path: root/060read.subx

# read: analogously to write, support reading from in-memory streams in
# addition to file descriptors.
#
# We can pass it either a file descriptor or an address to a stream. If a
# file descriptor is passed in, we _read from it using the right syscall. If a
# stream is passed in (a fake file descriptor), we read from it instead. This
# lets us initialize input for tests.
#
# A little counter-intuitively, the output of 'read' ends up in.. a stream. So
# tests end up doing a redundant copy. Why? Well, consider the alternatives:
#
#   a) Reading into a string, and returning a pointer to the end of the read
#   region, or a count of bytes written. Now this count or end pointer must be
#   managed separately by the caller, which can be error-prone.
#
#   b) Having 'read' return a buffer that it allocates. But there's no way to
#   know in advance how large to make the buffer. If you read less than the
#   size of the buffer you again end up needing to manage initialized vs
#   uninitialized memory.
#
#   c) Creating more helpful variants like 'read-byte' or 'read-until' which
#   also can take a file descriptor or stream, just like 'write'. But such
#   primitives don't exist in the Linux kernel, so we'd be implementing them
#   somehow, either with more internal buffering or by making multiple
#   syscalls.
#
# Reading into a stream avoids these problems. The buffer is externally
# provided and the caller has control over where it's allocated, its lifetime,
# and so on. The buffer's read and write pointers are internal to it so it's
# easier to keep in a consistent state. And it can now be passed directly to
# helpers like 'read-byte' or 'read-until' that only need to support streams,
# never file descriptors.
#
# Like with 'write', we assume our data segment will never begin at an address
# shorter than 0x08000000, so any smaller arguments are assumed to be real
# file descriptors.
#
# As a reminder, a stream looks like this:
#   write: int  # index at which to write to next
#   read: int  # index at which to read next
#   data: (array byte)  # prefixed by length as usual

== code
#   instruction                     effective address                                                   register    displacement    immediate
# . op          subop               mod             rm32          base        index         scale       r32
# . 1-3 bytes   3 bits              2 bits          3 bits        3 bits      3 bits        2 bits      2 bits      0/1/2/4 bytes   0/1/2/4 bytes

read:  # f : fd or (address stream), s : (address stream) -> num-bytes-read/eax
    # . prolog
    55/push-ebp
    89/copy                         3/mod/direct    5/rm32/ebp    .           .             .           4/r32/esp   .               .                 # copy esp to ebp
    # if (f < 0x08000000) return _read(f, s)  # f can't be a user-mode address, so treat it as a kernel file descriptor
    81          7/subop/compare     1/mod/*+disp8   5/rm32/ebp    .           .             .           .           8/disp8         0x08000000/imm32  # compare *(ebp+8)
    73/jump-if-greater-unsigned-or-equal  $read:fake/disp8
    # . . push args
    ff          6/subop/push        1/mod/*+disp8   5/rm32/ebp    .           .             .           .           0xc/disp8       .                 # push *(ebp+12)
    ff          6/subop/push        1/mod/*+disp8   5/rm32/ebp    .           .             .           .           8/disp8         .                 # push *(ebp+8)
    # . . call
    e8/call  _read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # return
    eb/jump  $read:end/disp8
$read:fake:
    # otherwise, treat 'f' as a stream to scan from
    # . save registers
    56/push-esi
    57/push-edi
    # esi = f
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           6/r32/esi   8/disp8         .                 # copy *(ebp+8) to esi
    # edi = s
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           7/r32/edi   0xc/disp8       .                 # copy *(ebp+12) to esi
    # eax = _buffer-4(out = &s->data[s->write], outend = &s->data[s->length],
    #                 in  = &f->data[f->read],  inend  = &f->data[f->write])
    # . . push &f->data[f->write]
    8b/copy                         0/mod/indirect  6/rm32/esi    .           .             .           0/r32/eax   .               .                 # copy *esi to eax
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    6/base/esi  0/index/eax   .           0/r32/eax   0xc/disp8       .                 # copy esi+eax+12 to eax
    50/push-eax
    # . . push &f->data[f->read]
    8b/copy                         1/mod/*+disp8   6/rm32/esi    .           .             .           0/r32/eax   4/disp8         .                 # copy *(esi+4) to eax
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    6/base/esi  0/index/eax   .           0/r32/eax   0xc/disp8       .                 # copy esi+eax+12 to eax
    50/push-eax
    # . . push &s->data[s->length]
    8b/copy                         1/mod/*+disp8   7/rm32/edi    .           .             .           0/r32/eax   8/disp8         .                 # copy *(edi+8) to eax
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    7/base/edi  0/index/eax   .           0/r32/eax   0xc/disp8       .                 # copy edi+eax+12 to eax
    50/push-eax
    # . . push &s->data[s->write]
    8b/copy                         0/mod/indirect  7/rm32/edi    .           .             .           0/r32/eax   .               .                 # copy *edi to eax
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    7/base/edi  0/index/eax   .           0/r32/eax   0xc/disp8       .                 # copy edi+eax+12 to eax
    50/push-eax
    # . . call
    e8/call  _buffer-4/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0x10/imm32        # add to esp
    # s->write += eax
    01/add                          0/mod/indirect  7/rm32/edi    .           .             .           0/r32/eax   .               .                 # add eax to *edi
    # f->read += eax
    01/add                          1/mod/*+disp8   6/rm32/esi    .           .             .           0/r32/eax   4/disp8         .                 # add eax to *(esi+4)
    # . restore registers
    5f/pop-to-edi
    5e/pop-to-esi
$read:end:
    # . epilog
    89/copy                         3/mod/direct    4/rm32/esp    .           .             .           5/r32/ebp   .               .                 # copy ebp to esp
    5d/pop-to-ebp
    c3/return

