~zh�z����7ܓ�HH�Ga롏���nCo�>������a ���~]���R���̲c?�6(�q�;5%� |�uj�~z8R=X��I�V=�|{v�Gj\gc��q����z�؋%M�ߍ����1y��#��@f^���^�>N�����#x#۹��6�Y~�?�dfPO��{��P�4��V��u1E1J �*|���%���JN��`eWu�zk M6���q t[�� ��g�G���v��WIG��u_ft����5�j�"�Y�:T��ɐ���*�;� e5���4����q$C��2d�}���� _S�L#m�Yp��O�.�C�;��c����Hi#֩%+) �Ӎ��ƲV���SYź��g |���tj��3�8���r|���V��1#;.SQ�A[���S������#���`n�+���$��$I �P\[�@�s��(�ED�z���P��])8�G#��0B��[ى��X�II�q<��9�~[Z멜�Z�⊔IWU&A>�P~�#��dp<�?����7���c��'~���5 ��+$���lx@�M�dm��n<=e�dyX��?{�|Aef ,|n3�<~z�ƃ�uۧ�����P��Y,�ӥQ�*g�#먙R�\���;T��i,��[9Qi歉����c>]9�� ��"�c��P�� �Md?٥��If�ت�u��k��/����F��9�c*9��Ǎ:�ØF���z�n*�@|I�ށ9����N3{'��[�'ͬ�Ҳ4��#}��!�V� Fu��,�,mTIk���v C�7v���B�6k�T9��1�*l� '~��ƞF��lU��'�M ����][ΩũJ_�{�i�I�n��$���L�� j��O�dx�����kza۪��#�E��Cl����x˘�o�����V���ɞ�ljr��)�/,�߬h�L��#��^��L�ф�,íMƁe�̩�NB�L�����iL����q�}��(��q��6IçJ$�W�E$��:������=#����(�K�B����zђ <��K(�N�۫K�w��^O{!����)�H���>x�������lx�?>Պ�+�>�W���,Ly!_�D���Ō�l���Q�!�[ �S����J��1��Ɛ�Y}��b,+�Lo�x�ɓ)����=�y�oh�@�꥟/��I��ѭ=��P�y9��� �ۍYӘ�e+�p�Jnϱ?V\SO%�(�t� ���=?MR�[Ș�����d�/ ��n�l��B�7j� ��!�;ӥ�/�[-���A�>�dN�sLj ��,ɪv��=1c�.SQ�O3�U���ƀ�ܽ�E����������̻��9G�ϷD�7(�}��Ävӌ\�y�_0[w ���<΍>����a_��[0+�L��F.�޺��f�>oN�T����q;���y\��bՃ��y�jH�<|q-eɏ�_?_9+P���Hp$�����[ux�K w�Mw��N�ی'$Y2�=��q���KB��P��~������Yul:�[<����F1�2�O���5=d����]Y�sw:���Ϯ���E��j,_Q��X��z`H1,#II ��d�wr��P˂@�ZJV����y$�\y�{}��^~���[:N����ߌ�U�������O��d�����ؾe��${p>G��3c���Ė�lʌ�� ת��[��`ϱ�-W����dg�I��ig2��� ��}s ��ؤ(%#sS@���~���3�X�nRG�~\jc3�v��ӍL��M[JB�T��s3}��j�Nʖ��W����;7��ç?=X�F=-�=����q�ߚ���#���='�c��7���ڑW�I(O+=:uxq�������������e2�zi+�kuG�R��������0�&e�n���iT^J����~\jy���p'dtG��s����O��3����9* �b#Ɋ�� p������[Bws�T�>d4�ۧs���nv�n���U���_�~,�v����ƜJ1��s�� �QIz��)�(lv8M���U=�;����56��G���s#�K���MP�=��LvyGd��}�VwWBF�'�à �?MH�U�g2�� ����!�p�7Q��j��ڴ����=��j�u��� Jn�A s���uM������e��Ɔ�Ҕ�!)'��8Ϣ�ٔ��ޝ(��Vp���צ֖d=�IC�J�Ǡ{q������kԭ�߸���i��@K����u�|�p=..�*+����x�����z[Aqġ#s2a�Ɗ���RR�)*HRsi�~�a &f��M��P����-K�L@��Z��Xy�'x�{}��Zm+���:�)�) IJ�-i�u���� ���ܒH��'�L(7�y�GӜq���� j��� 6ߌg1�g�o���,kر���tY�?W,���p���e���f�OQS��!K�۟cҒA�|ս�j�>��=⬒��˧L[�� �߿2JaB~R��u�:��Q�] �0H~���]�7��Ƽ�I���(}��cq '�ήET���q�?f�ab���ӥvr� �)o��-Q��_'����ᴎo��K������;��V���o��%���~OK ����*��b�f:���-ťIR��`B�5!RB@���ï�� �u �̯e\�_U�_������� g�ES��3�������QT��a����x����U<~�c?�*�#]�MW,[8O�a�x��]�1bC|踤�P��lw5V%�)�{t�<��d��5���0i�XSU��m:��Z�┵�i�"��1�^B�-��P�hJ��&)O��*�D��c�W��vM��)����}���P��ܗ-q����\mmζZ-l@�}��a��E�6��F�@��&Sg@���ݚ�M����� ȹ 4����#p�\H����dYDo�H���"��\��..R�B�H�z_�/5˘����6��KhJR��P�mƶi�m���3�,#c�co��q�a)*Pt����R�m�k�7x�D�E�\Y�閣_X�<���~�)���c[[�BP����6�Yq���S��0����%_����;��Àv�~�| VS؇ ��'O0��F0��\���U�-�d@�����7�SJ*z��3n��y��P����O���������m�~�P�3|Y��ʉr#�C�<�G~�.,! ���bqx���h~0=��!ǫ�jy����l�O,�[B��~��|9��ٱ����Xly�#�i�B��g%�S��������tˋ���e���ې��\[d�t)��.+u�|1 ������#�~Oj����hS�%��i.�~X���I�H�m��0n���c�1uE�q��cF�RF�o���7� �O�ꮧ� ���ۛ{��ʛi5�rw?׌#Qn�TW��~?y$��m\�\o����%W� ?=>S�N@�� �Ʈ���R����N�)�r"C�:��:����� �����#��qb��Y�. �6[��2K����2u�Ǧ�HYR��Q�MV��� �G�$��Q+.>�����nNH��q�^��� ����q��mM��V��D�+�-�#*�U�̒ ���p욳��u:�������IB���m���PV@O���r[b= �� ��1U�E��_Nm�yKbN�O���U�}�the�`�|6֮P>�\2�P�V���I�D�i�P�O;�9�r�mAHG�W�S]��J*�_�G��+kP�2����Ka�Z���H�'K�x�W�MZ%�O�YD�Rc+o��?�q��Ghm��d�S�oh�\�D�|:W������UA�Qc yT�q������~^�H��/��#p�CZ���T�I�1�ӏT����4��"�ČZ�����}��`w�#�*,ʹ�� ��0�i��課�Om�*�da��^gJ݅{���l�e9uF#T�ֲ��̲�ٞC"�q���ߍ ոޑ�o#�XZTp����@ o�8��(jd��xw�]�,f���`~�|,s��^����f�1���t��|��m�򸄭/ctr��5s��7�9Q�4�H1꠲BB@l9@���C�����+�wp�xu�£Yc�9��?`@#�o�mH�s2��)�=��2�.�l����jg�9$�Y�S�%*L������R�Y������7Z���,*=�䷘$�������arm�o�ϰ���UW.|�r�uf����IGw�t����Zwo��~5 ��YյhO+=8fF�)�W�7�L9lM�̘·Y���֘YLf�큹�pRF���99.A �"wz��=E\Z���'a� 2��Ǚ�#;�'}�G���*��l��^"q��+2FQ� hj��kŦ��${���ޮ-�T�٭cf�|�3#~�RJ����t��$b�(R��(����r���dx� >U b�&9,>���%E\� Ά�e�$��'�q't��*�א���ެ�b��-|d���SB�O�O��$�R+�H�)�܎�K��1m`;�J�2�Y~9��O�g8=vqD`K[�F)k�[���1m޼c��n���]s�k�z$@��)!I �x՝"v��9=�ZA=`Ɠi �:�E��)`7��vI��}d�YI�_ �o�:ob���o ���3Q��&D&�2=�� �Ά��;>�h����y.*ⅥS������Ӭ�+q&����j|UƧ����}���J0��WW< ۋS�)jQR�j���Ư��rN)�Gű�4Ѷ(�S)Ǣ�8��i��W52���No˓� ۍ%�5brOn�L�;�n��\G����=�^U�dI���8$�&���h��'���+�(������cȁ߫k�l��S^���cƗjԌE�ꭔ��gF���Ȓ��@���}O���*;e�v�WV���YJ\�]X'5��ղ�k�F��b 6R�o՜m��i N�i����>J����?��lPm�U��}>_Z&�KK��q�r��I�D�Չ~�q�3fL�:S�e>���E���-G���{L�6p�e,8��������QI��h��a�Xa��U�A'���ʂ���s�+טIjP�-��y�8ۈZ?J$��W�P� ��R�s�]��|�l(�ԓ��sƊi��o(��S0��Y� 8�T97.�����WiL��c�~�dxc�E|�2!�X�K�Ƙਫ਼�$((�6�~|d9u+�qd�^3�89��Y�6L�.I�����?���iI�q���9�)O/뚅����O���X��X�V��ZF[�یgQ�L��K1���RҖr@v�#��X�l��F���Нy�S�8�7�kF!A��sM���^rkp�jP�DyS$N���q��nxҍ!U�f�!eh�i�2�m���`�Y�I�9r�6� �TF���C}/�y�^���Η���5d�'��9A-��J��>{�_l+�`��A���[�'��յ�ϛ#w:݅�%��X�}�&�PSt�Q�"�-��\縵�/����$Ɨh�Xb�*�y��BS����;W�ջ_mc�����vt?2}1�;qS�d�d~u:2k5�2�R�~�z+|HE!)�Ǟl��7`��0�<�,�2*���Hl-��x�^����'_TV�gZA�'j� ^�2Ϊ��N7t�����?w�� �x1��f��Iz�C-Ȗ��K�^q�;���-W�DvT�7��8�Z�������� hK�(P:��Q- �8�n�Z���܃e貾�<�1�YT<�,�����"�6{/ �?�͟��|1�:�#g��W�>$����d��J��d�B��=��jf[��%rE^��il:��B���x���Sּ�1հ��,�=��*�7 fcG��#q� �eh?��2�7�����,�!7x��6�n�LC�4x��},Geǝ�tC.