path: root/arch/x86/xen/setup.c

/*
 * Machine specific setup for xen
 *
 * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007
 */

#include <linux/init.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/pm.h>
#include <linux/memblock.h>
#include <linux/cpuidle.h>
#include <linux/cpufreq.h>

#include <asm/elf.h>
#include <asm/vdso.h>
#include <asm/e820.h>
#include <asm/setup.h>
#include <asm/acpi.h>
#include <asm/numa.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>

#include <xen/xen.h>
#include <xen/page.h>
#include <xen/interface/callback.h>
#include <xen/interface/memory.h>
#include <xen/interface/physdev.h>
#include <xen/features.h>
#include <xen/hvc-console.h>
#include "xen-ops.h"
#include "vdso.h"
#include "mmu.h"

#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)

/* Amount of extra memory space we add to the e820 ranges */
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;

/* Number of pages released from the initial allocation. */
unsigned long xen_released_pages;

/* E820 map used during setting up memory. */
static struct e820entry xen_e820_map[E820MAX] __initdata;
static u32 xen_e820_map_entries __initdata;

/*
 * Buffer used to remap identity mapped pages. We only need the virtual space.
 * The physical page behind this address is remapped as needed to different
 * buffer pages.
 */
#define REMAP_SIZE	(P2M_PER_PAGE - 3)
static struct {
	unsigned long	next_area_mfn;
	unsigned long	target_pfn;
	unsigned long	size;
	unsigned long	mfns[REMAP_SIZE];
} xen_remap_buf __initdata __aligned(PAGE_SIZE);
static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;

/* 
 * The maximum amount of extra memory compared to the base size.  The
 * main scaling factor is the size of struct page.  At extreme ratios
 * of base:extra, all the base memory can be filled with page
 * structures for the extra memory, leaving no space for anything
 * else.
 * 
 * 10x seems like a reasonable balance between scaling flexibility and
 * leaving a practically usable system.
 */
#define EXTRA_MEM_RATIO		(10)

static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);

static void __init xen_parse_512gb(void)
{
	bool val = false;
	char *arg;

	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit");
	if (!arg)
		return;

	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit=");
	if (!arg)
		val = true;
	else if (strtobool(arg + strlen("xen_512gb_limit="), &val))
		return;

	xen_512gb_limit = val;
}

static void __init xen_add_extra_mem(unsigned long start_pfn,
				     unsigned long n_pfns)
{
	int i;

	/*
	 * No need to check for zero size, should happen rarely and will only
	 * write a new entry regarded to be unused due to zero size.
	 */
	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		/* Add new region. */
		if (xen_extra_mem[i].n_pfns == 0) {
			xen_extra_mem[i].start_pfn = start_pfn;
			xen_extra_mem[i].n_pfns = n_pfns;
			break;
		}
		/* Append to existing region. */
		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
		    start_pfn) {
			xen_extra_mem[i].n_pfns += n_pfns;
			break;
		}
	}
	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
		printk(KERN_WARNING "Warning: not enough extra memory regions\n");

	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}

static void __init xen_del_extra_mem(unsigned long start_pfn,
				     unsigned long n_pfns)
{
	int i;
	unsigned long start_r, size_r;

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		start_r = xen_extra_mem[i].start_pfn;
		size_r = xen_extra_mem[i].n_pfns;

		/* Start of region. */
		if (start_r == start_pfn) {
			BUG_ON(n_pfns > size_r);
			xen_extra_mem[i].start_pfn += n_pfns;
			xen_extra_mem[i].n_pfns -= n_pfns;
			break;
		}
		/* End of region. */
		if (start_r + size_r == start_pfn + n_pfns) {
			BUG_ON(n_pfns > size_r);
			xen_extra_mem[i].n_pfns -= n_pfns;
			break;
		}
		/* Mid of region. */
		if (start_pfn > start_r && start_pfn < start_r + size_r) {
			BUG_ON(start_pfn + n_pfns > start_r + size_r);
			xen_extra_mem[i].n_pfns = start_pfn - start_r;
			/* Calling memblock_reserve() again is okay. */
			xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r -
					  (start_pfn + n_pfns));
			break;
		}
	}
	memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}

/*
 * Called during boot before the p2m list can take entries beyond the
 * hypervisor supplied p2m list. Entries in extra mem are to be regarded as
 * invalid.
 */
unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
{
	int i;

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		if (pfn >= xen_extra_mem[i].start_pfn &&
		    pfn < xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns)
			return INVALID_P2M_ENTRY;
	}

	return IDENTITY_FRAME(pfn);
}

/*
 * Mark all pfns of extra mem as invalid in p2m list.
 */
void __init xen_inv_extra_mem(void)
{
	unsigned long pfn, pfn_s, pfn_e;
	int i;

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		if (!xen_extra_mem[i].n_pfns)
			continue;
		pfn_s = xen_extra_mem[i].start_pfn;
		pfn_e = pfn_s + xen_extra_mem[i].n_pfns;
		for (pfn =