From b79cd8f1268bab57ff85b19d131f7f23deab2dee Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 11 May 2008 00:30:15 -0700 Subject: x86: make e820.c to have common functions remove the duplicated copy of these functions. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 475 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 475 insertions(+) create mode 100644 arch/x86/kernel/e820.c (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c new file mode 100644 index 00000000000..2cb686f60d0 --- /dev/null +++ b/arch/x86/kernel/e820.c @@ -0,0 +1,475 @@ +/* + * Handle the memory map. + * The functions here do the job until bootmem takes over. + * + * Getting sanitize_e820_map() in sync with i386 version by applying change: + * - Provisions for empty E820 memory regions (reported by certain BIOSes). + * Alex Achenbach , December 2002. + * Venkatesh Pallipadi + * + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +struct e820map e820; + +/* For PCI or other memory-mapped resources */ +unsigned long pci_mem_start = 0xaeedbabe; +#ifdef CONFIG_PCI +EXPORT_SYMBOL(pci_mem_start); +#endif + +/* + * This function checks if any part of the range is mapped + * with type. + */ +int +e820_any_mapped(u64 start, u64 end, unsigned type) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (type && ei->type != type) + continue; + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(e820_any_mapped); + +/* + * This function checks if the entire range is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init e820_all_mapped(u64 start, u64 end, unsigned type) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + + /* if the region is at the beginning of we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* + * if start is now at or beyond end, we're done, full + * coverage + */ + if (start >= end) + return 1; + } + return 0; +} + +/* + * Add a memory region to the kernel e820 map. + */ +void __init add_memory_region(u64 start, u64 size, int type) +{ + int x = e820.nr_map; + + if (x == E820MAX) { + printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); + return; + } + + e820.map[x].addr = start; + e820.map[x].size = size; + e820.map[x].type = type; + e820.nr_map++; +} + +void __init e820_print_map(char *who) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + printk(KERN_INFO " %s: %016Lx - %016Lx ", who, + (unsigned long long) e820.map[i].addr, + (unsigned long long) + (e820.map[i].addr + e820.map[i].size)); + switch (e820.map[i].type) { + case E820_RAM: + printk(KERN_CONT "(usable)\n"); + break; + case E820_RESERVED: + printk(KERN_CONT "(reserved)\n"); + break; + case E820_ACPI: + printk(KERN_CONT "(ACPI data)\n"); + break; + case E820_NVS: + printk(KERN_CONT "(ACPI NVS)\n"); + break; + default: + printk(KERN_CONT "type %u\n", e820.map[i].type); + break; + } + } +} + +/* + * Sanitize the BIOS e820 map. + * + * Some e820 responses include overlapping entries. The following + * replaces the original e820 map with a new one, removing overlaps. + * + */ +int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map) +{ + struct change_member { + struct e820entry *pbios; /* pointer to original bios entry */ + unsigned long long addr; /* address for this change point */ + }; + static struct change_member change_point_list[2*E820MAX] __initdata; + static struct change_member *change_point[2*E820MAX] __initdata; + static struct e820entry *overlap_list[E820MAX] __initdata; + static struct e820entry new_bios[E820MAX] __initdata; + struct change_member *change_tmp; + unsigned long current_type, last_type; + unsigned long long last_addr; + int chgidx, still_changing; + int overlap_entries; + int new_bios_entry; + int old_nr, new_nr, chg_nr; + int i; + + /* + Visually we're performing the following + (1,2,3,4 = memory types)... + + Sample memory map (w/overlaps): + ____22__________________ + ______________________4_ + ____1111________________ + _44_____________________ + 11111111________________ + ____________________33__ + ___________44___________ + __________33333_________ + ______________22________ + ___________________2222_ + _________111111111______ + _____________________11_ + _________________4______ + + Sanitized equivalent (no overlap): + 1_______________________ + _44_____________________ + ___1____________________ + ____22__________________ + ______11________________ + _________1______________ + __________3_____________ + ___________44___________ + _____________33_________ + _______________2________ + ________________1_______ + _________________4______ + ___________________2____ + ____________________33__ + ______________________4_ + */ + + /* if there's only one memory region, don't bother */ + if (*pnr_map < 2) + return -1; + + old_nr = *pnr_map; + + /* bail out if we find any unreasonable addresses in bios map */ + for (i = 0; i < old_nr; i++) + if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + return -1; + + /* create pointers for initial change-point information (for sorting) */ + for (i = 0; i < 2 * old_nr; i++) + change_point[i] = &change_point_list[i]; + + /* record