��vS �F�43��zz\��;QYC,6����~;RYS/6���|2���5���v��T��i����������mlv��������&� �nRh^ejR�LG�f���? �ۉҬܦƩ��|��Ȱ����>3����!v��i�ʯ�>�v��オ�X3e���_1z�Kȗ\<������!�8���V��]��?b�k41�Re��T�q��mz��TiOʦ�Z��Xq���L������q"+���2ۨ��8}�&N7XU7Ap�d�X��~�׿��&4e�o�F��� �H����O���č�c�� 懴�6���͉��+)��v;j��ݷ�� �UV�� i��� j���Y9GdÒJ1��詞�����V?h��l����l�cGs�ځ�������y�Ac�����\V3�? �� ܙg�>qH�S,�E�W�[�㺨�uch�⍸�O�}���a��>�q�6�n6����N6�q������N ! 1AQaq�0@����"2BRb�#Pr���3C`��Scst���$4D���%Td�� ?���N����a��3��m���C���w��������xA�m�q�m���m������$����4n淿t'��C"w��zU=D�\R+w�p+Y�T�&�պ@��ƃ��3ޯ?�Aﶂ��aŘ���@-�����Q�=���9D��ռ�ѻ@��M�V��P��܅�G5�f�Y<�u=,EC)�<�Fy'�"�&�չ�X~f��l�KԆV��?�� �W�N����=(� �;���{�r����ٌ�Y���h{�١������jW����P���Tc�����X�K�r��}���w�R��%��?���E��m�� �Y�q|����\lEE4���r���}�lsI�Y������f�$�=�d�yO����p�����yBj8jU�o�/�S��?�U��*������ˍ�0������u�q�m [�?f����a�� )Q�>����6#������� ?����0UQ����,IX���(6ڵ[�DI�MNލ�c&���υ�j\��X�R|,4��� j������T�hA�e��^���d���b<����n�� �즇�=!���3�^�`j�h�ȓr��jẕ�c�,ٞX����-����a�ﶔ���#�$��]w�O��Ӫ�1y%��L�Y<�wg#�ǝ�̗`�x�xa�t�w��»1���o7o5��>�m뭛C���Uƃߜ}�C���y1Xνm�F8�jI���]����H���ۺиE@I�i;r�8ӭ����V�F�Շ| ��&?�3|x�B�MuS�Ge�=Ӕ�#BE5G�����Y!z��_e��q�р/W>|-�Ci߇�t�1ޯќd�R3�u��g�=0 5��[?�#͏��q�cf���H��{ ?u�=?�?ǯ���}Z��z���hmΔ�BFTW�����<�q�(v� ��!��z���iW]*�J�V�z��gX֧A�q�&��/w���u�gYӘa���; �i=����g:��?2�dž6�ى�k�4�>�Pxs����}������G�9��3 ���)gG�R<>r h�$��'nc�h�P��Bj��J�ҧH� -��N1���N��?��~��}-q!=��_2hc�M��l�vY%UE�@|�v����M2�.Y[|y�"Eï��K�ZF,�ɯ?,q�?v�M 80jx�"�;�9vk�����+ ֧�� �ȺU��?�%�vcV��mA�6��Qg^M����A}�3�nl� QRN�l8�kkn�'�����(��M�7m9و�q���%ޟ���*h$Zk"��$�9��: �?U8�Sl��,,|ɒ��xH(ѷ����Gn�/Q�4�P��G�%��Ա8�N��!� �&�7�;���eKM7�4��9R/%����l�c>�x;������>��C�:�����t��h?aKX�bhe�ᜋ^�$�Iհ �hr7%F$�E��Fd���t��5���+�(M6�t����Ü�UU|zW�=a�Ts�Tg������dqP�Q����b'�m���1{|Y����X�N��b �P~��F^F:����k6�"�j!�� �I�r�`��1&�-$�Bevk:y���#yw��I0��x��=D�4��tU���P�ZH��ڠ底taP��6����b>�xa����Q�#� WeF��ŮNj�p�J* mQ�N����*I�-*�ȩ�F�g�3 �5��V�ʊ�ɮ�a��5F���O@{���NX��?����H�]3��1�Ri_u��������ѕ�� ����0��� F��~��:60�p�͈�S��qX#a�5>���`�o&+�<2�D����: �������ڝ�$�nP���*)�N�|y�Ej�F�5ټ�e���ihy�Z �>���k�bH�a�v��h�-#���!�Po=@k̆IEN��@��}Ll?j�O������߭�ʞ���Q|A07x���wt!xf���I2?Z��<ץ�T���cU�j��]��陎Ltl �}5�ϓ��$�,��O�mˊ�;�@O��jE��j(�ا,��LX���LO���Ц�90�O �.����a��nA���7������j4 ��W��_ٓ���zW�jcB������y՗+EM�)d���N�g6�y1_x��p�$Lv:��9�"z��p���ʙ$��^��JԼ*�ϭ����o���=x�Lj�6�J��u82�A�H�3$�ٕ@�=Vv�]�'�qEz�;I˼��)��=��ɯ���x �/�W(V���p�����$ �m�������u�����񶤑Oqˎ�T����r��㠚x�sr�GC��byp�G��1ߠ�w e�8�$⿄����/�M{*}��W�]˷.�CK\�ުx���/$�WPw���r� |i���&�}�{�X� �>��$-��l���?-z���g����lΆ���(F���h�vS*���b���߲ڡn,|)mrH[���a�3�ר�[1��3o_�U�3�TC�$��(�=�)0�kgP���� ��u�^=��4 �WYCҸ:��vQ�ר�X�à��tk�m,�t*��^�,�}D*� �"(�I��9R����>`�`��[~Q]�#af��i6l��8���6�:,s�s�N6�j"�A4���IuQ��6E,�GnH��zS�HO�uk�5$�I�4��ؤ�Q9�@��C����wp�BGv[]�u�Ov���0I4���\��y�����Q�Ѹ��~>Z��8�T��a��q�ޣ;z��a���/��S��I:�ܫ_�|������>=Z����8:�S��U�I�J��"IY���8%b8���H��:�QO�6�;7�I�S��J��ҌAά3��>c���E+&jf$eC+�z�;��V����� �r���ʺ������my�e���aQ�f&��6�ND��.:��NT�vm�<- u���ǝ\MvZY�N�NT��-A�>jr!S��n�O 1�3�Ns�%�3D@���`������ܟ 1�^c<���� �a�ɽ�̲�Xë#�w�|y�cW�=�9I*H8�p�^(4���՗�k��arOcW�tO�\�ƍR��8����'�K���I�Q�����?5�>[�}��yU�ײ -h��=��% q�ThG�2�)���"ו3]�!kB��*p�FDl�A���,�eEi�H�f�Ps�����5�H:�Փ~�H�0Dت�D�I����h�F3�������c��2���E��9�H��5�zԑ�ʚ�i�X�=:m�xg�hd(�v����׊�9iS��O��d@0ڽ���:�p�5�h-��t�&���X�q�ӕ,��ie�|���7A�2���O%P��E��htj��Y1��w�Ѓ!����  ���� ࢽ��My�7�\�a�@�ţ�J �4�Ȼ�F�@o�̒?4�wx��)��]�P��~�����u�����5�����7X ��9��^ܩ�U;Iꭆ 5 �������eK2�7(�{|��Y׎ �V��\"���Z�1� Z�����}��(�Ǝ"�1S���_�vE30>���p;� ΝD��%x�W�?W?v����o�^V�i�d��r[��/&>�~`�9Wh��y�;���R��� ;;ɮT��?����r$�g1�K����A��C��c��K��l:�'��3 c�ﳯ*"t8�~l��)���m��+U,z��`(�>yJ�?����h>��]��v��ЍG*�{`��;y]��I�T� ;c��NU�fo¾h���/$���|NS���1�S�"�H��V���T���4��uhǜ�]�v;���5�͠x��'C\�SBpl���h}�N����� A�Bx���%��ޭ�l��/����T��w�ʽ]D�=����K���ž�r㻠l4�S�O?=�k �M:� ��c�C�a�#ha���)�ѐxc�s���gP�iG��{+���x���Q���I= �� z��ԫ+ �8"�k�ñ�j=|����c ��y��CF��/��*9ж�h{ �?4�o� ��k�m�Q�N�x��;�Y��4膚�a�w?�6�>e]�����Q�r�:����g�,i"�����ԩA�*M�<�G��b�if��l^M��5� �Ҩ�{����6J��ZJ�����P�*�����Y���ݛu�_4�9�I8�7���������,^ToR���m4�H��?�N�S�ѕw��/S��甍�@�9H�S�T��t�ƻ���ʒU��*{Xs�@����f�����֒Li�K{H�w^���������Ϥm�tq���s� ���ք��f:��o~s��g�r��ט� �S�ѱC�e]�x���a��) ���(b-$(�j>�7q�B?ӕ�F��hV25r[7 Y� }L�R��}����*sg+��x�r�2�U=�*'WS��ZDW]�WǞ�<��叓���{�$�9Ou4��y�90-�1�'*D`�c�^o?(�9��u���ݐ��'PI&� f�Jݮ�������:wS����jfP1F:X �H�9dԯ���˝[�_54 �}*;@�ܨ�� ð�yn�T���?�ןd�#���4rG�ͨ��H�1�|-#���Mr�S3��G�3�����)�.᧏3v�z֑��r����$G"�`j �1t��x0<Ɔ�Wh6�y�6��,œ�Ga��gA����y��b��)��h�D��ß�_�m��ü �gG;��e�v��ݝ�nQ� ��C����-�*��o���y�a��M��I�>�<���]obD��"�:���G�A��-\%LT�8���c�)��+y76���o�Q�#*{�(F�⽕�y����=���rW�\p���۩�c���A���^e6��K������ʐ�cVf5$�'->���ՉN"���F�"�UQ@�f��Gb~��#�&�M=��8�ט�JNu9��D��[̤�s�o�~������ G��9T�tW^g5y$b��Y'��س�Ǵ�=��U-2 #�MC�t(�i� �lj�@Q 5�̣i�*�O����s�x�K�f��}\��M{E�V�{�υ��Ƈ�����);�H����I��fe�Lȣr�2��>��W�I�Ȃ6������i��k�� �5�YOxȺ����>��Y�f5'��|��H+��98pj�n�.O�y�������jY��~��i�w'������l�;�s�2��Y��:'lg�ꥴ)o#'Sa�a�K��Z� �m��}�`169�n���"���x��I ��*+� }F<��cГ���F�P�������ֹ*�PqX�x۩��,� ��N�� �4<-����%����:��7����W���u�`����� $�?�I��&����o��o��`v�>��P��"��l���4��5'�Z�gE���8���?