x86: extend e820 ealy_res support 32bit (a4c81cf6) · Commits · 戴 / test

arch/x86/kernel/e820.c

+214 −0

Original line number	Diff line number	Diff line
		@@ -22,7 +22,9 @@
		#include <asm/pgtable.h>
		#include <asm/page.h>
		#include <asm/e820.h>
		#include <asm/proto.h>
		#include <asm/setup.h>
		#include <asm/trampoline.h>

		struct e820map e820;

		@@ -493,3 +495,215 @@ __init void e820_setup_gap(void)
		pci_mem_start, gapstart, gapsize);
		}


		/*
		* Early reserved memory areas.
		*/
		#define MAX_EARLY_RES 20

		struct early_res {
		u64 start, end;
		char name[16];
		};
		static struct early_res early_res[MAX_EARLY_RES] __initdata = {
		{ 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */
		#if defined(CONFIG_X86_64) && defined(CONFIG_X86_TRAMPOLINE)
		{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
		#endif
		#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
		/*
		* But first pinch a few for the stack/trampoline stuff
		* FIXME: Don't need the extra page at 4K, but need to fix
		* trampoline before removing it. (see the GDT stuff)
		*/
		{ PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE" },
		/*
		* Has to be in very low memory so we can execute
		* real-mode AP code.
		*/
		{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + PAGE_SIZE, "TRAMPOLINE" },
		#endif
		{}
		};

		void __init reserve_early(u64 start, u64 end, char *name)
		{
		int i;
		struct early_res *r;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];
		if (end > r->start && start < r->end)
		panic("Overlapping early reservations %llx-%llx %s to %llx-%llx %s\n",
		start, end - 1, name?name:"", r->start,
		r->end - 1, r->name);
		}
		if (i >= MAX_EARLY_RES)
		panic("Too many early reservations");
		r = &early_res[i];
		r->start = start;
		r->end = end;
		if (name)
		strncpy(r->name, name, sizeof(r->name) - 1);
		}

		void __init free_early(u64 start, u64 end)
		{
		struct early_res *r;
		int i, j;

		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];
		if (start == r->start && end == r->end)
		break;
		}
		if (i >= MAX_EARLY_RES \|\| !early_res[i].end)
		panic("free_early on not reserved area: %llx-%llx!",
		start, end);

		for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
		;

		memmove(&early_res[i], &early_res[i + 1],
		(j - 1 - i) * sizeof(struct early_res));

		early_res[j - 1].end = 0;
		}

		void __init early_res_to_bootmem(u64 start, u64 end)
		{
		int i;
		u64 final_start, final_end;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		final_start = max(start, r->start);
		final_end = min(end, r->end);
		if (final_start >= final_end)
		continue;
		printk(KERN_INFO " early res: %d [%llx-%llx] %s\n", i,
		final_start, final_end - 1, r->name);
		#ifdef CONFIG_X86_64
		reserve_bootmem_generic(final_start, final_end - final_start);
		#else
		reserve_bootmem(final_start, final_end - final_start,
		BOOTMEM_DEFAULT);
		#endif
		}
		}

		/* Check for already reserved areas */
		static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
		{
		int i;
		u64 addr = *addrp, last;
		int changed = 0;
		again:
		last = addr + size;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		if (last >= r->start && addr < r->end) {
		*addrp = addr = round_up(r->end, align);
		changed = 1;
		goto again;
		}
		}
		return changed;
		}

		/* Check for already reserved areas */
		static inline int __init bad_addr_size(u64 addrp, u64 sizep, u64 align)
		{
		int i;
		u64 addr = *addrp, last;
		u64 size = *sizep;
		int changed = 0;
		again:
		last = addr + size;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		if (last > r->start && addr < r->start) {
		size = r->start - addr;
		changed = 1;
		goto again;
		}
		if (last > r->end && addr < r->end) {
		addr = round_up(r->end, align);
		size = last - addr;
		changed = 1;
		goto again;
		}
		if (last <= r->end && addr >= r->start) {
		(*sizep)++;
		return 0;
		}
		}
		if (changed) {
		*addrp = addr;
		*sizep = size;
		}
		return changed;
		}