all known change-points (starting and ending addresses), + omitting those that are for empty memory regions */ + chgidx = 0; + for (i = 0; i < old_nr; i++) { + if (biosmap[i].size != 0) { + change_point[chgidx]->addr = biosmap[i].addr; + change_point[chgidx++]->pbios = &biosmap[i]; + change_point[chgidx]->addr = biosmap[i].addr + + biosmap[i].size; + change_point[chgidx++]->pbios = &biosmap[i]; + } + } + chg_nr = chgidx; + + /* sort change-point list by memory addresses (low -> high) */ + still_changing = 1; + while (still_changing) { + still_changing = 0; + for (i = 1; i < chg_nr; i++) { + unsigned long long curaddr, lastaddr; + unsigned long long curpbaddr, lastpbaddr; + + curaddr = change_point[i]->addr; + lastaddr = change_point[i - 1]->addr; + curpbaddr = change_point[i]->pbios->addr; + lastpbaddr = change_point[i - 1]->pbios->addr; + + /* + * swap entries, when: + * + * curaddr > lastaddr or + * curaddr == lastaddr and curaddr == curpbaddr and + * lastaddr != lastpbaddr + */ + if (curaddr < lastaddr || + (curaddr == lastaddr && curaddr == curpbaddr && + lastaddr != lastpbaddr)) { + change_tmp = change_point[i]; + change_point[i] = change_point[i-1]; + change_point[i-1] = change_tmp; + still_changing = 1; + } + } + } + + /* create a new bios memory map, removing overlaps */ + overlap_entries = 0; /* number of entries in the overlap table */ + new_bios_entry = 0; /* index for creating new bios map entries */ + last_type = 0; /* start with undefined memory type */ + last_addr = 0; /* start with 0 as last starting address */ + + /* loop through change-points, determining affect on the new bios map */ + for (chgidx = 0; chgidx < chg_nr; chgidx++) { + /* keep track of all overlapping bios entries */ + if (change_point[chgidx]->addr == + change_point[chgidx]->pbios->addr) { + /* + * add map entry to overlap list (> 1 entry + * implies an overlap) + */ + overlap_list[overlap_entries++] = + change_point[chgidx]->pbios; + } else { + /* + * remove entry from list (order independent, + * so swap with last) + */ + for (i = 0; i < overlap_entries; i++) { + if (overlap_list[i] == + change_point[chgidx]->pbios) + overlap_list[i] = + overlap_list[overlap_entries-1]; + } + overlap_entries--; + } + /* + * if there are overlapping entries, decide which + * "type" to use (larger value takes precedence -- + * 1=usable, 2,3,4,4+=unusable) + */ + current_type = 0; + for (i = 0; i < overlap_entries; i++) + if (overlap_list[i]->type > current_type) + current_type = overlap_list[i]->type; + /* + * continue building up new bios map based on this + * information + */ + if (current_type != last_type) { + if (last_type != 0) { + new_bios[new_bios_entry].size = + change_point[chgidx]->addr - last_addr; + /* + * move forward only if the new size + * was non-zero + */ + if (new_bios[new_bios_entry].size != 0) + /* + * no more space left for new + * bios entries ? + */ + if (++new_bios_entry >= E820MAX) + break; + } + if (current_type != 0) { + new_bios[new_bios_entry].addr = + change_point[chgidx]->addr; + new_bios[new_bios_entry].type = current_type; + last_addr = change_point[chgidx]->addr; + } + last_type = current_type; + } + } + /* retain count for new bios entries */ + new_nr = new_bios_entry; + + /* copy new bios mapping into original location */ + memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry)); + *pnr_map = new_nr; + + return 0; +} + +/* + * Copy the BIOS e820 map into a safe place. + * + * Sanity-check it while we're at it.. + * + * If we're lucky and live on a modern system, the setup code + * will have given us a memory map that we can use to properly + * set up memory. If we aren't, we'll fake a memory map. + */ +int __init copy_e820_map(struct e820entry *biosmap, int nr_map) +{ + /* Only one memory region (or negative)? Ignore it */ + if (nr_map < 2) + return -1; + + do { + u64 start = biosmap->addr; + u64 size = biosmap->size; + u64 end = start + size; + u32 type = biosmap->type; + + /* Overflow in 64 bits? Ignore the memory map. */ + if (start > end) + return -1; + + add_memory_region(start, size, type); + } while (biosmap++, --nr_map); + return 0; +} + +u64 __init update_memory_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + int i; + u64 real_updated_size = 0; + + BUG_ON(old_type == new_type); + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + if (ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && + (ei->addr + ei->size) <= (start + size)) { + ei->type = new_type; + real_updated_size += ei->size; + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + add_memory_region(final_start, final_end - final_start, + new_type); + real_updated_size += final_end - final_start; + } + return real_updated_size; +} + +void __init update_e820(void) +{ + u8 nr_map; + + nr_map = e820.nr_map; + if (sanitize_e820_map(e820.map, &nr_map)) + return; + e820.nr_map = nr_map; + printk(KERN_INFO "modified physical RAM map:\n"); + e820_print_map("modified"); +} + +/* + * Search for the biggest gap in the low 32 bits of the e820 + * memory space. We pass this space to PCI to assign MMIO resources + * for hotplug or unconfigured devices in. + * Hopefully the BIOS let enough space left. + */ +__init void e820_setup_gap(void) +{ + unsigned long gapstart, gapsize, round; + unsigned long long last; + int i; + int found = 0; + + last = 0x100000000ull; + gapstart = 0x10000000; + gapsize = 0x400000; + i = e820.nr_map; + while (--i >= 0) { + unsigned long long start = e820.map[i].addr; + unsigned long long end = start + e820.map[i].size; + + /* + * Since "last" is at most 4GB, we know we'll + * fit in 32 bits if this condition is true + */ + if (last > end) { + unsigned long gap = last - end; + + if (gap > gapsize) { + gapsize = gap; + gapstart = end; + found = 1; + } + } + if (start < last) + last = start; + } + +#ifdef CONFIG_X86_64 + if (!found) { + gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024; + printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit " + "address range\n" + KERN_ERR "PCI: Unassigned devices with 32bit resource " + "registers may break!\n"); + } +#endif + + /* + * See how much we want to round up: start off with + * rounding to the next 1MB area. + */ + round = 0x100000; + while ((gapsize >> 4) > round) + round += round; + /* Fun with two's complement */ + pci_mem_start = (gapstart + round) & -round; + + printk(KERN_INFO + "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", + pci_mem_start, gapstart, gapsize); +} + -- cgit v1.2.3 From c3965bd15118742d72b4bc1a290d37b3f081eb98 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 14 May 2008 08:15:34 -0700 Subject: x86 boot: proper use of ARRAY_SIZE instead of repeated E820MAX constant This patch is motivated by a subsequent patch which will allow for more memory map entries on EFI supported systems than can be passed via the x86 legacy BIOS E820 interface. The legacy interface is limited to E820MAX == 128 memory entries, and that "E820MAX" manifest constant was used as the size for several arrays and loops over those arrays. The primary change in this patch is to change code loop sizes over those arrays from using the constant E820MAX, to using the ARRAY_SIZE() macro evaluated for the array being looped. That way, a subsequent patch can change the size of some of these arrays, without breaking this code. This patch also adds a parameter to the sanitize_e820_map() routine, which had an implicit size for the array passed it of E820MAX entries. This new parameter explicitly passes the size of said array. Once again, this will allow a subsequent patch to change that array size for some calls to sanitize_e820_map() without breaking the code. As part of enhancing the sanitize_e820_map() interface this way, I further combined the unnecessarily distinct x86_32 and x86_64 declarations for this routine into a single, commonly used, declaration. This patch in itself should make no difference to the resulting kernel binary. [ mingo@elte.hu: merged to -tip ] Signed-off-by: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2cb686f60d0..2396b9da802 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -95,7 +95,7 @@ void __init add_memory_region(u64 start, u64 size, int type) { int x = e820.nr_map; - if (x == E820MAX) { + if (x == ARRAY_SIZE(e820.map)) { printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); return; } @@ -142,7 +142,8 @@ void __init e820_print_map(char *who) * replaces the original e820 map with a new one, removing overlaps. * */ -int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map) +int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, + char *pnr_map) { struct change_member { struct e820entry *pbios; /* pointer to original bios entry */ @@ -314,7 +315,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, char *pnr_map) * no more space left for new * bios entries ? */ - if (++new_bios_entry >= E820MAX) + if (++new_bios_entry >= max_nr_map) break; } if (current_type != 0) { @@ -403,7 +404,7 @@ void __init update_e820(void) u8 nr_map; nr_map = e820.nr_map; - if (sanitize_e820_map(e820.map, &nr_map)) + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) return; e820.nr_map = nr_map; printk(KERN_INFO "modified physical RAM map:\n"); -- cgit v1.2.3 From 028b785888c523baccdf27af0cdbf1deb92edec0 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 14 May 2008 08:15:40 -0700 Subject: x86 boot: extend some internal memory map arrays to handle larger EFI input Extend internal boot time memory tables to allow for up to three entries per node, which may be larger than the 128 E820MAX entries handled by the legacy BIOS E820 interface. The EFI interface, if present, is capable of passing memory map entries for these larger node counts. This patch requires an earlier patch that rewrote code depending on these array sizes from using E820MAX explicitly to size loops, to instead using ARRAY_SIZE() of the applicable array. Another patch following this one will provide the code to pick up additional memory entries passed via the EFI interface from the BIOS and insert them in the