��[�X�7(��.Q�-��*���ތL@̲����v��.5���[��=�t\+�CNܛ��,g�SQnH����}*F�G16���&:�t��4ُ"A��̣��$�b �|����#rs��a�����T�� ]�<�j��BS�('$�ɻ� �wP;�/�n��?�ݜ��x�F��yUn�~mL*-�������Xf�wd^�a�}��f�,=t�׵i�.2/wpN�Ep8�OР���•��R�FJ� 55TZ��T �ɭ�<��]��/�0�r�@�f��V��V����Nz�G��^���7hZi����k��3�,kN�e|�vg�1{9]_i��X5y7� 8e]�U����'�-2,���e"����]ot�I��Y_��n�(JҼ��1�O ]bXc���Nu�No��pS���Q_���_�?i�~�x h5d'�(qw52] ��'ޤ�q��o1�R!���`ywy�A4u���h<קy���\[~�4�\ X�Wt/� 6�����n�F�a8��f���z �3$�t(���q��q�x��^�XWeN'p<-v�!�{�(>ӽDP7��ո0�y)�e$ٕv�Ih'Q�EA�m*�H��RI��=:��� ���4牢) �%_iN�ݧ�l]� �Nt���G��H�L��� ɱ�g<���1V�,�J~�ٹ�"K��Q�� 9�HS�9�?@��k����r�;we݁�]I�!{ �@�G�[�"��`���J:�n]�{�cA�E����V��ʆ���#��U9�6����j�#Y�m\��q�e4h�B�7��C�������d<�?J����1g:ٳ���=Y���D�p�ц� ׈ǔ��1�]26؜oS�'��9�V�FVu�P�h�9�xc�oq�X��p�o�5��Ա5$�9W�V(�[Ak�aY錎qf;�'�[�|���b�6�Ck��)��#a#a˙��8���=äh�4��2��C��4tm^ �n'c���]GQ$[Wҿ��i���vN�{Fu ��1�gx��1┷���N�m��{j-,��x�� Ūm�ЧS�[�s���Gna���䑴�� x�p 8<������97�Q���ϴ�v�aϚG��Rt�Һ׈�f^\r��WH�JU�7Z���y)�vg=����n��4�_)y��D'y�6�]�c�5̪�\� �PF�k����&�c;��cq�$~T�7j ���nç]�<�g ":�to�t}�159�<�/�8������m�b�K#g'I'.W�����6��I/��>v��\�MN��g���m�A�yQL�4u�Lj�j9��#44�t��l^�}L����n��R��!��t��±]��r��h6ٍ>�yҏ�N��fU�� ���� Fm@�8}�/u��jb9������he:A�y�ծw��GpΧh�5����l}�3p468��)U��d��c����;Us/�֔�YX�1�O2��uq�s��`hwg�r~�{ R��mhN��؎*q 42�*th��>�#���E����#��Hv�O����q�}�����6�e��\�,Wk�#���X��b>��p}�դ��3���T5��†��6��[��@�P�y*n��|'f�֧>�lư΂�̺����SU�'*�q�p�_S�����M�� '��c�6�����m�� ySʨ;M��r���Ƌ�m�Kxo,���Gm�P��A�G�:��i��w�9�}M(�^�V��$ǒ�ѽ�9���|���� �a����J�SQ�a���r�B;����}���ٻ֢�2�%U���c�#�g���N�a�ݕ�'�v�[�OY'��3L�3�;,p�]@�S��{ls��X�'���c�jw�k'a�.��}�}&�� �dP�*�bK=ɍ!����;3n�gΊU�ߴmt�'*{,=SzfD� A��ko~�G�aoq�_mi}#�m�������P�Xhύ����mxǍ�΂���巿zf��Q���c���|kc�����?���W��Y�$���_Lv����l߶��c���`?����l�j�ݲˏ!V��6����U�Ђ(A���4y)H���p�Z_�x��>���e��R��$�/�`^'3qˏ�-&Q�=?��CFVR �D�fV�9��{�8g�������n�h�(P"��6�[�D���< E�����~0<@�`�G�6����Hг�cc�� �c�K.5��D��d�B���`?�XQ��2��ٿyqo&+�1^� DW�0�ꊩ���G�#��Q�nL3��c���������/��x ��1�1[y�x�პCW��C�c�UĨ80�m�e�4.{�m��u���I=��f�����0QRls9���f���������9���~f�����Ǩ��a�"@�8���ȁ�Q����#c�ic������G��$���G���r/$W�(��W���V�"��m�7�[m�A�m����bo��D� j����۳� l���^�k�h׽����� ��#� iXn�v��eT�k�a�^Y�4�BN��ĕ��0 !01@Q"2AaPq3BR������?���@4�Q�����T3,���㺠�W�[=JK�Ϟ���2�r^7��vc�:�9 �E�ߴ�w�S#d���Ix��u��:��Hp��9E!�� V 2;73|F��9Y���*ʬ�F��D����u&���y؟��^EA��A��(ɩ���^��GV:ݜDy�`��Jr29ܾ�㝉��[���E;Fzx��YG��U�e�Y�C���� ����v-tx����I�sם�Ę�q��Eb�+P\ :>�i�C'�;�����k|z�رn�y]�#ǿb��Q��������w�����(�r|ӹs��[�D��2v-%��@;�8<a���[\o[ϧw��I!��*0�krs)�[�J9^��ʜ��p1)� "��/_>��o��<1����A�E�y^�C��`�x1'ܣn�p��s`l���fQ��):�l����b>�Me�jH^?�kl3(�z:���1ŠK&?Q�~�{�ٺ�h�y���/�[��V�|6��}�KbX����mn[-��7�5q�94�������dm���c^���h� X��5��<�eޘ>G���-�}�دB�ޟ� ��|�rt�M��V+�]�c?�-#ڛ��^ǂ}���Lkr���O��u�>�-D�ry� D?:ޞ�U��ǜ�7�V��?瓮�"�#���r��չģVR;�n���/_� ؉v�ݶe5d�b9��/O��009�G���5n�W����JpA�*�r9�>�1��.[t���s�F���nQ� V 77R�]�ɫ8����_0<՜�IF�u(v��4��F�k�3��E)��N:��yڮe��P�`�1}�$WS��J�SQ�N�j�ٺ��޵�#l���ј(�5=��5�lǏmoW�v-�1����v,W�mn��߀$x�<����v�j(����c]��@#��1������Ǔ���o'��u+����;G�#�޸��v-lη��/(`i⣍Pm^���ԯ̾9Z��F��������n��1��� ��]�[��)�'������:�֪�W��FC����� �B9،!?���]��V��A�Վ�M��b�w��G F>_DȬ0¤�#�QR�[V��kz���m�w�"��9ZG�7'[��=�Q����j8R?�zf�\a�=��O�U����*oB�A�|G���2�54 �p��.w7� �� ��&������ξxGHp� B%��$g�����t�Џ򤵍z���HN�u�Я�-�'4��0��;_��3 !01"@AQa2Pq#3BR������?��ʩca��en��^��8���<�u#��m*08r��y�N"�<�Ѳ0��@\�p��� �����Kv�D��J8�Fҽ� �f�Y��-m�ybX�NP����}�!*8t(�OqѢ��Q�wW�K��ZD��Δ^e��!� ��B�K��p~�����e*l}z#9ң�k���q#�Ft�o��S�R����-�w�!�S���Ӥß|M�l޶V��!eˈ�8Y���c�ЮM2��tk���� ������J�fS����Ö*i/2�����n]�k�\���|4yX�8��U�P.���Ы[���l��@"�t�<������5�lF���vU�����W��W��;�b�cД^6[#7@vU�xgZv��F�6��Q,K�v��� �+Ъ��n��Ǣ��Ft���8��0��c�@�!�Zq s�v�t�;#](B��-�nῃ~���3g������5�J�%���O������n�kB�ĺ�.r��+���#�N$?�q�/�s�6��p��a����a��J/��M�8��6�ܰ"�*������ɗud"\w���aT(����[��F��U՛����RT�b���n�*��6���O��SJ�.�ij<�v�MT��R\c��5l�sZB>F��<7�;EA��{��E���Ö��1U/�#��d1�a�n.1ě����0�ʾR�h��|�R��Ao�3�m3 ��%�� ���28Q� ��y��φ���H�To�7�lW>����#i`�q���c����a��� �m,B�-j����݋�'mR1Ήt�>��V��p���s�0IbI�C.���1R�ea�����]H�6����������4B>��o��](��$B���m�����a�!=��?�B� K�Ǿ+�Ծ"�n���K��*��+��[T#�{E�J�S����Q�����s�5�:�U�\wĐ�f�3����܆&�)����I���Ԇw��E T�lrTf6Q|R�h:��[K�� �z��c֧�G�C��%\��_�a�84��HcO�bi��ؖV��7H �)*ģK~Xhչ0��4?�0��� �E<���}3���#���u�?�� ��|g�S�6ꊤ�|�I#Hڛ� �ա��w�X��9��7���Ŀ%�SL��y6č��|�F�a 8���b��$�sק�h���b9RAu7�˨p�Č�_\*w��묦��F ����4D~�f����|(�"m���NK��i�S�>�$d7SlA��/�²����SL��|6N�}���S�˯���g��]6��; �#�.��<���q'Q�1|KQ$�����񛩶"�$r�b:���N8�w@��8$�� �AjfG|~�9F ���Y��ʺ��Bwؒ������M:I岎�G��`s�YV5����6��A �b:�W���G�q%l�����F��H���7�������Fsv7��k�� 403WebShell
403Webshell
Server IP : 13.127.148.211  /  Your IP : 216.73.216.100
Web Server : Apache/2.4.41 (Ubuntu)
System : Linux ip-172-31-43-195 5.15.0-1083-aws #90~20.04.1-Ubuntu SMP Tue Apr 22 09:59:53 UTC 2025 x86_64
User : www-data ( 33)
PHP Version : 7.4.3-4ubuntu2.29
Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare,
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : OFF  |  Sudo : ON  |  Pkexec : ON
Directory :  /usr/lib/modules/5.15.0-1084-aws/build/arch/arm/crypto/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :


[ Back ]     

Current File : /usr/lib/modules/5.15.0-1084-aws/build/arch/arm/crypto/poly1305-armv4.pl
#!/usr/bin/env perl
# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
#
# ====================================================================
# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
# project.
# ====================================================================
#
#			IALU(*)/gcc-4.4		NEON
#
# ARM11xx(ARMv6)	7.78/+100%		-
# Cortex-A5		6.35/+130%		3.00
# Cortex-A8		6.25/+115%		2.36
# Cortex-A9		5.10/+95%		2.55
# Cortex-A15		3.85/+85%		1.25(**)
# Snapdragon S4		5.70/+100%		1.48(**)
#
# (*)	this is for -march=armv6, i.e. with bunch of ldrb loading data;
# (**)	these are trade-off results, they can be improved by ~8% but at
#	the cost of 15/12% regression on Cortex-A5/A7, it's even possible
#	to improve Cortex-A9 result, but then A5/A7 loose more than 20%;

$flavour = shift;
if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }

if ($flavour && $flavour ne "void") {
    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
    die "can't locate arm-xlate.pl";

    open STDOUT,"| \"$^X\" $xlate $flavour $output";
} else {
    open STDOUT,">$output";
}

($ctx,$inp,$len,$padbit)=map("r$_",(0..3));

$code.=<<___;
#ifndef	__KERNEL__
# include "arm_arch.h"
#else
# define __ARM_ARCH__ __LINUX_ARM_ARCH__
# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
# define poly1305_init   poly1305_init_arm
# define poly1305_blocks poly1305_blocks_arm
# define poly1305_emit   poly1305_emit_arm
.globl	poly1305_blocks_neon
#endif

#if defined(__thumb2__)
.syntax	unified
.thumb
#else
.code	32
#endif

.text

.globl	poly1305_emit
.globl	poly1305_blocks
.globl	poly1305_init
.type	poly1305_init,%function
.align	5
poly1305_init:
.Lpoly1305_init:
	stmdb	sp!,{r4-r11}

	eor	r3,r3,r3
	cmp	$inp,#0
	str	r3,[$ctx,#0]		@ zero hash value
	str	r3,[$ctx,#4]
	str	r3,[$ctx,#8]
	str	r3,[$ctx,#12]
	str	r3,[$ctx,#16]
	str	r3,[$ctx,#36]		@ clear is_base2_26
	add	$ctx,$ctx,#20

#ifdef	__thumb2__
	it	eq
#endif
	moveq	r0,#0
	beq	.Lno_key

#if	__ARM_MAX_ARCH__>=7
	mov	r3,#-1
	str	r3,[$ctx,#28]		@ impossible key power value
# ifndef __KERNEL__
	adr	r11,.Lpoly1305_init
	ldr	r12,.LOPENSSL_armcap
# endif
#endif
	ldrb	r4,[$inp,#0]
	mov	r10,#0x0fffffff
	ldrb	r5,[$inp,#1]
	and	r3,r10,#-4		@ 0x0ffffffc
	ldrb	r6,[$inp,#2]
	ldrb	r7,[$inp,#3]
	orr	r4,r4,r5,lsl#8
	ldrb	r5,[$inp,#4]
	orr	r4,r4,r6,lsl#16
	ldrb	r6,[$inp,#5]
	orr	r4,r4,r7,lsl#24
	ldrb	r7,[$inp,#6]
	and	r4,r4,r10

#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
# if !defined(_WIN32)
	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
# endif
# if defined(__APPLE__) || defined(_WIN32)
	ldr	r12,[r12]
# endif
#endif
	ldrb	r8,[$inp,#7]
	orr	r5,r5,r6,lsl#8
	ldrb	r6,[$inp,#8]
	orr	r5,r5,r7,lsl#16
	ldrb	r7,[$inp,#9]
	orr	r5,r5,r8,lsl#24
	ldrb	r8,[$inp,#10]
	and	r5,r5,r3

#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	tst	r12,#ARMV7_NEON		@ check for NEON
# ifdef	__thumb2__
	adr	r9,.Lpoly1305_blocks_neon
	adr	r11,.Lpoly1305_blocks
	it	ne
	movne	r11,r9
	adr	r12,.Lpoly1305_emit
	orr	r11,r11,#1		@ thumb-ify addresses
	orr	r12,r12,#1
# else
	add	r12,r11,#(.Lpoly1305_emit-.Lpoly1305_init)
	ite	eq
	addeq	r11,r11,#(.Lpoly1305_blocks-.Lpoly1305_init)
	addne	r11,r11,#(.Lpoly1305_blocks_neon-.Lpoly1305_init)
# endif
#endif
	ldrb	r9,[$inp,#11]
	orr	r6,r6,r7,lsl#8
	ldrb	r7,[$inp,#12]
	orr	r6,r6,r8,lsl#16
	ldrb	r8,[$inp,#13]
	orr	r6,r6,r9,lsl#24
	ldrb	r9,[$inp,#14]
	and	r6,r6,r3

	ldrb	r10,[$inp,#15]
	orr	r7,r7,r8,lsl#8
	str	r4,[$ctx,#0]
	orr	r7,r7,r9,lsl#16
	str	r5,[$ctx,#4]
	orr	r7,r7,r10,lsl#24
	str	r6,[$ctx,#8]
	and	r7,r7,r3
	str	r7,[$ctx,#12]
#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
	stmia	r2,{r11,r12}		@ fill functions table
	mov	r0,#1
#else
	mov	r0,#0
#endif
.Lno_key:
	ldmia	sp!,{r4-r11}
#if	__ARM_ARCH__>=5
	ret				@ bx	lr
#else
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_init,.-poly1305_init
___
{
my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
my ($s1,$s2,$s3)=($r1,$r2,$r3);

