https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110946
--- Comment #1 from Dave Rodgman <dave.rodgman at arm dot com> ---
Disassembly under -Os:
000000000000139c <mbedtls_aes_crypt_xts>:
139c: a9b67bfd stp x29, x30, [sp, #-160]!
13a0: 910003fd mov x29, sp
13a4: a9046bf9 stp x25, x26, [sp, #64]
13a8: aa0003f9 mov x25, x0
13ac: 90000000 adrp x0, 0 <__stack_chk_guard>
13b0: a90153f3 stp x19, x20, [sp, #16]
13b4: f9400000 ldr x0, [x0]
13b8: a9025bf5 stp x21, x22, [sp, #32]
13bc: 2a0103f6 mov w22, w1
13c0: a90363f7 stp x23, x24, [sp, #48]
13c4: a90573fb stp x27, x28, [sp, #80]
13c8: f9400001 ldr x1, [x0]
13cc: f9004fe1 str x1, [sp, #152]
13d0: d2800001 mov x1, #0x0 // #0
13d4: 710006df cmp w22, #0x1
13d8: 54000c28 b.hi 155c <mbedtls_aes_crypt_xts+0x1c0> //
b.pmore
13dc: d1004041 sub x1, x2, #0x10
13e0: aa0203f3 mov x19, x2
13e4: b27c4fe0 mov x0, #0xfffff0 //
#16777200
13e8: eb00003f cmp x1, x0
13ec: 54000bc8 b.hi 1564 <mbedtls_aes_crypt_xts+0x1c8> //
b.pmore
13f0: 9101a3f5 add x21, sp, #0x68
13f4: aa0303e2 mov x2, x3
13f8: aa0403f8 mov x24, x4
13fc: aa0503f7 mov x23, x5
1400: aa1503e3 mov x3, x21
1404: 91048320 add x0, x25, #0x120
1408: 52800021 mov w1, #0x1 // #1
140c: 94000000 bl 1210 <mbedtls_aes_crypt_ecb>
1410: 2a0003f4 mov w20, w0
1414: 35000540 cbnz w0, 14bc <mbedtls_aes_crypt_xts+0x120>
1418: 520002db eor w27, w22, #0x1
141c: d344fe7a lsr x26, x19, #4
1420: 1200037b and w27, w27, #0x1
1424: 92400e73 and x19, x19, #0xf
1428: 910223fc add x28, sp, #0x88
142c: d100075a sub x26, x26, #0x1
1430: b100075f cmn x26, #0x1
1434: 54000541 b.ne 14dc <mbedtls_aes_crypt_xts+0x140> //
b.any
1438: b4000433 cbz x19, 14bc <mbedtls_aes_crypt_xts+0x120>
143c: 710002df cmp w22, #0x0
1440: d10042fb sub x27, x23, #0x10
1444: 9101e3fa add x26, sp, #0x78
1448: aa1303e2 mov x2, x19
144c: 9a95035a csel x26, x26, x21, eq // eq = none
1450: aa1b03e1 mov x1, x27
1454: 910223f5 add x21, sp, #0x88
1458: aa1703e0 mov x0, x23
145c: 94000000 bl 0 <memmove>
1460: d2800217 mov x23, #0x10 // #16
1464: aa1303e3 mov x3, x19
1468: aa1a03e2 mov x2, x26
146c: aa1803e1 mov x1, x24
1470: aa1503e0 mov x0, x21
1474: 94000000 bl 0 <mbedtls_xor>
1478: cb1302e3 sub x3, x23, x19
147c: 8b130342 add x2, x26, x19
1480: 8b130361 add x1, x27, x19
1484: 8b1302a0 add x0, x21, x19
1488: 94000000 bl 0 <mbedtls_xor>
148c: aa1503e3 mov x3, x21
1490: aa1503e2 mov x2, x21
1494: 2a1603e1 mov w1, w22