# - helpers

# '_buffer' is like '_append', but silently stops instead of aborting when it runs out of space

# 3-argument variant of _buffer
_buffer-3:  # out : address, outend : address, s : (array byte) -> num_bytes_buffered/eax
    # . prolog
    55/push-ebp
    89/copy                         3/mod/direct    5/rm32/ebp    .           .             .           4/r32/esp   .               .                 # copy esp to ebp
    # . save registers
    51/push-ecx
    # eax = _buffer-4(out, outend, &s->data[0], &s->data[s->length])
    # . . push &s->data[s->length]
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .                         0/r32/eax   0x10/disp8      .                 # copy *(ebp+16) to eax
    8b/copy                         0/mod/indirect  0/rm32/eax    .           .             .           1/r32/ecx   .               .                 # copy *eax to ecx
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    0/base/eax  1/index/ecx   .           1/r32/ecx   4/disp8         .                 # copy eax+ecx+4 to ecx
    51/push-ecx
    # . . push &s->data[0]
    8d/copy-address                 1/mod/*+disp8   0/rm32/eax    .           .             .           1/r32/ecx   4/disp8         .                 # copy eax+4 to ecx
    51/push-ecx
    # . . push outend
    ff          6/subop/push        1/mod/*+disp8   5/rm32/ebp    .           .             .           .           0xc/disp8       .                 # push *(ebp+12)
    # . . push out
    ff          6/subop/push        1/mod/*+disp8   5/rm32/ebp    .           .             .           .           8/disp8         .                 # push *(ebp+8)
    # . . call
    e8/call  _buffer-4/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0x10/imm32        # add to esp
$_buffer-3:end:
    # . restore registers
    59/pop-to-ecx
    # . epilog
    89/copy                         3/mod/direct    4/rm32/esp    .           .             .           5/r32/ebp   .               .                 # copy ebp to esp
    5d/pop-to-ebp
    c3/return

