memmove_P and 'flash / not flash' address comparison

[mcspr]

Looking at the current memmove_P implementation
https://github.com/earlephilhower/newlib-xtensa/blob/ebc967552ce827f21fc579fd8c437037c1b472ab/newlib/libc/sys/xtensa/string_pgmspace.c#L184-L190

It branches between two different functions, depending on the pointer address. Since it is checking for a number with only one bit set... I wondered if just checking that fact does anything to the code, since we could simply discard the idea that it is going to be used on any 'higher' addresses.

// > cat memmove.c
#include <stddef.h>
#include <stdint.h>
#include <stdbool.h>
#include <string.h>
#include <sys/pgmspace.h>

inline static bool inFlash(const void* ptr) {
    // common comparison would use >=0x40000000
    // instead, slightly reduce the footprint by
    // checking *only* for numbers below it
    static const uintptr_t Mask = 1 << 30;
    return ((uintptr_t)(ptr) & Mask) > 0;
}

void* memmove_P2 (void* dest, const void* src, size_t n) {
    if (inFlash(src) && !inFlash(dest)) {
        return memcpy_P(dest, src, n);
    } else {
        return memmove(dest, src, n);
    }
}

void* memmove_P1 (void* dest, const void* src, size_t n)
{
    if ( ((const char *)src >= (const char *)0x40000000) && ((const char *)dest < (const char *)0x40000000) )
        return memcpy_P(dest, src, n);
    else
        return memmove(dest, src, n);
}

Turns out it does

• the resulting func 5 bytes smaller :)
• makes it consistent between optimization levels. original variant utilizes mov + ssli shift that generates const number with 30th bit set with size optimization and l32r of the const value on other levels. here we just generate it directly, regardless of the level used

Not sure how to benchmark it, though, or whether these different instructions do anything to the overall performance
(or, anything at all, since this is just mildly improving memmove operations that are probably not that frequently performed)

> xtensa-lx106-elf-gcc -c -Os memmove.c
> xtensa-lx106-elf-nm --radix=d -S memmove.o | grep memmove
         U memmove
00000020 00000023 T memmove_P1
00000000 00000018 T memmove_P2
> xtensa-lx106-elf-gcc -S -Os memmove.c

    .file   "memmove.c"
    .text
    .literal_position
    .align  4
    .global memmove_P2
    .type   memmove_P2, @function
memmove_P2:
    bbci    a3, 30, .L2    ; branch on bit set / unset
    bbsi    a2, 30, .L2
    j.l memcpy_P, a9
.L2:
    j.l memmove, a9
    .size   memmove_P2, .-memmove_P2
    .literal_position
    .align  4
    .global memmove_P1
    .type   memmove_P1, @function
memmove_P1:
    movi.n  a5, -1        ; btw this only happens on Os, O2 and O3 use l32r const of 0x40000000
    srli    a5, a5, 2
    bgeu    a5, a3, .L7
    bltu    a5, a2, .L7
    j.l memcpy_P, a9
.L7:
    j.l memmove, a9
    .size   memmove_P1, .-memmove_P1
    .ident  "GCC: (GNU) 10.3.0"