1498: aa1903e0 mov x0, x25
149c: 94000000 bl 1210 <mbedtls_aes_crypt_ecb>
14a0: 2a0003f4 mov w20, w0
14a4: 350000c0 cbnz w0, 14bc <mbedtls_aes_crypt_xts+0x120>
14a8: aa1703e3 mov x3, x23
14ac: aa1a03e2 mov x2, x26
14b0: aa1503e1 mov x1, x21
14b4: aa1b03e0 mov x0, x27
14b8: 94000000 bl 0 <mbedtls_xor>
14bc: 90000000 adrp x0, 0 <__stack_chk_guard>
14c0: f9400000 ldr x0, [x0]
14c4: f9404fe2 ldr x2, [sp, #152]
14c8: f9400001 ldr x1, [x0]
14cc: eb010042 subs x2, x2, x1
14d0: d2800001 mov x1, #0x0 // #0
14d4: 54000500 b.eq 1574 <mbedtls_aes_crypt_xts+0x1d8> //
b.none
14d8: 94000000 bl 0 <__stack_chk_fail>
14dc: f100027f cmp x19, #0x0
14e0: 1a9f07e0 cset w0, ne // ne = any
14e4: 6a1b001f tst w0, w27
14e8: 540000e0 b.eq 1504 <mbedtls_aes_crypt_xts+0x168> //
b.none
14ec: b50000da cbnz x26, 1504 <mbedtls_aes_crypt_xts+0x168>
14f0: a94687e0 ldp x0, x1, [sp, #104]
14f4: a90787e0 stp x0, x1, [sp, #120]
14f8: aa1503e1 mov x1, x21
14fc: aa1503e0 mov x0, x21
1500: 97fffb63 bl 28c <mbedtls_gf128mul_x_ble>
1504: aa1503e2 mov x2, x21
1508: aa1803e1 mov x1, x24
150c: aa1c03e0 mov x0, x28
1510: d2800203 mov x3, #0x10 // #16
1514: 94000000 bl 0 <mbedtls_xor>
1518: aa1c03e3 mov x3, x28
151c: aa1c03e2 mov x2, x28
1520: 2a1603e1 mov w1, w22
1524: aa1903e0 mov x0, x25
1528: 94000000 bl 1210 <mbedtls_aes_crypt_ecb>
152c: 35000200 cbnz w0, 156c <mbedtls_aes_crypt_xts+0x1d0>
1530: aa1503e2 mov x2, x21
1534: d2800203 mov x3, #0x10 // #16
1538: aa1703e0 mov x0, x23
153c: aa1c03e1 mov x1, x28
1540: 94000000 bl 0 <mbedtls_xor>
1544: 910042f7 add x23, x23, #0x10
1548: aa1503e1 mov x1, x21
154c: aa1503e0 mov x0, x21
1550: 91004318 add x24, x24, #0x10
1554: 97fffb4e bl 28c <mbedtls_gf128mul_x_ble>
1558: 17ffffb5 b 142c <mbedtls_aes_crypt_xts+0x90>
155c: 12800414 mov w20, #0xffffffdf // #-33
1560: 17ffffd7 b 14bc <mbedtls_aes_crypt_xts+0x120>
1564: 12800434 mov w20, #0xffffffde // #-34
1568: 17ffffd5 b 14bc <mbedtls_aes_crypt_xts+0x120>
156c: 2a0003f4 mov w20, w0
1570: 17ffffd3 b 14bc <mbedtls_aes_crypt_xts+0x120>
1574: 2a1403e0 mov w0, w20
1578: a94153f3 ldp x19, x20, [sp, #16]
157c: a9425bf5 ldp x21, x22, [sp, #32]
1580: a94363f7 ldp x23, x24, [sp, #48]
1584: a9446bf9 ldp x25, x26, [sp, #64]
1588: a94573fb ldp x27, x28, [sp, #80]
158c: a8ca7bfd ldp x29, x30, [sp], #160
1590: d65f03c0 ret
Disassembly for mbedtls_gf128mul_x_ble:
000000000000028c <mbedtls_gf128mul_x_ble>:
28c: a9be7bfd stp x29, x30, [sp, #-32]!