following, now enlarged, arrays. Signed-off-by: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2396b9da802..3f7777b255a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,10 +149,10 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, struct e820entry *pbios; /* pointer to original bios entry */ unsigned long long addr; /* address for this change point */ }; - static struct change_member change_point_list[2*E820MAX] __initdata; - static struct change_member *change_point[2*E820MAX] __initdata; - static struct e820entry *overlap_list[E820MAX] __initdata; - static struct e820entry new_bios[E820MAX] __initdata; +static struct change_member change_point_list[2*E820_X_MAX] __initdata; +static struct change_member *change_point[2*E820_X_MAX] __initdata; +static struct e820entry *overlap_list[E820_X_MAX] __initdata; +static struct e820entry new_bios[E820_X_MAX] __initdata; struct change_member *change_tmp; unsigned long current_type, last_type; unsigned long long last_addr; -- cgit v1.2.3 From 6e9bcc796b120d17b08dde7ab958b82ddb899889 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 14 May 2008 08:15:46 -0700 Subject: x86 boot: change sanitize_e820_map parameter from byte to int to allow bigger memory maps The map size counter passed into, and back out of, sanitize_e820_map(), was an eight bit type (char or u8), as derived from its origins in legacy BIOS E820 structures. This patch changes that type to an 'int', to allow this sanitize routine to also be used on larger maps (larger than the 256 count that fits in a char). The legacy BIOS E820 interface of course does not change; that remains at 8 bits for this count, holding up to E820MAX == 128 entries. But the kernel internals can handle more when those additional memory map entries are passed from the BIOS via EFI interfaces. Signed-off-by: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 3f7777b255a..91abf5b2fb9 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -143,7 +143,7 @@ void __init e820_print_map(char *who) * */ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - char *pnr_map) + int *pnr_map) { struct change_member { struct e820entry *pbios; /* pointer to original bios entry */ @@ -204,6 +204,7 @@ static struct e820entry new_bios[E820_X_MAX] __initdata; return -1; old_nr = *pnr_map; + BUG_ON(old_nr > max_nr_map); /* bail out if we find any unreasonable addresses in bios map */ for (i = 0; i < old_nr; i++) @@ -401,7 +402,7 @@ u64 __init update_memory_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - u8 nr_map; + int nr_map; nr_map = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) -- cgit v1.2.3 From 5b7eb2e9ef4e467a1248537b47a63bab265be3cc Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 14 May 2008 08:15:52 -0700 Subject: x86 boot: longer comment explaining sanitize_e820_map routine Elaborate on the comment for sanitize_e820_map(), epxlaining more what it does, what it inputs, and what it returns. Rearrange the placement of this comment to fit kernel conventions, before the routine's code rather than buried inside it. Signed-off-by: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 94 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 56 insertions(+), 38 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 91abf5b2fb9..41c480ae47d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -139,9 +139,64 @@ void __init e820_print_map(char *who) * Sanitize the BIOS e820 map. * * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps. + * replaces the original e820 map with a new one, removing overlaps, + * and resolving conflicting memory types in favor of highest + * numbered type. * + * The input parameter biosmap points to an array of 'struct + * e820entry' which on entry has elements in the range [0, *pnr_map) + * valid, and which has space for up to max_nr_map entries. + * On return, the resulting sanitized e820 map entries will be in + * overwritten in the same location, starting at biosmap. + * + * The integer pointed to by pnr_map must be valid on entry (the + * current number of valid entries located at biosmap) and will + * be updated on return, with the new number of valid entries + * (something no more than max_nr_map.) + * + * The return value from sanitize_e820_map() is zero if it + * successfully 'sanitized' the map entries passed in, and is -1 + * if it did nothing, which can happen if either of (1) it was + * only passed one map entry, or (2) any of the input map entries + * were invalid (start + size < start, meaning that the size was + * so big the described memory range wrapped around through zero.) + * + * Visually we're performing the following + * (1,2,3,4 = memory types)... + * + * Sample memory map (w/overlaps): + * ____22__________________ + * ______________________4_ + * ____1111________________ + * _44_____________________ + * 11111111________________ + * ____________________33__ + * ___________44___________ + * __________33333_________ + * ______________22________ + * ___________________2222_ + * _________111111111______ + * _____________________11_ + * _________________4______ + * + * Sanitized equivalent (no overlap): + * 1_______________________ + * _44_____________________ + * ___1____________________ + * ____22__________________ + * ______11________________ + * _________1______________ + * __________3_____________ + * ___________44___________ + * _____________33_________ + * _______________2________ + * ________________1_______ + * _________________4______ + * ___________________2____ + * ____________________33__ + * ______________________4_ */ + int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map) { @@ -162,43 +217,6 @@ static struct e820entry new_bios[E820_X_MAX] __initdata; int old_nr, new_nr, chg_nr; int i; - /* - Visually we're performing the following - (1,2,3,4 = memory types)... - - Sample memory map (w/overlaps): - ____22__________________ - ______________________4_ - ____1111________________ - _44_____________________ - 11111111________________ - ____________________33__ - ___________44___________ - __________33333_________ - ______________22________ - ___________________2222_ - _________111111111______ - _____________________11_ - _________________4______ - - Sanitized equivalent (no overlap): - 1_______________________ - _44_____________________ - ___1____________________ - ____22__________________ - ______11________________ - _________1______________ - __________3_____________ - ___________44___________ - _____________33_________ - _______________2________ - ________________1_______ - _________________4______ - ___________________2____ - ____________________33__ - ______________________4_ - */ - /* if there's only one memory region, don't bother */ if (*pnr_map < 2) return -1; -- cgit v1.2.3 From a4c81cf684350797939416c99effb9d3ae46bca6 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 18 May 2008 01:18:57 -0700 Subject: x86: extend e820 ealy_res support 32bit move early_res related from e820_64.c to e820.c make edba detection to be done in head32.c remove smp_alloc_memory, because we have fixed trampoline address now. Signed-off-by: Yinghai Lu arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 arch/x86/kernel/e820.c | 214 ++++++++++++++++++++++++++++++++++++ arch/x86/kernel/e820_64.c | 196 -------------------------------- arch/x86/kernel/head32.c | 76 ++++++++++++ arch/x86/kernel/setup_32.c | 109 +++--------------- arch/x86/kernel/smpboot.c | 17 -- arch/x86/kernel/trampoline.c | 2 arch/x86/mach-voyager/voyager_smp.c | 9 - include/asm-x86/e820.h | 6 + include/asm-x86/e820_64.h | 9 - include/asm-x86/smp.h | 1 10 files changed, 320 insertions(+), 319 deletions(-) Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 214 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 214 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 41c480ae47d..35da8cdbe5e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -22,7 +22,9 @@ #include #include #include +#include #include +#include 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; + +} -- cgit v1.2.3 From bf62f3981c7076714e3b9f5fa6989a806cad02bf Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 20 May 2008 20:10:58 -0700 Subject: x86: move e820_mark_nosave_regions to e820.c and make e820_mark_nosave_regions to take limit_pfn to use max_low_pfn for 32bit and end_pfn for 64bit Signed-off-by: Yinghai Lu Cc: Andrew Morton Signed-off-by: Thomas Gleixner --- arch/x86/kernel/e820.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 35da8cdbe5e..0cd9132c945 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -495,6 +496,37 @@ __init void e820_setup_gap(void) pci_mem_start, gapstart, gapsize); } +#if defined(CONFIG_X86_64) || \ + (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) +/** + * Find the ranges of physical addresses that do not correspond to + * e820 RAM areas and mark the corresponding pages as nosave for + * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). + * + * This function requires the e820 map to be sorted and without any + * overlapping entries and assumes the first e820 area to be RAM. + */ +void __init e820_mark_nosave_regions(unsigned long limit_pfn) +{ + int i; + unsigned long pfn; + + pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); + for (i = 1; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (pfn < PFN_UP(ei->addr)) + register_nosave_region(pfn, PFN_UP(ei->addr)); + + pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM) + register_nosave_region(PFN_UP(ei->addr), pfn); + + if (pfn >= limit_pfn) + break; + } +} +#endif /* * Early reserved memory areas. -- cgit v1.2.3 From 2944e16b25e7fb8b5ee0dd9dc7197a0f9e523cfd Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 1 Jun 2008 13:17:38 -0700 Subject: x86: update mptable make mptable to be consistent with acpi routing, so we could: 1. kexec kernel with acpi=off 2. work around BIOSes where acpi routing is working, but mptable is not right, so can use kernel/kexec to start other OSes that don't have good acpi support. command line: update_mptable Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 