outgoing: rework the handling of the `missingroots` case to be faster The previous implementation was slow, to the point it was taking a significant amount of `hg bundle --type none-streamv2` call. We rework the code to compute the same value much faster, making the operation disappear from the `hg bundle --type none-streamv2` profile. Someone would remark that producing a streamclone does not requires an `outgoing` object. However that is a matter for another day. There is other user of `missingroots` (non stream `hg bundle` call for example), and they will also benefit from this rework. We implement an old TODO in the process, directly computing the missing and common attribute as we have most element at hand already. ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 7.750458 after: 6.665565 (-14.00%, -1.08) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 0.700229 after: 0.496050 (-29.16%, -0.20) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 346.508952 after: 316.749699 (-8.59%, -29.76) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 3.401700 after: 2.915810 (-14.28%, -0.49) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 1.870798 after: 1.461583 (-21.87%, -0.41) note: this whole `missingroots` of outgoing has a limited number of callers and could likely be replace by something simpler (like taking an explicit "missing_revs" set for example). However this is a wider change and we focus on a small impact, quick rework that does not change the API for now.

#ifndef HG_BITMANIPULATION_H
#define HG_BITMANIPULATION_H

#include <string.h>

#include "compat.h"

/* Reads a 64 bit integer from big-endian bytes. Assumes that the data is long
 enough */
static inline uint64_t getbe64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint64_t)d[0]) << 56) | (((uint64_t)d[1]) << 48) |
	        (((uint64_t)d[2]) << 40) | (((uint64_t)d[3]) << 32) |
	        (((uint64_t)d[4]) << 24) | (((uint64_t)d[5]) << 16) |
	        (((uint64_t)d[6]) << 8) | (d[7]));
}

static inline uint32_t getbe32(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((((uint32_t)d[0]) << 24) | (((uint32_t)d[1]) << 16) |
	        (((uint32_t)d[2]) << 8) | (d[3]));
}

static inline int16_t getbeint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

static inline uint16_t getbeuint16(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;

	return ((d[0] << 8) | (d[1]));
}

/* Writes a 64 bit integer to bytes in a big-endian format.
 Assumes that the buffer is long enough */
static inline void putbe64(uint64_t x, char *c)
{
	c[0] = (x >> 56) & 0xff;
	c[1] = (x >> 48) & 0xff;
	c[2] = (x >> 40) & 0xff;
	c[3] = (x >> 32) & 0xff;
	c[4] = (x >> 24) & 0xff;
	c[5] = (x >> 16) & 0xff;
	c[6] = (x >> 8) & 0xff;
	c[7] = (x)&0xff;
}

static inline void putbe32(uint32_t x, char *c)
{
	c[0] = (x >> 24) & 0xff;
	c[1] = (x >> 16) & 0xff;
	c[2] = (x >> 8) & 0xff;
	c[3] = (x)&0xff;
}

static inline double getbefloat64(const char *c)
{
	const unsigned char *d = (const unsigned char *)c;
	double ret;
	int i;
	uint64_t t = 0;
	for (i = 0; i < 8; i++) {
		t = (t << 8) + d[i];
	}
	memcpy(&ret, &t, sizeof(t));
	return ret;
}

#endif