		/*
		* Find a free area with specified alignment in a specific range.
		*/
		u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align)
		{
		int i;

		for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 addr, last;
		u64 ei_last;

		if (ei->type != E820_RAM)
		continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
		addr = round_up(start, align);
		if (addr >= ei_last)
		continue;
		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
		;
		last = addr + size;
		if (last > ei_last)
		continue;
		if (last > end)
		continue;
		return addr;
		}
		return -1ULL;
		}

		/*
		* Find next free range after *start
		*/
		u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align)
		{
		int i;

		for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		u64 addr, last;
		u64 ei_last;

		if (ei->type != E820_RAM)
		continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
		addr = round_up(start, align);
		if (addr >= ei_last)
		continue;
		*sizep = ei_last - addr;
		while (bad_addr_size(&addr, sizep, align) &&
		addr + *sizep <= ei_last)
		;
		last = addr + *sizep;
		if (last > ei_last)
		continue;
		return addr;
		}
		return -1UL;

		}

arch/x86/kernel/e820_64.c

+0 −196

Original line number	Diff line number	Diff line
		@@ -46,202 +46,6 @@ unsigned long max_pfn_mapped;
		*/
		static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT;

		/*
		* Early reserved memory areas.
		*/
		#define MAX_EARLY_RES 20

		struct early_res {
		unsigned long start, end;
		char name[16];
		};
		static struct early_res early_res[MAX_EARLY_RES] __initdata = {
		{ 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */
		#ifdef CONFIG_X86_TRAMPOLINE
		{ TRAMPOLINE_BASE, TRAMPOLINE_BASE + 2 * PAGE_SIZE, "TRAMPOLINE" },
		#endif
		{}
		};

		void __init reserve_early(unsigned long start, unsigned long end, char *name)
		{
		int i;
		struct early_res *r;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];
		if (end > r->start && start < r->end)
		panic("Overlapping early reservations %lx-%lx %s to %lx-%lx %s\n",
		start, end - 1, name?name:"", r->start, r->end - 1, r->name);
		}
		if (i >= MAX_EARLY_RES)
		panic("Too many early reservations");
		r = &early_res[i];
		r->start = start;
		r->end = end;
		if (name)
		strncpy(r->name, name, sizeof(r->name) - 1);
		}

		void __init free_early(unsigned long start, unsigned long end)
		{
		struct early_res *r;
		int i, j;

		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		r = &early_res[i];
		if (start == r->start && end == r->end)
		break;
		}
		if (i >= MAX_EARLY_RES \|\| !early_res[i].end)
		panic("free_early on not reserved area: %lx-%lx!", start, end);

		for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++)
		;

		memmove(&early_res[i], &early_res[i + 1],
		(j - 1 - i) * sizeof(struct early_res));

		early_res[j - 1].end = 0;
		}

		void __init early_res_to_bootmem(unsigned long start, unsigned long end)
		{
		int i;
		unsigned long final_start, final_end;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		final_start = max(start, r->start);
		final_end = min(end, r->end);
		if (final_start >= final_end)
		continue;
		printk(KERN_INFO " early res: %d [%lx-%lx] %s\n", i,
		final_start, final_end - 1, r->name);
		reserve_bootmem_generic(final_start, final_end - final_start);
		}
		}

		/* Check for already reserved areas */
		static inline int __init
		bad_addr(unsigned long *addrp, unsigned long size, unsigned long align)
		{
		int i;
		unsigned long addr = *addrp, last;
		int changed = 0;
		again:
		last = addr + size;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		if (last >= r->start && addr < r->end) {
		*addrp = addr = round_up(r->end, align);
		changed = 1;
		goto again;
		}
		}
		return changed;
		}