0cd9132c945..cd2b99e27d4 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -739,3 +739,28 @@ u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align) return -1UL; } + +/* + * pre allocated 4k and reserved it in e820 + */ +u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) +{ + u64 size = 0; + u64 addr; + u64 start; + + start = startt; + while (size < sizet) + start = find_e820_area_size(start, &size, align); + + if (size < sizet) + return 0; + + addr = round_down(start + size - sizet, align); + update_memory_range(addr, sizet, E820_RAM, E820_RESERVED); + printk(KERN_INFO "update e820 for early_reserve_e820\n"); + update_e820(); + + return addr; +} + -- cgit v1.2.3 From ee0c80fadfa56bf4f9d90c1c023429a6bd8edd69 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 3 Jun 2008 19:34:00 -0700 Subject: x86: move e820_register_active() to e820.c to prepare 32-bit to use it. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index cd2b99e27d4..c140f731743 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -764,3 +764,112 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) return addr; } +#ifdef CONFIG_X86_32 +# ifdef CONFIG_X86_PAE +# define MAX_ARCH_PFN (1ULL<<(36-PAGE_SHIFT)) +# else +# define MAX_ARCH_PFN (1ULL<<(32-PAGE_SHIFT)) +# endif +#else /* CONFIG_X86_32 */ +# define MAX_ARCH_PFN MAXMEM< max_arch_pfn) + last_pfn = max_arch_pfn; + if (last_pfn > end_user_pfn) + last_pfn = end_user_pfn; + + printk(KERN_INFO "last_pfn = %lu max_arch_pfn = %lu\n", + last_pfn, max_arch_pfn); + return last_pfn; +} + +/* + * Finds an active region in the address range from start_pfn to last_pfn and + * returns its range in ei_startpfn and ei_endpfn for the e820 entry. + */ +int __init e820_find_active_region(const struct e820entry *ei, + unsigned long start_pfn, + unsigned long last_pfn, + unsigned long *ei_startpfn, + unsigned long *ei_endpfn) +{ + u64 align = PAGE_SIZE; + + *ei_startpfn = round_up(ei->addr, align) >> PAGE_SHIFT; + *ei_endpfn = round_down(ei->addr + ei->size, align) >> PAGE_SHIFT; + + /* Skip map entries smaller than a page */ + if (*ei_startpfn >= *ei_endpfn) + return 0; + + /* Skip if map is outside the node */ + if (ei->type != E820_RAM || *ei_endpfn <= start_pfn || + *ei_startpfn >= last_pfn) + return 0; + + /* Check for overlaps */ + if (*ei_startpfn < start_pfn) + *ei_startpfn = start_pfn; + if (*ei_endpfn > last_pfn) + *ei_endpfn = last_pfn; + + /* Obey end_user_pfn to save on memmap */ + if (*ei_startpfn >= end_user_pfn) + return 0; + if (*ei_endpfn > end_user_pfn) + *ei_endpfn = end_user_pfn; + + return 1; +} + +/* Walk the e820 map and register active regions within a node */ +void __init e820_register_active_regions(int nid, unsigned long start_pfn, + unsigned long last_pfn) +{ + unsigned long ei_startpfn; + unsigned long ei_endpfn; + int i; + + for (i = 0; i < e820.nr_map; i++) + if (e820_find_active_region(&e820.map[i], + start_pfn, last_pfn, + &ei_startpfn, &ei_endpfn)) + add_active_range(nid, ei_startpfn, ei_endpfn); +} + +/* + * Find the hole size (in bytes) in the memory range. + * @start: starting address of the memory range to scan + * @end: ending address of the memory range to scan + */ +u64 __init e820_hole_size(u64 start, u64 end) +{ + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long last_pfn = end >> PAGE_SHIFT; + unsigned long ei_startpfn, ei_endpfn, ram = 0; + int i; + + for (i = 0; i < e820.nr_map; i++) { + if (e820_find_active_region(&e820.map[i], + start_pfn, last_pfn, + &ei_startpfn, &ei_endpfn)) + ram += ei_endpfn - ei_startpfn; + } + return end - start - ((u64)ram << PAGE_SHIFT); +} -- cgit v1.2.3 From bd70e522afce2f7837d081dc52f261ecf9d4d2d5 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 4 Jun 2008 13:21:29 -0700 Subject: x86: e820 max_arch_pfn typo fix for 64 bit should use right shift Signed-off-by: Yinghai Lu Cc: Andrew Morton Signed-off-by: Thomas Gleixner --- arch/x86/kernel/e820.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index c140f731743..5d33b9c08d1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -771,7 +771,7 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) # define MAX_ARCH_PFN (1ULL<<(32-PAGE_SHIFT)) # endif #else /* CONFIG_X86_32 */ -# define MAX_ARCH_PFN MAXMEM<>PAGE_SHIFT #endif /* -- cgit v1.2.3 From d3fbe5ea9518b46a68e6b278974e92e2c3acef4a Mon Sep 17 00:00:00 2001 From: "Huang, Ying" Date: Mon, 2 Jun 2008 14:26:14 +0800 Subject: x86: split out common code into find_overlapped_early() This patch clean up reserve_early() family functions by extracting the common part of reserve_early(), free_early() and bad_addr() into find_overlapped_early(). Signed-off-by: Huang Ying Cc: andi@firstfloor.org Cc: mingo@redhat.