# 4-argument variant of _buffer
_buffer-4:  # out : address, outend : address, in : address, inend : address -> num_bytes_buffered/eax
    # . prolog
    55/push-ebp
    89/copy                         3/mod/direct    5/rm32/ebp    .           .             .           4/r32/esp   .               .                 # copy esp to ebp
    # . save registers
    51/push-ecx
    52/push-edx
    53/push-ebx
    56/push-esi
    57/push-edi
    # eax/num_bytes_buffered = 0
    b8/copy-to-eax  0/imm32
    # edi = out
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           7/r32/edi   8/disp8         .                 # copy *(ebp+8) to edi
    # edx = outend
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           2/r32/edx   0xc/disp8       .                 # copy *(ebp+12) to edx
    # esi = in
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           6/r32/esi   0x10/disp8      .                 # copy *(ebp+16) to esi
    # ecx = inend
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           1/r32/ecx   0x14/disp8      .                 # copy *(ebp+20) to ecx
$_buffer-4:loop:
    # if (in >= inend) break
    39/compare                      3/mod/direct    6/rm32/esi    .           .             .           1/r32/ecx   .               .                 # compare esi with ecx
    73/jump-if-greater-or-equal-unsigned  $_buffer-4:end/disp8
    # if (out >= outend) break  # for now silently ignore filled up buffer
    39/compare                      3/mod/direct    7/rm32/edi    .           .             .           2/r32/edx   .               .                 # compare edi with edx
    73/jump-if-greater-or-equal-unsigned  $_buffer-4:end/disp8
    # *out = *in
    8a/copy-byte                    0/mod/indirect  6/rm32/esi    .           .             .           3/r32/BL    .               .                 # copy byte at *esi to BL
    88/copy-byte                    0/mod/indirect  7/rm32/edi    .           .             .           3/r32/BL    .               .                 # copy byte at BL to *edi
    # ++num_bytes_buffered
    40/increment-eax
    # ++in
    46/increment-esi
    # ++out
    47/increment-edi
    eb/jump  $_buffer-4:loop/disp8
$_buffer-4:end:
    # . restore registers
    5f/pop-to-edi
    5e/pop-to-esi
    5b/pop-to-ebx
    5a/pop-to-edx
    59/pop-to-ecx
    # . epilog
    89/copy                         3/mod/direct    4/rm32/esp    .           .             .           5/r32/ebp   .               .                 # copy ebp to esp
    5d/pop-to-ebp
    c3/return


# idea: a clear-if-empty method on streams that clears only if f->read == f->write
# Unclear how I'd use it, though. Callers seem to need the check anyway.
# Maybe a better helper would be 'empty-stream?'

_read:  # fd : int, s : (address stream) -> num-bytes-read/eax
    # . prolog
    55/push-ebp
    89/copy                         3/mod/direct    5/rm32/ebp    .           .             .           4/r32/esp   .               .                 # copy esp to ebp
    # . save registers
    51/push-ecx
    52/push-edx
    53/push-ebx
    56/push-esi
    # esi = s
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           6/r32/esi   0xc/disp8       .                 # copy *(ebp+12) to esi
    # eax = s->write
    8b/copy                         0/mod/indirect  6/rm32/esi    .           .             .           0/r32/eax   .               .                 # copy *esi to eax
    # edx = s->length
    8b/copy                         1/mod/*+disp8   6/rm32/esi    .           .             .           2/r32/edx   8/disp8         .                 # copy *(esi+8) to edx
    # syscall(read, fd, &s->data[s->write], s->length - s->write)
    # . . fd : ebx
    8b/copy                         1/mod/*+disp8   5/rm32/ebp    .           .             .           3/r32/ebx   8/disp8         .                 # copy *(ebp+8) to ebx
    # . . data : ecx = &s->data[s->write]
    8d/copy-address                 1/mod/*+disp8   4/rm32/sib    6/base/esi  0/index/eax   .           1/r32/ecx   0xc/disp8       .                 # copy esi+eax+12 to ecx
    # . . size : edx = s->length - s->write
    29/subtract                     3/mod/direct    2/rm32/edx    .           .             .           0/r32/eax   .               .                 # subtract eax from edx
    # . . syscall
    b8/copy-to-eax  3/imm32/read
    cd/syscall  0x80/imm8
    # add the result eax to s->write
    01/add                          0/mod/indirect  6/rm32/esi    .           .             .           0/r32/eax   .               .                 # add eax to *esi
$_read:end:
    # . restore registers
    5e/pop-to-esi
    5b/pop-to-ebx
    5a/pop-to-edx
    59/pop-to-ecx
    # . epilog
    89/copy                         3/mod/direct    4/rm32/esp    .           .             .           5/r32/ebp   .               .                 # copy ebp to esp
    5d/pop-to-ebp
    c3/return