		/* Check for already reserved areas */
		static inline int __init
		bad_addr_size(unsigned long addrp, unsigned long sizep, unsigned long align)
		{
		int i;
		unsigned long addr = *addrp, last;
		unsigned long size = *sizep;
		int changed = 0;
		again:
		last = addr + size;
		for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
		struct early_res *r = &early_res[i];
		if (last > r->start && addr < r->start) {
		size = r->start - addr;
		changed = 1;
		goto again;
		}
		if (last > r->end && addr < r->end) {
		addr = round_up(r->end, align);
		size = last - addr;
		changed = 1;
		goto again;
		}
		if (last <= r->end && addr >= r->start) {
		(*sizep)++;
		return 0;
		}
		}
		if (changed) {
		*addrp = addr;
		*sizep = size;
		}
		return changed;
		}

		/*
		* Find a free area with specified alignment in a specific range.
		*/
		unsigned long __init find_e820_area(unsigned long start, unsigned long end,
		unsigned long size, unsigned long align)
		{
		int i;

		for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		unsigned long addr, last;
		unsigned long ei_last;

		if (ei->type != E820_RAM)
		continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
		addr = round_up(start, align);
		if (addr >= ei_last)
		continue;
		while (bad_addr(&addr, size, align) && addr+size <= ei_last)
		;
		last = addr + size;
		if (last > ei_last)
		continue;
		if (last > end)
		continue;
		return addr;
		}
		return -1UL;
		}

		/*
		* Find next free range after *start
		*/
		unsigned long __init find_e820_area_size(unsigned long start,
		unsigned long *sizep,
		unsigned long align)
		{
		int i;

		for (i = 0; i < e820.nr_map; i++) {
		struct e820entry *ei = &e820.map[i];
		unsigned long addr, last;
		unsigned long ei_last;

		if (ei->type != E820_RAM)
		continue;
		addr = round_up(ei->addr, align);
		ei_last = ei->addr + ei->size;
		if (addr < start)
		addr = round_up(start, align);
		if (addr >= ei_last)
		continue;
		*sizep = ei_last - addr;
		while (bad_addr_size(&addr, sizep, align) &&
		addr + *sizep <= ei_last)
		;
		last = addr + *sizep;
		if (last > ei_last)
		continue;
		return addr;
		}
		return -1UL;

		}
		/*
		* Find the highest page frame number we have available
		*/

arch/x86/kernel/head32.c

+76 −0

Original line number	Diff line number	Diff line
		@@ -8,7 +8,83 @@
		#include <linux/init.h>
		#include <linux/start_kernel.h>

		#include <asm/setup.h>
		#include <asm/sections.h>
		#include <asm/e820.h>
		#include <asm/bios_ebda.h>

		#define BIOS_LOWMEM_KILOBYTES 0x413

		/*
		* The BIOS places the EBDA/XBDA at the top of conventional
		* memory, and usually decreases the reported amount of
		* conventional memory (int 0x12) too. This also contains a
		* workaround for Dell systems that neglect to reserve EBDA.
		* The same workaround also avoids a problem with the AMD768MPX
		* chipset: reserve a page before VGA to prevent PCI prefetch
		* into it (errata #56). Usually the page is reserved anyways,
		* unless you have no PS/2 mouse plugged in.
		*/
		static void __init reserve_ebda_region(void)
		{
		unsigned int lowmem, ebda_addr;

		/* To determine the position of the EBDA and the */
		/* end of conventional memory, we need to look at */
		/* the BIOS data area. In a paravirtual environment */
		/* that area is absent. We'll just have to assume */
		/* that the paravirt case can handle memory setup */
		/* correctly, without our help. */
		if (paravirt_enabled())
		return;

		/* end of low (conventional) memory */
		lowmem = (unsigned short )__va(BIOS_LOWMEM_KILOBYTES);
		lowmem <<= 10;

		/* start of EBDA area */
		ebda_addr = get_bios_ebda();

		/* Fixup: bios puts an EBDA in the top 64K segment */
		/* of conventional memory, but does not adjust lowmem. */
		if ((lowmem - ebda_addr) <= 0x10000)
		lowmem = ebda_addr;

		/* Fixup: bios does not report an EBDA at all. */
		/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
		if ((ebda_addr == 0) && (lowmem >= 0x9f000))
		lowmem = 0x9f000;