290: 910003fd mov x29, sp
294: a90153f3 stp x19, x20, [sp, #16]
298: aa0003f3 mov x19, x0
29c: a9400823 ldp x3, x2, [x1]
2a0: 52800101 mov w1, #0x8 // #8
2a4: 93c3fc54 extr x20, x2, x3, #63
2a8: d37ffc42 lsr x2, x2, #63
2ac: 4b020c22 sub w2, w1, w2, lsl #3
2b0: 528010e1 mov w1, #0x87 // #135
2b4: 1ac22821 asr w1, w1, w2
2b8: 93407c21 sxtw x1, w1
2bc: ca030421 eor x1, x1, x3, lsl #1
2c0: 94000000 bl 0 <mbedtls_put_unaligned_uint64>
2c4: aa1403e1 mov x1, x20
2c8: 91002260 add x0, x19, #0x8
2cc: a94153f3 ldp x19, x20, [sp, #16]
2d0: a8c27bfd ldp x29, x30, [sp], #32
2d4: 14000000 b 0 <mbedtls_put_unaligned_uint64>
and under -O2:
Disassembly for mbedtls_aes_crypt_xts:
0000000000001500 <mbedtls_aes_crypt_xts>:
1500: a9b57bfd stp x29, x30, [sp, #-176]!
1504: 90000006 adrp x6, 0 <__stack_chk_guard>
1508: 910003fd mov x29, sp
150c: f94000c6 ldr x6, [x6]
1510: a90153f3 stp x19, x20, [sp, #16]
1514: 2a0103f4 mov w20, w1
1518: f94000c1 ldr x1, [x6]
151c: f90057e1 str x1, [sp, #168]
1520: d2800001 mov x1, #0x0 // #0
1524: 7100069f cmp w20, #0x1
1528: 54001348 b.hi 1790 <mbedtls_aes_crypt_xts+0x290> //
b.pmore
152c: d1004041 sub x1, x2, #0x10
1530: a9025bf5 stp x21, x22, [sp, #32]
1534: aa0003f5 mov x21, x0
1538: aa0203f6 mov x22, x2
153c: b27c4fe0 mov x0, #0xfffff0 //
#16777200
1540: eb00003f cmp x1, x0
1544: 54001208 b.hi 1784 <mbedtls_aes_crypt_xts+0x284> //
b.pmore
1548: aa0503f3 mov x19, x5
154c: a90363f7 stp x23, x24, [sp, #48]
1550: aa0303f7 mov x23, x3
1554: a90573fb stp x27, x28, [sp, #80]
1558: aa0403fb mov x27, x4
155c: 94000000 bl 0 <mbedtls_aesce_has_support>
1560: 910482a3 add x3, x21, #0x120
1564: 9101e3fc add x28, sp, #0x78
1568: 35000ec0 cbnz w0, 1740 <mbedtls_aes_crypt_xts+0x240>
156c: aa1703e1 mov x1, x23
1570: aa0303e0 mov x0, x3
1574: aa1c03e2 mov x2, x28
1578: 94000000 bl 9c0 <mbedtls_internal_aes_encrypt>
157c: 35000760 cbnz w0, 1668 <mbedtls_aes_crypt_xts+0x168>
1580: f2400ec0 ands x0, x22, #0xf
1584: d344fec4 lsr x4, x22, #4
1588: 52000298 eor w24, w20, #0x1
158c: f90037e0 str x0, [sp, #104]
1590: 1a9f07e0 cset w0, ne // ne = any
1594: 52800117 mov w23, #0x8 // #8
1598: 0a000318 and w24, w24, w0
159c: 528010f6 mov w22, #0x87 // #135
15a0: a9046bf9 stp x25, x26, [sp, #64]
15a4: d1000499 sub x25, x4, #0x1
15a8: 910263fa add x26, sp, #0x98
15ac: 14000014 b 15fc <mbedtls_aes_crypt_xts+0xfc>
15b0: 3dc00341 ldr q1, [x26]
15b4: aa1303e3 mov x3, x19
15b8: 3dc00380 ldr q0, [x28]
15bc: d1000739 sub x25, x25, #0x1
15c0: 91004366 add x6, x27, #0x10