$code.=<<___;
.type	poly1305_blocks,%function
.align	5
poly1305_blocks:
.Lpoly1305_blocks:
	stmdb	sp!,{r3-r11,lr}

	ands	$len,$len,#-16
	beq	.Lno_data

	add	$len,$len,$inp		@ end pointer
	sub	sp,sp,#32

#if __ARM_ARCH__<7
	ldmia	$ctx,{$h0-$r3}		@ load context
	add	$ctx,$ctx,#20
	str	$len,[sp,#16]		@ offload stuff
	str	$ctx,[sp,#12]
#else
	ldr	lr,[$ctx,#36]		@ is_base2_26
	ldmia	$ctx!,{$h0-$h4}		@ load hash value
	str	$len,[sp,#16]		@ offload stuff
	str	$ctx,[sp,#12]

	adds	$r0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
	mov	$r1,$h1,lsr#6
	adcs	$r1,$r1,$h2,lsl#20
	mov	$r2,$h2,lsr#12
	adcs	$r2,$r2,$h3,lsl#14
	mov	$r3,$h3,lsr#18
	adcs	$r3,$r3,$h4,lsl#8
	mov	$len,#0
	teq	lr,#0
	str	$len,[$ctx,#16]		@ clear is_base2_26
	adc	$len,$len,$h4,lsr#24

	itttt	ne
	movne	$h0,$r0			@ choose between radixes
	movne	$h1,$r1
	movne	$h2,$r2
	movne	$h3,$r3
	ldmia	$ctx,{$r0-$r3}		@ load key
	it	ne
	movne	$h4,$len
#endif

	mov	lr,$inp
	cmp	$padbit,#0
	str	$r1,[sp,#20]
	str	$r2,[sp,#24]
	str	$r3,[sp,#28]
	b	.Loop

.align	4
.Loop:
#if __ARM_ARCH__<7
	ldrb	r0,[lr],#16		@ load input
# ifdef	__thumb2__
	it	hi
# endif
	addhi	$h4,$h4,#1		@ 1<<128
	ldrb	r1,[lr,#-15]
	ldrb	r2,[lr,#-14]
	ldrb	r3,[lr,#-13]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-12]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-11]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-10]
	adds	$h0,$h0,r3		@ accumulate input

	ldrb	r3,[lr,#-9]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-8]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-7]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-6]
	adcs	$h1,$h1,r3

	ldrb	r3,[lr,#-5]
	orr	r1,r0,r1,lsl#8
	ldrb	r0,[lr,#-4]
	orr	r2,r1,r2,lsl#16
	ldrb	r1,[lr,#-3]
	orr	r3,r2,r3,lsl#24
	ldrb	r2,[lr,#-2]
	adcs	$h2,$h2,r3

	ldrb	r3,[lr,#-1]
	orr	r1,r0,r1,lsl#8
	str	lr,[sp,#8]		@ offload input pointer
	orr	r2,r1,r2,lsl#16
	add	$s1,$r1,$r1,lsr#2
	orr	r3,r2,r3,lsl#24
#else
	ldr	r0,[lr],#16		@ load input
	it	hi
	addhi	$h4,$h4,#1		@ padbit
	ldr	r1,[lr,#-12]
	ldr	r2,[lr,#-8]
	ldr	r3,[lr,#-4]
# ifdef	__ARMEB__
	rev	r0,r0
	rev	r1,r1
	rev	r2,r2
	rev	r3,r3
# endif
	adds	$h0,$h0,r0		@ accumulate input
	str	lr,[sp,#8]		@ offload input pointer
	adcs	$h1,$h1,r1
	add	$s1,$r1,$r1,lsr#2
	adcs	$h2,$h2,r2
#endif
	add	$s2,$r2,$r2,lsr#2
	adcs	$h3,$h3,r3
	add	$s3,$r3,$r3,lsr#2

	umull	r2,r3,$h1,$r0
	 adc	$h4,$h4,#0
	umull	r0,r1,$h0,$r0
	umlal	r2,r3,$h4,$s1
	umlal	r0,r1,$h3,$s1
	ldr	$r1,[sp,#20]		@ reload $r1
	umlal	r2,r3,$h2,$s3
	umlal	r0,r1,$h1,$s3
	umlal	r2,r3,$h3,$s2
	umlal	r0,r1,$h2,$s2
	umlal	r2,r3,$h0,$r1
	str	r0,[sp,#0]		@ future $h0
	 mul	r0,$s2,$h4
	ldr	$r2,[sp,#24]		@ reload $r2
	adds	r2,r2,r1		@ d1+=d0>>32
	 eor	r1,r1,r1
	adc	lr,r3,#0		@ future $h2
	str	r2,[sp,#4]		@ future $h1

	mul	r2,$s3,$h4
	eor	r3,r3,r3
	umlal	r0,r1,$h3,$s3
	ldr	$r3,[sp,#28]		@ reload $r3
	umlal	r2,r3,$h3,$r0
	umlal	r0,r1,$h2,$r0
	umlal	r2,r3,$h2,$r1
	umlal	r0,r1,$h1,$r1
	umlal	r2,r3,$h1,$r2
	umlal	r0,r1,$h0,$r2
	umlal	r2,r3,$h0,$r3
	ldr	$h0,[sp,#0]
	mul	$h4,$r0,$h4
	ldr	$h1,[sp,#4]

	adds	$h2,lr,r0		@ d2+=d1>>32
	ldr	lr,[sp,#8]		@ reload input pointer
	adc	r1,r1,#0
	adds	$h3,r2,r1		@ d3+=d2>>32
	ldr	r0,[sp,#16]		@ reload end pointer
	adc	r3,r3,#0
	add	$h4,$h4,r3		@ h4+=d3>>32

	and	r1,$h4,#-4
	and	$h4,$h4,#3
	add	r1,r1,r1,lsr#2		@ *=5
	adds	$h0,$h0,r1
	adcs	$h1,$h1,#0
	adcs	$h2,$h2,#0
	adcs	$h3,$h3,#0
	adc	$h4,$h4,#0

	cmp	r0,lr			@ done yet?
	bhi	.Loop

	ldr	$ctx,[sp,#12]
	add	sp,sp,#32
	stmdb	$ctx,{$h0-$h4}		@ store the result

.Lno_data:
#if	__ARM_ARCH__>=5
	ldmia	sp!,{r3-r11,pc}
#else
	ldmia	sp!,{r3-r11,lr}
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_blocks,.-poly1305_blocks
___
}
{
my ($ctx,$mac,$nonce)=map("r$_",(0..2));
my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
my $g4=$ctx;

$code.=<<___;
.type	poly1305_emit,%function
.align	5
poly1305_emit:
.Lpoly1305_emit:
	stmdb	sp!,{r4-r11}

	ldmia	$ctx,{$h0-$h4}

#if __ARM_ARCH__>=7
	ldr	ip,[$ctx,#36]		@ is_base2_26

	adds	$g0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
	mov	$g1,$h1,lsr#6
	adcs	$g1,$g1,$h2,lsl#20
	mov	$g2,$h2,lsr#12
	adcs	$g2,$g2,$h3,lsl#14
	mov	$g3,$h3,lsr#18
	adcs	$g3,$g3,$h4,lsl#8
	mov	$g4,#0
	adc	$g4,$g4,$h4,lsr#24

	tst	ip,ip
	itttt	ne
	movne	$h0,$g0
	movne	$h1,$g1
	movne	$h2,$g2
	movne	$h3,$g3
	it	ne
	movne	$h4,$g4
#endif

	adds	$g0,$h0,#5		@ compare to modulus
	adcs	$g1,$h1,#0
	adcs	$g2,$h2,#0
	adcs	$g3,$h3,#0
	adc	$g4,$h4,#0
	tst	$g4,#4			@ did it carry/borrow?