		/* Paranoia: should never happen, but... */
		if ((lowmem == 0) \|\| (lowmem >= 0x100000))
		lowmem = 0x9f000;

		/* reserve all memory between lowmem and the 1MB mark */
		reserve_early(lowmem, 0x100000, "BIOS reserved");
		}

		void __init i386_start_kernel(void)
		{
		reserve_early(__pa_symbol(&_text), __pa_symbol(&_end), "TEXT DATA BSS");

		#ifdef CONFIG_BLK_DEV_INITRD
		/* Reserve INITRD */
		if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
		u64 ramdisk_size = boot_params.hdr.ramdisk_size;
		u64 ramdisk_end = ramdisk_image + ramdisk_size;
		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
		}
		#endif
		reserve_early(__pa_symbol(&_end), init_pg_tables_end, "INIT_PG_TABLE");

		reserve_ebda_region();

		/*
		* At this point everything still needed from the boot loader
		* or BIOS or kernel text should be early reserved or marked not
		* RAM in e820. All other memory is free game.
		*/

		start_kernel();
		}

arch/x86/kernel/setup_32.c

+23 −86

Original line number	Diff line number	Diff line
		@@ -359,56 +359,6 @@ unsigned long __init find_max_low_pfn(void)
		return max_low_pfn;
		}

		#define BIOS_LOWMEM_KILOBYTES 0x413

		/*
		* The BIOS places the EBDA/XBDA at the top of conventional
		* memory, and usually decreases the reported amount of
		* conventional memory (int 0x12) too. This also contains a
		* workaround for Dell systems that neglect to reserve EBDA.
		* The same workaround also avoids a problem with the AMD768MPX
		* chipset: reserve a page before VGA to prevent PCI prefetch
		* into it (errata #56). Usually the page is reserved anyways,
		* unless you have no PS/2 mouse plugged in.
		*/
		static void __init reserve_ebda_region(void)
		{
		unsigned int lowmem, ebda_addr;

		/* To determine the position of the EBDA and the */
		/* end of conventional memory, we need to look at */
		/* the BIOS data area. In a paravirtual environment */
		/* that area is absent. We'll just have to assume */
		/* that the paravirt case can handle memory setup */
		/* correctly, without our help. */
		if (paravirt_enabled())
		return;

		/* end of low (conventional) memory */
		lowmem = (unsigned short )__va(BIOS_LOWMEM_KILOBYTES);
		lowmem <<= 10;

		/* start of EBDA area */
		ebda_addr = get_bios_ebda();

		/* Fixup: bios puts an EBDA in the top 64K segment */
		/* of conventional memory, but does not adjust lowmem. */
		if ((lowmem - ebda_addr) <= 0x10000)
		lowmem = ebda_addr;

		/* Fixup: bios does not report an EBDA at all. */
		/* Some old Dells seem to need 4k anyhow (bugzilla 2990) */
		if ((ebda_addr == 0) && (lowmem >= 0x9f000))
		lowmem = 0x9f000;

		/* Paranoia: should never happen, but... */
		if ((lowmem == 0) \|\| (lowmem >= 0x100000))
		lowmem = 0x9f000;

		/* reserve all memory between lowmem and the 1MB mark */
		reserve_bootmem(lowmem, 0x100000 - lowmem, BOOTMEM_DEFAULT);
		}

		#ifndef CONFIG_NEED_MULTIPLE_NODES
		static void __init setup_bootmem_allocator(void);
		static unsigned long __init setup_memory(void)
		@@ -522,25 +472,32 @@ static void __init reserve_initrd(void)
		unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT;
		unsigned long ramdisk_here;

		initrd_start = 0;

		if (!boot_params.hdr.type_of_loader \|\|
		!ramdisk_image \|\| !ramdisk_size)
		return; /* No initrd provided by bootloader */

		initrd_start = 0;

		if (ramdisk_end < ramdisk_image) {
		free_bootmem(ramdisk_image, ramdisk_size);
		printk(KERN_ERR "initrd wraps around end of memory, "
		"disabling initrd\n");
		return;
		}
		if (ramdisk_size >= end_of_lowmem/2) {
		free_bootmem(ramdisk_image, ramdisk_size);
		printk(KERN_ERR "initrd too large to handle, "
		"disabling initrd\n");
		return;
		}