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/e820.c | 50 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 20 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 5d33b9c08d1..ac5e9ebf70e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -558,20 +558,34 @@ static struct early_res early_res[MAX_EARLY_RES] __initdata = { {} }; -void __init reserve_early(u64 start, u64 end, char *name) +static int __init find_overlapped_early(u64 start, u64 end) { 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); + break; } + + return i; +} + +void __init reserve_early(u64 start, u64 end, char *name) +{ + int i; + struct early_res *r; + + i = find_overlapped_early(start, end); if (i >= MAX_EARLY_RES) panic("Too many early reservations"); r = &early_res[i]; + if (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); r->start = start; r->end = end; if (name) @@ -583,14 +597,11 @@ 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) + i = find_overlapped_early(start, end); + r = &early_res[i]; + if (i >= MAX_EARLY_RES || r->end != end || r->start != start) panic("free_early on not reserved area: %llx-%llx!", - start, end); + start, end - 1); for (j = i + 1; j < MAX_EARLY_RES && early_res[j].end; j++) ; @@ -626,17 +637,16 @@ void __init early_res_to_bootmem(u64 start, u64 end) static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) { int i; - u64 addr = *addrp, last; + u64 addr = *addrp; int changed = 0; + struct early_res *r; 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; - } + i = find_overlapped_early(addr, addr + size); + r = &early_res[i]; + if (i < MAX_EARLY_RES && r->end) { + *addrp = addr = round_up(r->end, align); + changed = 1; + goto again; } return changed; } -- cgit v1.2.3 From d0ec2c6f2c2f0478b34ae78b3e65f60a561ac807 Mon Sep 17 00:00:00 2001 From: "Huang, Ying" Date: Mon, 2 Jun 2008 14:26:18 +0800 Subject: x86: reserve highmem pages via reserve_early This patch makes early reserved highmem pages become reserved pages. This can be used for highmem pages allocated by bootloader such as EFI memory map, linked list of setup_data, etc. Signed-off-by: Huang Ying Cc: andi@firstfloor.org Cc: mingo@redhat.com Signed-off-by: Thomas Gleixner --- arch/x86/kernel/e820.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ac5e9ebf70e..a706e9057ba 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -612,6 +612,17 @@ void __init free_early(u64 start, u64 end) early_res[j - 1].end = 0; } +int __init page_is_reserved_early(unsigned long pagenr) +{ + u64 start = (u64)pagenr << PAGE_SHIFT; + int i; + struct early_res *r; + + i = find_overlapped_early(start, start + PAGE_SIZE); + r = &early_res[i]; + return (i < MAX_EARLY_RES && r->end); +} + void __init early_res_to_bootmem(u64 start, u64 end) { int i; -- cgit v1.2.3 From df5f6c212cc049d1989b5ce71bb863a367c261e9 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 10 Jun 2008 16:38:41 +0200 Subject: x86: unify the reserve_bootmem() behavior of early_res_to_bootmem() Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a706e9057ba..68aba413d40 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -635,12 +635,8 @@ void __init early_res_to_bootmem(u64 start, u64 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 } } -- cgit v1.2.3 From ab4a465e96adf2f3a8aaa95384bacfa9ab661e35 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 10 Jun 2008 12:55:54 -0700 Subject: x86: e820 merge parsing of the mem=/memmap= boot parameters since we now have 32-bit support for e820_register_active_regions(), we can merge the parsing of the mem=/memmap= boot parameters. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 68aba413d40..4f2cd5d179e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -890,3 +890,89 @@ u64 __init e820_hole_size(u64 start, u64 end) } return end - start - ((u64)ram << PAGE_SHIFT); } + +static void early_panic(char *msg) +{ + early_printk(msg); + panic(msg); +} + +/* "mem=nopentium" disables the 4MB page tables. */ +static int __init parse_memopt(char *p) +{ + u64 mem_size; + + if (!p) + return -EINVAL; + +#ifdef CONFIG_X86_32 + if (!strcmp(p, "nopentium")) { + setup_clear_cpu_cap(X86_FEATURE_PSE); + return 0; + } +#endif + + mem_size = memparse(p, &p); + end_user_pfn = mem_size>>PAGE_SHIFT; + return 0; +} +early_param("mem", parse_memopt); + +static int userdef __initdata; + +static int __init parse_memmap_opt(char *p) +{ + char *oldp; + u64 start_at, mem_size; + + if (!strcmp(p, "exactmap")) { +#ifdef CONFIG_CRASH_DUMP + /* + * If we are doing a crash dump, we still need to know + * the real mem size before original memory map is + * reset. + */ + e820_register_active_regions(0, 0, -1UL); + saved_max_pfn = e820_end_of_ram(); + remove_all_active_ranges(); +#endif + e820.nr_map = 0; + userdef = 1; + return 0; + } + + oldp = p; + mem_size = memparse(p, &p); + if (p == oldp) + return -EINVAL; + + userdef = 1; + if (*p == '@') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, E820_RAM); + } else if (*p == '#') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, E820_ACPI); + } else if (*p == '$') { + start_at = memparse(p+1, &p); + add_memory_region(start_at, mem_size, E820_RESERVED); + } else { + end_user_pfn = (mem_size >> PAGE_SHIFT); + } + return *p == '\0' ? 