    # Two options:
    #   1 (what we have above):
    #     ecx = s
    #     eax = s->write
    #     edx = s->length
    #     # syscall
    #     ecx = lea ecx+eax+12
    #     edx = sub edx eax
    #
    #   2:
    #     ecx = s
    #     edx = s->length
    #     ecx = &s->data
    #     # syscall
    #     ecx = add ecx, s->write
    #     edx = sub edx, s->write
    #
    # Not much to choose between the two? Option 2 performs a duplicate load to
    # use one less register, but doesn't increase the amount of spilling (ecx
    # and edx must be used, and eax must be clobbered anyway).

# - tests

test-read-single:
    # - write a single character into _test-stream, then read from it
    # clear-stream(_test-stream)
    # . . push args
    68/push  _test-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # clear-stream(_test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # write(_test-stream, "Ab")
    # . . push args
    68/push  "Ab"/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  write/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # eax = read(_test-stream, _test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # check-ints-equal(eax, 2, msg)
    # . . push args
    68/push  "F - test-read-single: return value"/imm32
    68/push  2/imm32
    50/push-eax
    # . . call
    e8/call  check-ints-equal/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0xc/imm32         # add to esp
    # check-stream-equal(_test-tmp-stream, "Ab", msg)
    # . . push args
    68/push  "F - test-read-single"/imm32
    68/push  "Ab"/imm32
    68/push  _test-tmp-stream/imm32
    # . . call
    e8/call  check-stream-equal/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0xc/imm32         # add to esp
    # end
    c3/return

test-read-is-stateful:
    # - make two consecutive reads, check that their results are appended
    # clear-stream(_test-stream)
    # . . push args
    68/push  _test-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # clear-stream(_test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # write(_test-stream, "C")
    # . . push args
    68/push  "C"/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  write/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # read(_test-stream, _test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # write(_test-stream, "D")
    # . . push args
    68/push  "D"/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  write/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # read(_test-stream, _test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # check-stream-equal(_test-tmp-stream, "CD", msg)
    # . . push args
    68/push  "F - test-read-is-stateful"/imm32
    68/push  "CD"/imm32
    68/push  _test-tmp-stream/imm32
    # . . call
    e8/call  check-stream-equal/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0xc/imm32         # add to esp
    # end
    c3/return

test-read-returns-0-on-end-of-file:
    # - read after hitting end-of-file, check that result is 0
    # setup
    # . clear-stream(_test-stream)
    # . . push args
    68/push  _test-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # . clear-stream(_test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    # . . call
    e8/call  clear-stream/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               4/imm32           # add to esp
    # . write(_test-stream, "Ab")
    # . . push args
    68/push  "Ab"/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  write/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # first read gets to end-of-file
    # . read(_test-stream, _test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # second read
    # . read(_test-stream, _test-tmp-stream)
    # . . push args
    68/push  _test-tmp-stream/imm32
    68/push  _test-stream/imm32
    # . . call
    e8/call  read/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               8/imm32           # add to esp
    # check-ints-equal(eax, 0, msg)
    # . . push args
    68/push  "F - test-read-returns-0-on-end-of-file"/imm32
    68/push  0/imm32
    50/push-eax
    # . . call
    e8/call  check-ints-equal/disp32
    # . . discard args
    81          0/subop/add         3/mod/direct    4/rm32/esp    .           .             .           .           .               0xc/imm32         # add to esp
    # end
    c3/return

== data

_test-tmp-stream:
    # current write index
    0/imm32
    # current read index
    0/imm32
    # length
    8/imm32
    # data
    00 00 00 00 00 00 00 00  # 8 bytes

# . . vim:nowrap:textwidth=0