#ifdef	__thumb2__
	it	ne
#endif
	movne	$h0,$g0
	ldr	$g0,[$nonce,#0]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h1,$g1
	ldr	$g1,[$nonce,#4]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h2,$g2
	ldr	$g2,[$nonce,#8]
#ifdef	__thumb2__
	it	ne
#endif
	movne	$h3,$g3
	ldr	$g3,[$nonce,#12]

	adds	$h0,$h0,$g0
	adcs	$h1,$h1,$g1
	adcs	$h2,$h2,$g2
	adc	$h3,$h3,$g3

#if __ARM_ARCH__>=7
# ifdef __ARMEB__
	rev	$h0,$h0
	rev	$h1,$h1
	rev	$h2,$h2
	rev	$h3,$h3
# endif
	str	$h0,[$mac,#0]
	str	$h1,[$mac,#4]
	str	$h2,[$mac,#8]
	str	$h3,[$mac,#12]
#else
	strb	$h0,[$mac,#0]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#4]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#8]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#12]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#1]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#5]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#9]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#13]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#2]
	mov	$h0,$h0,lsr#8
	strb	$h1,[$mac,#6]
	mov	$h1,$h1,lsr#8
	strb	$h2,[$mac,#10]
	mov	$h2,$h2,lsr#8
	strb	$h3,[$mac,#14]
	mov	$h3,$h3,lsr#8

	strb	$h0,[$mac,#3]
	strb	$h1,[$mac,#7]
	strb	$h2,[$mac,#11]
	strb	$h3,[$mac,#15]
#endif
	ldmia	sp!,{r4-r11}
#if	__ARM_ARCH__>=5
	ret				@ bx	lr
#else
	tst	lr,#1
	moveq	pc,lr			@ be binary compatible with V4, yet
	bx	lr			@ interoperable with Thumb ISA:-)
#endif
.size	poly1305_emit,.-poly1305_emit
___
{
my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
my ($T0,$T1,$MASK) = map("q$_",(15,4,0));

my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));

$code.=<<___;
#if	__ARM_MAX_ARCH__>=7
.fpu	neon

.type	poly1305_init_neon,%function
.align	5
poly1305_init_neon:
.Lpoly1305_init_neon:
	ldr	r3,[$ctx,#48]		@ first table element
	cmp	r3,#-1			@ is value impossible?
	bne	.Lno_init_neon

	ldr	r4,[$ctx,#20]		@ load key base 2^32
	ldr	r5,[$ctx,#24]
	ldr	r6,[$ctx,#28]
	ldr	r7,[$ctx,#32]

	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
	mov	r3,r4,lsr#26
	mov	r4,r5,lsr#20
	orr	r3,r3,r5,lsl#6
	mov	r5,r6,lsr#14
	orr	r4,r4,r6,lsl#12
	mov	r6,r7,lsr#8
	orr	r5,r5,r7,lsl#18
	and	r3,r3,#0x03ffffff
	and	r4,r4,#0x03ffffff
	and	r5,r5,#0x03ffffff

	vdup.32	$R0,r2			@ r^1 in both lanes
	add	r2,r3,r3,lsl#2		@ *5
	vdup.32	$R1,r3
	add	r3,r4,r4,lsl#2
	vdup.32	$S1,r2
	vdup.32	$R2,r4
	add	r4,r5,r5,lsl#2
	vdup.32	$S2,r3
	vdup.32	$R3,r5
	add	r5,r6,r6,lsl#2
	vdup.32	$S3,r4
	vdup.32	$R4,r6
	vdup.32	$S4,r5

	mov	$zeros,#2		@ counter

.Lsquare_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4

	vmull.u32	$D0,$R0,${R0}[1]
	vmull.u32	$D1,$R1,${R0}[1]
	vmull.u32	$D2,$R2,${R0}[1]
	vmull.u32	$D3,$R3,${R0}[1]
	vmull.u32	$D4,$R4,${R0}[1]

	vmlal.u32	$D0,$R4,${S1}[1]
	vmlal.u32	$D1,$R0,${R1}[1]
	vmlal.u32	$D2,$R1,${R1}[1]
	vmlal.u32	$D3,$R2,${R1}[1]
	vmlal.u32	$D4,$R3,${R1}[1]

	vmlal.u32	$D0,$R3,${S2}[1]
	vmlal.u32	$D1,$R4,${S2}[1]
	vmlal.u32	$D3,$R1,${R2}[1]
	vmlal.u32	$D2,$R0,${R2}[1]
	vmlal.u32	$D4,$R2,${R2}[1]

	vmlal.u32	$D0,$R2,${S3}[1]
	vmlal.u32	$D3,$R0,${R3}[1]
	vmlal.u32	$D1,$R3,${S3}[1]
	vmlal.u32	$D2,$R4,${S3}[1]
	vmlal.u32	$D4,$R1,${R3}[1]

	vmlal.u32	$D3,$R4,${S4}[1]
	vmlal.u32	$D0,$R1,${S4}[1]
	vmlal.u32	$D1,$R2,${S4}[1]
	vmlal.u32	$D2,$R3,${S4}[1]
	vmlal.u32	$D4,$R0,${R4}[1]

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
	@ and P. Schwabe
	@
	@ H0>>+H1>>+H2>>+H3>>+H4
	@ H3>>+H4>>*5+H0>>+H1
	@
	@ Trivia.
	@
	@ Result of multiplication of n-bit number by m-bit number is
	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
	@ m-bit number multiplied by 2^n is still n+m bits wide.
	@
	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
	@ one is n+1 bits wide.
	@
	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
	@ can be 27. However! In cases when their width exceeds 26 bits
	@ they are limited by 2^26+2^6. This in turn means that *sum*
	@ of the products with these values can still be viewed as sum
	@ of 52-bit numbers as long as the amount of addends is not a
	@ power of 2. For example,
	@
	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
	@
	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
	@ which is less than 32 * (2^52) or 2^57. And when processing
	@ data we are looking at triple as many addends...
	@
	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
	@ This means that result of reduction have to be compressed upon
	@ loop wrap-around. This can be done in the process of reduction
	@ to minimize amount of instructions [as well as amount of
	@ 128-bit instructions, which benefits low-end processors], but
	@ one has to watch for H2 (which is narrower than H0) and 5*H4
	@ not being wider than 58 bits, so that result of right shift
	@ by 26 bits fits in 32 bits. This is also useful on x86,
	@ because it allows to use paddd in place for paddq, which
	@ benefits Atom, where paddq is ridiculously slow.

	vshr.u64	$T0,$D3,#26
	vmovn.i64	$D3#lo,$D3
	 vshr.u64	$T1,$D0,#26
	 vmovn.i64	$D0#lo,$D0
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	vbic.i32	$D3#lo,#0xfc000000	@ &=0x03ffffff
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
	 vbic.i32	$D0#lo,#0xfc000000

	vshrn.u64	$T0#lo,$D4,#26
	vmovn.i64	$D4#lo,$D4
	 vshr.u64	$T1,$D1,#26
	 vmovn.i64	$D1#lo,$D1
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
	vbic.i32	$D4#lo,#0xfc000000
	 vbic.i32	$D1#lo,#0xfc000000

	vadd.i32	$D0#lo,$D0#lo,$T0#lo
	vshl.u32	$T0#lo,$T0#lo,#2
	 vshrn.u64	$T1#lo,$D2,#26
	 vmovn.i64	$D2#lo,$D2
	vadd.i32	$D0#lo,$D0#lo,$T0#lo	@ h4 -> h0
	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
	 vbic.i32	$D2#lo,#0xfc000000

	vshr.u32	$T0#lo,$D0#lo,#26
	vbic.i32	$D0#lo,#0xfc000000
	 vshr.u32	$T1#lo,$D3#lo,#26
	 vbic.i32	$D3#lo,#0xfc000000
	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4

	subs		$zeros,$zeros,#1
	beq		.Lsquare_break_neon

	add		$tbl0,$ctx,#(48+0*9*4)
	add		$tbl1,$ctx,#(48+1*9*4)

	vtrn.32		$R0,$D0#lo		@ r^2:r^1
	vtrn.32		$R2,$D2#lo
	vtrn.32		$R3,$D3#lo
	vtrn.32		$R1,$D1#lo
	vtrn.32		$R4,$D4#lo

	vshl.u32	$S2,$R2,#2		@ *5
	vshl.u32	$S3,$R3,#2
	vshl.u32	$S1,$R1,#2
	vshl.u32	$S4,$R4,#2
	vadd.i32	$S2,$S2,$R2
	vadd.i32	$S1,$S1,$R1
	vadd.i32	$S3,$S3,$R3
	vadd.i32	$S4,$S4,$R4

	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vst1.32		{${S4}[0]},[$tbl0,:32]
	vst1.32		{${S4}[1]},[$tbl1,:32]

	b		.Lsquare_neon

.align	4
.Lsquare_break_neon:
	add		$tbl0,$ctx,#(48+2*4*9)
	add		$tbl1,$ctx,#(48+3*4*9)

	vmov		$R0,$D0#lo		@ r^4:r^3
	vshl.u32	$S1,$D1#lo,#2		@ *5
	vmov		$R1,$D1#lo
	vshl.u32	$S2,$D2#lo,#2
	vmov		$R2,$D2#lo
	vshl.u32	$S3,$D3#lo,#2
	vmov		$R3,$D3#lo
	vshl.u32	$S4,$D4#lo,#2
	vmov		$R4,$D4#lo
	vadd.i32	$S1,$S1,$D1#lo
	vadd.i32	$S2,$S2,$D2#lo
	vadd.i32	$S3,$S3,$D3#lo
	vadd.i32	$S4,$S4,$D4#lo

	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vst1.32		{${S4}[0]},[$tbl0]
	vst1.32		{${S4}[1]},[$tbl1]

.Lno_init_neon:
	ret				@ bx	lr
.size	poly1305_init_neon,.-poly1305_init_neon

.type	poly1305_blocks_neon,%function
.align	5
poly1305_blocks_neon:
.Lpoly1305_blocks_neon:
	ldr	ip,[$ctx,#36]		@ is_base2_26

	cmp	$len,#64
	blo	.Lpoly1305_blocks

	stmdb	sp!,{r4-r7}
	vstmdb	sp!,{d8-d15}		@ ABI specification says so

	tst	ip,ip			@ is_base2_26?
	bne	.Lbase2_26_neon

	stmdb	sp!,{r1-r3,lr}
	bl	.Lpoly1305_init_neon

	ldr	r4,[$ctx,#0]		@ load hash value base 2^32
	ldr	r5,[$ctx,#4]
	ldr	r6,[$ctx,#8]
	ldr	r7,[$ctx,#12]
	ldr	ip,[$ctx,#16]