15c4: 6e211c00 eor v0.16b, v0.16b, v1.16b
15c8: 3c810460 str q0, [x3], #16
15cc: a94797e1 ldp x1, x5, [sp, #120]
15d0: d37ffca2 lsr x2, x5, #63
15d4: 93c1fca5 extr x5, x5, x1, #63
15d8: 4b020ee2 sub w2, w23, w2, lsl #3
15dc: 1ac22ac2 asr w2, w22, w2
15e0: 93407c42 sxtw x2, w2
15e4: ca010441 eor x1, x2, x1, lsl #1
15e8: a90797e1 stp x1, x5, [sp, #120]
15ec: b100073f cmn x25, #0x1
15f0: 54000440 b.eq 1678 <mbedtls_aes_crypt_xts+0x178> //
b.none
15f4: aa0303f3 mov x19, x3
15f8: aa0603fb mov x27, x6
15fc: f100033f cmp x25, #0x0
1600: 7a400b04 ccmp w24, #0x0, #0x4, eq // eq = none
1604: 54000aa1 b.ne 1758 <mbedtls_aes_crypt_xts+0x258> //
b.any
1608: 3dc00360 ldr q0, [x27]
160c: aa1a03e3 mov x3, x26
1610: 3dc00381 ldr q1, [x28]
1614: aa1a03e2 mov x2, x26
1618: 2a1403e1 mov w1, w20
161c: aa1503e0 mov x0, x21
1620: 6e211c00 eor v0.16b, v0.16b, v1.16b
1624: 3d800340 str q0, [x26]
1628: 94000000 bl 12d0 <mbedtls_aes_crypt_ecb>
162c: 34fffc20 cbz w0, 15b0 <mbedtls_aes_crypt_xts+0xb0>
1630: a9425bf5 ldp x21, x22, [sp, #32]
1634: a94363f7 ldp x23, x24, [sp, #48]
1638: a9446bf9 ldp x25, x26, [sp, #64]
163c: a94573fb ldp x27, x28, [sp, #80]
1640: 90000001 adrp x1, 0 <__stack_chk_guard>
1644: f9400021 ldr x1, [x1]
1648: f94057e3 ldr x3, [sp, #168]
164c: f9400022 ldr x2, [x1]
1650: eb020063 subs x3, x3, x2
1654: d2800002 mov x2, #0x0 // #0
1658: 54000a01 b.ne 1798 <mbedtls_aes_crypt_xts+0x298> //
b.any
165c: a94153f3 ldp x19, x20, [sp, #16]
1660: a8cb7bfd ldp x29, x30, [sp], #176
1664: d65f03c0 ret
1668: a9425bf5 ldp x21, x22, [sp, #32]
166c: a94363f7 ldp x23, x24, [sp, #48]
1670: a94573fb ldp x27, x28, [sp, #80]
1674: 17fffff3 b 1640 <mbedtls_aes_crypt_xts+0x140>
1678: f94037e2 ldr x2, [sp, #104]
167c: b4fffda2 cbz x2, 1630 <mbedtls_aes_crypt_xts+0x130>
1680: 7100029f cmp w20, #0x0
1684: 910223f6 add x22, sp, #0x88
1688: 9a9c02d6 csel x22, x22, x28, eq // eq = none
168c: aa0303e0 mov x0, x3
1690: aa1303e1 mov x1, x19
1694: 91003f7b add x27, x27, #0xf
1698: 94000000 bl 0 <memmove>
169c: d10006c5 sub x5, x22, #0x1
16a0: d2800020 mov x0, #0x1 // #1
16a4: d503201f nop
16a8: 38606b62 ldrb w2, [x27, x0]
16ac: 8b000343 add x3, x26, x0
16b0: 386068a4 ldrb w4, [x5, x0]
16b4: aa0003e1 mov x1, x0
16b8: 91000400 add x0, x0, #0x1
16bc: 4a040042 eor w2, w2, w4
16c0: 381ff062 sturb w2, [x3, #-1]
16c4: f94037e2 ldr x2, [sp, #104]
16c8: eb02003f cmp x1, x2
16cc: 54fffee1 b.ne 16a8 <mbedtls_aes_crypt_xts+0x1a8> //
b.any
16d0: d2800203 mov x3, #0x10 // #16
16d4: 8b020265 add x5, x19, x2