		if (ramdisk_end <= end_of_lowmem) {
		/* All in lowmem, easy case */
		reserve_bootmem(ramdisk_image, ramdisk_size, BOOTMEM_DEFAULT);
		/*
		* don't need to reserve again, already reserved early
		* in i386_start_kernel, and early_res_to_bootmem
		* convert that to reserved in bootmem
		*/
		initrd_start = ramdisk_image + PAGE_OFFSET;
		initrd_end = initrd_start+ramdisk_size;
		return;
		@@ -582,6 +539,8 @@ static void __init relocate_initrd(void)
		p = (char *)__va(ramdisk_image);
		memcpy(q, p, clen);
		q += clen;
		/* need to free these low pages...*/
		free_bootmem(ramdisk_image, clen);
		ramdisk_image += clen;
		ramdisk_size -= clen;
		}
		@@ -600,47 +559,28 @@ static void __init relocate_initrd(void)
		ramdisk_image += clen;
		ramdisk_size -= clen;
		}
		/* high pages is not converted by early_res_to_bootmem */
		}

		#endif /* CONFIG_BLK_DEV_INITRD */

		void __init setup_bootmem_allocator(void)
		{
		unsigned long bootmap_size;
		unsigned long bootmap_size, bootmap;
		/*
		* Initialize the boot-time allocator (with low memory only):
		*/
		bootmap_size = init_bootmem(min_low_pfn, max_low_pfn);

		bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
		bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT,
		max_low_pfn<<PAGE_SHIFT, bootmap_size,
		PAGE_SIZE);
		if (bootmap == -1L)
		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
		bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, max_low_pfn);
		register_bootmem_low_pages(max_low_pfn);
		early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
		reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);

		/*
		* Reserve the bootmem bitmap itself as well. We do this in two
		* steps (first step was init_bootmem()) because this catches
		* the (very unlikely) case of us accidentally initializing the
		* bootmem allocator with an invalid RAM area.
		*/
		reserve_bootmem(__pa_symbol(_text), (PFN_PHYS(min_low_pfn) +
		bootmap_size + PAGE_SIZE-1) - __pa_symbol(_text),
		BOOTMEM_DEFAULT);

		/*
		* reserve physical page 0 - it's a special BIOS page on many boxes,
		* enabling clean reboots, SMP operation, laptop functions.
		*/
		reserve_bootmem(0, PAGE_SIZE, BOOTMEM_DEFAULT);

		/* reserve EBDA region */
		reserve_ebda_region();

		#ifdef CONFIG_SMP
		/*
		* But first pinch a few for the stack/trampoline stuff
		* FIXME: Don't need the extra page at 4K, but need to fix
		* trampoline before removing it. (see the GDT stuff)
		*/
		reserve_bootmem(PAGE_SIZE, PAGE_SIZE, BOOTMEM_DEFAULT);
		#endif
		#ifdef CONFIG_ACPI_SLEEP
		/*
		* Reserve low memory region for sleep support.
		@@ -803,9 +743,6 @@ void __init setup_arch(char **cmdline_p)
		* not to exceed the 8Mb limit.
		*/

		#ifdef CONFIG_SMP
		smp_alloc_memory(); /* AP processor realmode stacks in low memory*/
		#endif
		paging_init();

		/*

arch/x86/kernel/smpboot.c

+0 −17

Original line number	Diff line number	Diff line
		@@ -555,23 +555,6 @@ cpumask_t cpu_coregroup_map(int cpu)
		return c->llc_shared_map;
		}

		#ifdef CONFIG_X86_32
		/*
		* We are called very early to get the low memory for the
		* SMP bootup trampoline page.
		*/
		void __init smp_alloc_memory(void)
		{
		trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
		/*
		* Has to be in very low memory so we can execute
		* real-mode AP code.
		*/
		if (__pa(trampoline_base) >= 0x9F000)
		BUG();
		}
		#endif

		static void impress_friends(void)
		{
		int cpu;

Admin message