	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
	mov	r3,r4,lsr#26
	 veor	$D0#lo,$D0#lo,$D0#lo
	mov	r4,r5,lsr#20
	orr	r3,r3,r5,lsl#6
	 veor	$D1#lo,$D1#lo,$D1#lo
	mov	r5,r6,lsr#14
	orr	r4,r4,r6,lsl#12
	 veor	$D2#lo,$D2#lo,$D2#lo
	mov	r6,r7,lsr#8
	orr	r5,r5,r7,lsl#18
	 veor	$D3#lo,$D3#lo,$D3#lo
	and	r3,r3,#0x03ffffff
	orr	r6,r6,ip,lsl#24
	 veor	$D4#lo,$D4#lo,$D4#lo
	and	r4,r4,#0x03ffffff
	mov	r1,#1
	and	r5,r5,#0x03ffffff
	str	r1,[$ctx,#36]		@ set is_base2_26

	vmov.32	$D0#lo[0],r2
	vmov.32	$D1#lo[0],r3
	vmov.32	$D2#lo[0],r4
	vmov.32	$D3#lo[0],r5
	vmov.32	$D4#lo[0],r6
	adr	$zeros,.Lzeros

	ldmia	sp!,{r1-r3,lr}
	b	.Lhash_loaded

.align	4
.Lbase2_26_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ load hash value

	veor		$D0#lo,$D0#lo,$D0#lo
	veor		$D1#lo,$D1#lo,$D1#lo
	veor		$D2#lo,$D2#lo,$D2#lo
	veor		$D3#lo,$D3#lo,$D3#lo
	veor		$D4#lo,$D4#lo,$D4#lo
	vld4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
	adr		$zeros,.Lzeros
	vld1.32		{$D4#lo[0]},[$ctx]
	sub		$ctx,$ctx,#16		@ rewind

.Lhash_loaded:
	add		$in2,$inp,#32
	mov		$padbit,$padbit,lsl#24
	tst		$len,#31
	beq		.Leven

	vld4.32		{$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
	vmov.32		$H4#lo[0],$padbit
	sub		$len,$len,#16
	add		$in2,$inp,#32

# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H3,$H3
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
# endif
	vsri.u32	$H4#lo,$H3#lo,#8	@ base 2^32 -> base 2^26
	vshl.u32	$H3#lo,$H3#lo,#18

	vsri.u32	$H3#lo,$H2#lo,#14
	vshl.u32	$H2#lo,$H2#lo,#12
	vadd.i32	$H4#hi,$H4#lo,$D4#lo	@ add hash value and move to #hi

	vbic.i32	$H3#lo,#0xfc000000
	vsri.u32	$H2#lo,$H1#lo,#20
	vshl.u32	$H1#lo,$H1#lo,#6

	vbic.i32	$H2#lo,#0xfc000000
	vsri.u32	$H1#lo,$H0#lo,#26
	vadd.i32	$H3#hi,$H3#lo,$D3#lo

	vbic.i32	$H0#lo,#0xfc000000
	vbic.i32	$H1#lo,#0xfc000000
	vadd.i32	$H2#hi,$H2#lo,$D2#lo

	vadd.i32	$H0#hi,$H0#lo,$D0#lo
	vadd.i32	$H1#hi,$H1#lo,$D1#lo

	mov		$tbl1,$zeros
	add		$tbl0,$ctx,#48

	cmp		$len,$len
	b		.Long_tail

.align	4
.Leven:
	subs		$len,$len,#64
	it		lo
	movlo		$in2,$zeros

	vmov.i32	$H4,#1<<24		@ padbit, yes, always
	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
	add		$inp,$inp,#64
	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
	add		$in2,$in2,#64
	itt		hi
	addhi		$tbl1,$ctx,#(48+1*9*4)
	addhi		$tbl0,$ctx,#(48+3*9*4)

# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H3,$H3
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
# endif
	vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
	vshl.u32	$H3,$H3,#18

	vsri.u32	$H3,$H2,#14
	vshl.u32	$H2,$H2,#12

	vbic.i32	$H3,#0xfc000000
	vsri.u32	$H2,$H1,#20
	vshl.u32	$H1,$H1,#6

	vbic.i32	$H2,#0xfc000000
	vsri.u32	$H1,$H0,#26

	vbic.i32	$H0,#0xfc000000
	vbic.i32	$H1,#0xfc000000

	bls		.Lskip_loop

	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^2
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	b		.Loop_neon

.align	5
.Loop_neon:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
	@   \___________________/
	@ ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
	@ ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
	@   \___________________/ \____________________/
	@
	@ Note that we start with inp[2:3]*r^2. This is because it
	@ doesn't depend on reduction in previous iteration.
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ inp[2:3]*r^2

	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ accumulate inp[0:1]
	vmull.u32	$D2,$H2#hi,${R0}[1]
	vadd.i32	$H0#lo,$H0#lo,$D0#lo
	vmull.u32	$D0,$H0#hi,${R0}[1]
	vadd.i32	$H3#lo,$H3#lo,$D3#lo
	vmull.u32	$D3,$H3#hi,${R0}[1]
	vmlal.u32	$D2,$H1#hi,${R1}[1]
	vadd.i32	$H1#lo,$H1#lo,$D1#lo
	vmull.u32	$D1,$H1#hi,${R0}[1]

	vadd.i32	$H4#lo,$H4#lo,$D4#lo
	vmull.u32	$D4,$H4#hi,${R0}[1]
	subs		$len,$len,#64
	vmlal.u32	$D0,$H4#hi,${S1}[1]
	it		lo
	movlo		$in2,$zeros
	vmlal.u32	$D3,$H2#hi,${R1}[1]
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D1,$H0#hi,${R1}[1]
	vmlal.u32	$D4,$H3#hi,${R1}[1]

	vmlal.u32	$D0,$H3#hi,${S2}[1]
	vmlal.u32	$D3,$H1#hi,${R2}[1]
	vmlal.u32	$D4,$H2#hi,${R2}[1]
	vmlal.u32	$D1,$H4#hi,${S2}[1]
	vmlal.u32	$D2,$H0#hi,${R2}[1]

	vmlal.u32	$D3,$H0#hi,${R3}[1]
	vmlal.u32	$D0,$H2#hi,${S3}[1]
	vmlal.u32	$D4,$H1#hi,${R3}[1]
	vmlal.u32	$D1,$H3#hi,${S3}[1]
	vmlal.u32	$D2,$H4#hi,${S3}[1]

	vmlal.u32	$D3,$H4#hi,${S4}[1]
	vmlal.u32	$D0,$H1#hi,${S4}[1]
	vmlal.u32	$D4,$H0#hi,${R4}[1]
	vmlal.u32	$D1,$H2#hi,${S4}[1]
	vmlal.u32	$D2,$H3#hi,${S4}[1]

	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
	add		$in2,$in2,#64

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ (hash+inp[0:1])*r^4 and accumulate

	vmlal.u32	$D3,$H3#lo,${R0}[0]
	vmlal.u32	$D0,$H0#lo,${R0}[0]
	vmlal.u32	$D4,$H4#lo,${R0}[0]
	vmlal.u32	$D1,$H1#lo,${R0}[0]
	vmlal.u32	$D2,$H2#lo,${R0}[0]
	vld1.32		${S4}[0],[$tbl0,:32]

	vmlal.u32	$D3,$H2#lo,${R1}[0]
	vmlal.u32	$D0,$H4#lo,${S1}[0]
	vmlal.u32	$D4,$H3#lo,${R1}[0]
	vmlal.u32	$D1,$H0#lo,${R1}[0]
	vmlal.u32	$D2,$H1#lo,${R1}[0]

	vmlal.u32	$D3,$H1#lo,${R2}[0]
	vmlal.u32	$D0,$H3#lo,${S2}[0]
	vmlal.u32	$D4,$H2#lo,${R2}[0]
	vmlal.u32	$D1,$H4#lo,${S2}[0]
	vmlal.u32	$D2,$H0#lo,${R2}[0]

	vmlal.u32	$D3,$H0#lo,${R3}[0]
	vmlal.u32	$D0,$H2#lo,${S3}[0]
	vmlal.u32	$D4,$H1#lo,${R3}[0]
	vmlal.u32	$D1,$H3#lo,${S3}[0]
	vmlal.u32	$D3,$H4#lo,${S4}[0]

	vmlal.u32	$D2,$H4#lo,${S3}[0]
	vmlal.u32	$D0,$H1#lo,${S4}[0]
	vmlal.u32	$D4,$H0#lo,${R4}[0]
	vmov.i32	$H4,#1<<24		@ padbit, yes, always
	vmlal.u32	$D1,$H2#lo,${S4}[0]
	vmlal.u32	$D2,$H3#lo,${S4}[0]

	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
	add		$inp,$inp,#64
# ifdef	__ARMEB__
	vrev32.8	$H0,$H0
	vrev32.8	$H1,$H1
	vrev32.8	$H2,$H2
	vrev32.8	$H3,$H3
# endif

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
	@ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.