16d8: cb020063 sub x3, x3, x2
16dc: 8b0202c4 add x4, x22, x2
16e0: 8b020359 add x25, x26, x2
16e4: d2800000 mov x0, #0x0 // #0
16e8: 386068a1 ldrb w1, [x5, x0]
16ec: 38606882 ldrb w2, [x4, x0]
16f0: 4a020021 eor w1, w1, w2
16f4: 38206b21 strb w1, [x25, x0]
16f8: 91000400 add x0, x0, #0x1
16fc: eb00007f cmp x3, x0
1700: 54ffff41 b.ne 16e8 <mbedtls_aes_crypt_xts+0x1e8> //
b.any
1704: 2a1403e1 mov w1, w20
1708: aa1503e0 mov x0, x21
170c: aa1a03e3 mov x3, x26
1710: aa1a03e2 mov x2, x26
1714: 94000000 bl 12d0 <mbedtls_aes_crypt_ecb>
1718: 35fff8c0 cbnz w0, 1630 <mbedtls_aes_crypt_xts+0x130>
171c: 3dc002c0 ldr q0, [x22]
1720: 3dc00341 ldr q1, [x26]
1724: 6e211c00 eor v0.16b, v0.16b, v1.16b
1728: 3d800260 str q0, [x19]
172c: a9425bf5 ldp x21, x22, [sp, #32]
1730: a94363f7 ldp x23, x24, [sp, #48]
1734: a9446bf9 ldp x25, x26, [sp, #64]
1738: a94573fb ldp x27, x28, [sp, #80]
173c: 17ffffc1 b 1640 <mbedtls_aes_crypt_xts+0x140>
1740: aa1703e2 mov x2, x23
1744: aa0303e0 mov x0, x3
1748: 52800021 mov w1, #0x1 // #1
174c: aa1c03e3 mov x3, x28
1750: 94000000 bl 0 <mbedtls_aesce_crypt_ecb>
1754: 17ffff8a b 157c <mbedtls_aes_crypt_xts+0x7c>
1758: a94797e1 ldp x1, x5, [sp, #120]
175c: a9478fe2 ldp x2, x3, [sp, #120]
1760: a9088fe2 stp x2, x3, [sp, #136]
1764: d37ffca0 lsr x0, x5, #63
1768: 93c1fca5 extr x5, x5, x1, #63
176c: 4b000ee0 sub w0, w23, w0, lsl #3
1770: 1ac02ac0 asr w0, w22, w0
1774: 93407c00 sxtw x0, w0
1778: ca010401 eor x1, x0, x1, lsl #1
177c: a90797e1 stp x1, x5, [sp, #120]
1780: 17ffffa2 b 1608 <mbedtls_aes_crypt_xts+0x108>
1784: 12800420 mov w0, #0xffffffde // #-34
1788: a9425bf5 ldp x21, x22, [sp, #32]
178c: 17ffffad b 1640 <mbedtls_aes_crypt_xts+0x140>
1790: 12800400 mov w0, #0xffffffdf // #-33
1794: 17ffffab b 1640 <mbedtls_aes_crypt_xts+0x140>
1798: a9025bf5 stp x21, x22, [sp, #32]
179c: a90363f7 stp x23, x24, [sp, #48]
17a0: a9046bf9 stp x25, x26, [sp, #64]
17a4: a90573fb stp x27, x28, [sp, #80]
17a8: 94000000 bl 0 <__stack_chk_fail>
Disassembly for mbedtls_gf128mul_x_ble: (actually, this gets inlined, but I
removed the "static inline" to get this disassembly)
0000000000001500 <mbedtls_gf128mul_x_ble>:
1500: a9401023 ldp x3, x4, [x1]
1504: 52800105 mov w5, #0x8 // #8
1508: 528010e2 mov w2, #0x87 // #135
150c: d37ffc81 lsr x1, x4, #63
1510: 93c3fc84 extr x4, x4, x3, #63
1514: 4b010ca1 sub w1, w5, w1, lsl #3
1518: 1ac12841 asr w1, w2, w1
151c: 93407c21 sxtw x1, w1
1520: ca030423 eor x3, x1, x3, lsl #1
1524: a9001003 stp x3, x4, [x0]
1528: d65f03c0 ret