	vshr.u64	$T0,$D3,#26
	vmovn.i64	$D3#lo,$D3
	 vshr.u64	$T1,$D0,#26
	 vmovn.i64	$D0#lo,$D0
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	vbic.i32	$D3#lo,#0xfc000000
	  vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
	  vshl.u32	$H3,$H3,#18
	 vbic.i32	$D0#lo,#0xfc000000

	vshrn.u64	$T0#lo,$D4,#26
	vmovn.i64	$D4#lo,$D4
	 vshr.u64	$T1,$D1,#26
	 vmovn.i64	$D1#lo,$D1
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
	  vsri.u32	$H3,$H2,#14
	vbic.i32	$D4#lo,#0xfc000000
	  vshl.u32	$H2,$H2,#12
	 vbic.i32	$D1#lo,#0xfc000000

	vadd.i32	$D0#lo,$D0#lo,$T0#lo
	vshl.u32	$T0#lo,$T0#lo,#2
	  vbic.i32	$H3,#0xfc000000
	 vshrn.u64	$T1#lo,$D2,#26
	 vmovn.i64	$D2#lo,$D2
	vaddl.u32	$D0,$D0#lo,$T0#lo	@ h4 -> h0 [widen for a sec]
	  vsri.u32	$H2,$H1,#20
	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
	  vshl.u32	$H1,$H1,#6
	 vbic.i32	$D2#lo,#0xfc000000
	  vbic.i32	$H2,#0xfc000000

	vshrn.u64	$T0#lo,$D0,#26		@ re-narrow
	vmovn.i64	$D0#lo,$D0
	  vsri.u32	$H1,$H0,#26
	  vbic.i32	$H0,#0xfc000000
	 vshr.u32	$T1#lo,$D3#lo,#26
	 vbic.i32	$D3#lo,#0xfc000000
	vbic.i32	$D0#lo,#0xfc000000
	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
	  vbic.i32	$H1,#0xfc000000

	bhi		.Loop_neon

.Lskip_loop:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1

	add		$tbl1,$ctx,#(48+0*9*4)
	add		$tbl0,$ctx,#(48+1*9*4)
	adds		$len,$len,#32
	it		ne
	movne		$len,#0
	bne		.Long_tail

	vadd.i32	$H2#hi,$H2#lo,$D2#lo	@ add hash value and move to #hi
	vadd.i32	$H0#hi,$H0#lo,$D0#lo
	vadd.i32	$H3#hi,$H3#lo,$D3#lo
	vadd.i32	$H1#hi,$H1#lo,$D1#lo
	vadd.i32	$H4#hi,$H4#lo,$D4#lo

.Long_tail:
	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^1
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^2

	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ can be redundant
	vmull.u32	$D2,$H2#hi,$R0
	vadd.i32	$H0#lo,$H0#lo,$D0#lo
	vmull.u32	$D0,$H0#hi,$R0
	vadd.i32	$H3#lo,$H3#lo,$D3#lo
	vmull.u32	$D3,$H3#hi,$R0
	vadd.i32	$H1#lo,$H1#lo,$D1#lo
	vmull.u32	$D1,$H1#hi,$R0
	vadd.i32	$H4#lo,$H4#lo,$D4#lo
	vmull.u32	$D4,$H4#hi,$R0

	vmlal.u32	$D0,$H4#hi,$S1
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vmlal.u32	$D3,$H2#hi,$R1
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vmlal.u32	$D1,$H0#hi,$R1
	vmlal.u32	$D4,$H3#hi,$R1
	vmlal.u32	$D2,$H1#hi,$R1

	vmlal.u32	$D3,$H1#hi,$R2
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D0,$H3#hi,$S2
	vld1.32		${S4}[0],[$tbl0,:32]
	vmlal.u32	$D4,$H2#hi,$R2
	vmlal.u32	$D1,$H4#hi,$S2
	vmlal.u32	$D2,$H0#hi,$R2

	vmlal.u32	$D3,$H0#hi,$R3
	 it		ne
	 addne		$tbl1,$ctx,#(48+2*9*4)
	vmlal.u32	$D0,$H2#hi,$S3
	 it		ne
	 addne		$tbl0,$ctx,#(48+3*9*4)
	vmlal.u32	$D4,$H1#hi,$R3
	vmlal.u32	$D1,$H3#hi,$S3
	vmlal.u32	$D2,$H4#hi,$S3

	vmlal.u32	$D3,$H4#hi,$S4
	 vorn		$MASK,$MASK,$MASK	@ all-ones, can be redundant
	vmlal.u32	$D0,$H1#hi,$S4
	 vshr.u64	$MASK,$MASK,#38
	vmlal.u32	$D4,$H0#hi,$R4
	vmlal.u32	$D1,$H2#hi,$S4
	vmlal.u32	$D2,$H3#hi,$S4

	beq		.Lshort_tail

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ (hash+inp[0:1])*r^4:r^3 and accumulate

	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^3
	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4

	vmlal.u32	$D2,$H2#lo,$R0
	vmlal.u32	$D0,$H0#lo,$R0
	vmlal.u32	$D3,$H3#lo,$R0
	vmlal.u32	$D1,$H1#lo,$R0
	vmlal.u32	$D4,$H4#lo,$R0

	vmlal.u32	$D0,$H4#lo,$S1
	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
	vmlal.u32	$D3,$H2#lo,$R1
	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
	vmlal.u32	$D1,$H0#lo,$R1
	vmlal.u32	$D4,$H3#lo,$R1
	vmlal.u32	$D2,$H1#lo,$R1

	vmlal.u32	$D3,$H1#lo,$R2
	vld1.32		${S4}[1],[$tbl1,:32]
	vmlal.u32	$D0,$H3#lo,$S2
	vld1.32		${S4}[0],[$tbl0,:32]
	vmlal.u32	$D4,$H2#lo,$R2
	vmlal.u32	$D1,$H4#lo,$S2
	vmlal.u32	$D2,$H0#lo,$R2

	vmlal.u32	$D3,$H0#lo,$R3
	vmlal.u32	$D0,$H2#lo,$S3
	vmlal.u32	$D4,$H1#lo,$R3
	vmlal.u32	$D1,$H3#lo,$S3
	vmlal.u32	$D2,$H4#lo,$S3

	vmlal.u32	$D3,$H4#lo,$S4
	 vorn		$MASK,$MASK,$MASK	@ all-ones
	vmlal.u32	$D0,$H1#lo,$S4
	 vshr.u64	$MASK,$MASK,#38
	vmlal.u32	$D4,$H0#lo,$R4
	vmlal.u32	$D1,$H2#lo,$S4
	vmlal.u32	$D2,$H3#lo,$S4

.Lshort_tail:
	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ horizontal addition

	vadd.i64	$D3#lo,$D3#lo,$D3#hi
	vadd.i64	$D0#lo,$D0#lo,$D0#hi
	vadd.i64	$D4#lo,$D4#lo,$D4#hi
	vadd.i64	$D1#lo,$D1#lo,$D1#hi
	vadd.i64	$D2#lo,$D2#lo,$D2#hi

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ lazy reduction, but without narrowing

	vshr.u64	$T0,$D3,#26
	vand.i64	$D3,$D3,$MASK
	 vshr.u64	$T1,$D0,#26
	 vand.i64	$D0,$D0,$MASK
	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1

	vshr.u64	$T0,$D4,#26
	vand.i64	$D4,$D4,$MASK
	 vshr.u64	$T1,$D1,#26
	 vand.i64	$D1,$D1,$MASK
	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2

	vadd.i64	$D0,$D0,$T0
	vshl.u64	$T0,$T0,#2
	 vshr.u64	$T1,$D2,#26
	 vand.i64	$D2,$D2,$MASK
	vadd.i64	$D0,$D0,$T0		@ h4 -> h0
	 vadd.i64	$D3,$D3,$T1		@ h2 -> h3

	vshr.u64	$T0,$D0,#26
	vand.i64	$D0,$D0,$MASK
	 vshr.u64	$T1,$D3,#26
	 vand.i64	$D3,$D3,$MASK
	vadd.i64	$D1,$D1,$T0		@ h0 -> h1
	 vadd.i64	$D4,$D4,$T1		@ h3 -> h4

	cmp		$len,#0
	bne		.Leven

	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
	@ store hash value

	vst4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
	vst1.32		{$D4#lo[0]},[$ctx]

	vldmia	sp!,{d8-d15}			@ epilogue
	ldmia	sp!,{r4-r7}
	ret					@ bx	lr
.size	poly1305_blocks_neon,.-poly1305_blocks_neon

.align	5
.Lzeros:
.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
#ifndef	__KERNEL__
.LOPENSSL_armcap:
# ifdef	_WIN32
.word	OPENSSL_armcap_P
# else
.word	OPENSSL_armcap_P-.Lpoly1305_init
# endif
.comm	OPENSSL_armcap_P,4,4
.hidden	OPENSSL_armcap_P
#endif
#endif
___
}	}
$code.=<<___;
.asciz	"Poly1305 for ARMv4/NEON, CRYPTOGAMS by \@dot-asm"
.align	2
___

foreach (split("\n",$code)) {
	s/\`([^\`]*)\`/eval $1/geo;

	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
	s/\bret\b/bx	lr/go						or
	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4

	print $_,"\n";
}
close STDOUT; # enforce flush

Youez - 2016 - github.com/yon3zu
LinuXploit