0 : -EINVAL; +} +early_param("memmap", parse_memmap_opt); + +void __init finish_e820_parsing(void) +{ + if (userdef) { + int nr = e820.nr_map; + + if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) + early_panic("Invalid user supplied memory map"); + e820.nr_map = nr; + + printk(KERN_INFO "user-defined physical RAM map:\n"); + e820_print_map("user"); + } +} -- cgit v1.2.3 From d2dbf343329dc777d77488743465f7be4245971d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 13 Jun 2008 02:00:56 -0700 Subject: x86: clean up reserve_bootmem_generic() and port it to 32-bit 1. add reserve_bootmem_generic for 32bit 2. change len to unsigned long 3. make early_res_to_bootmem to use it Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 4f2cd5d179e..774063f11be 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -635,7 +635,7 @@ void __init early_res_to_bootmem(u64 start, u64 end) continue; printk(KERN_INFO " early res: %d [%llx-%llx] %s\n", i, final_start, final_end - 1, r->name); - reserve_bootmem(final_start, final_end - final_start, + reserve_bootmem_generic(final_start, final_end - final_start, BOOTMEM_DEFAULT); } } -- cgit v1.2.3 From d0be6bdea103b8d04c8a3495538b7c0011ae4129 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 15 Jun 2008 18:58:51 -0700 Subject: x86: rename two e820 related functions rename update_memory_range to e820_update_range rename add_memory_region to e820_add_region to make it more clear that they are about e820 map operations. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 774063f11be..5051ce744b4 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -94,7 +94,7 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) /* * Add a memory region to the kernel e820 map. */ -void __init add_memory_region(u64 start, u64 size, int type) +void __init e820_add_region(u64 start, u64 size, int type) { int x = e820.nr_map; @@ -384,12 +384,12 @@ int __init copy_e820_map(struct e820entry *biosmap, int nr_map) if (start > end) return -1; - add_memory_region(start, size, type); + e820_add_region(start, size, type); } while (biosmap++, --nr_map); return 0; } -u64 __init update_memory_range(u64 start, u64 size, unsigned old_type, +u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type) { int i; @@ -414,7 +414,7 @@ u64 __init update_memory_range(u64 start, u64 size, unsigned old_type, final_end = min(start + size, ei->addr + ei->size); if (final_start >= final_end) continue; - add_memory_region(final_start, final_end - final_start, + e820_add_region(final_start, final_end - final_start, new_type); real_updated_size += final_end - final_start; } @@ -774,7 +774,7 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) return 0; addr = round_down(start + size - sizet, align); - update_memory_range(addr, sizet, E820_RAM, E820_RESERVED); + e820_update_range(addr, sizet, E820_RAM, E820_RESERVED); printk(KERN_INFO "update e820 for early_reserve_e820\n"); update_e820(); @@ -949,13 +949,13 @@ static int __init parse_memmap_opt(char *p) userdef = 1; if (*p == '@') { start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_RAM); + e820_add_region(start_at, mem_size, E820_RAM); } else if (*p == '#') { start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_ACPI); + e820_add_region(start_at, mem_size, E820_ACPI); } else if (*p == '$') { start_at = memparse(p+1, &p); - add_memory_region(start_at, mem_size, E820_RESERVED); + e820_add_region(start_at, mem_size, E820_RESERVED); } else { end_user_pfn = (mem_size >> PAGE_SHIFT); } -- cgit v1.2.3 From b5bc6c0e55000dab86b73f838f5ad02908b23755 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 14 Jun 2008 18:32:52 -0700 Subject: x86, mm: use add_highpages_with_active_regions() for high pages init v2 use early_node_map to init high pages, so we can remove page_is_ram() and page_is_reserved_early() in the big loop with add_one_highpage also remove page_is_reserved_early(), it is not needed anymore. v2: fix the build of other platforms Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 5051ce744b4..ed46b7a6bc1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -612,17 +612,6 @@ void __init free_early(u64 start, u64 end) early_res[j - 1].end = 0; } -int __init page_is_reserved_early(unsigned long pagenr) -{ - u64 start = (u64)pagenr << PAGE_SHIFT; - int i; - struct early_res *r; - - i = find_overlapped_early(start, start + PAGE_SIZE); - r = &early_res[i]; - return (i < MAX_EARLY_RES && r->end); -} - void __init early_res_to_bootmem(u64 start, u64 end) { int i; -- cgit v1.2.3 From 8c5beb50d3ec915d15c4d38aa37282309a65f14e Mon Sep 17 00:00:00 2001 From: "Huang, Ying" Date: Wed, 11 Jun 2008 11:33:39 +0800 Subject: x86 boot: pass E820 memory map entries more than 128 via linked list of setup data Because of the size limits of struct boot_params (zero page), the maximum number of E820 memory map entries can be passed to kernel is 128. As pointed by Paul Jackson, there is some machine produced by SGI with so many nodes that the number of E820 memory map entries is more than 128. To enabling Linux kernel on these system, a new setup data type named SETUP_E820_EXT is defined to pass additional memory map entries to Linux kernel. This patch is based on x86/auto-latest branch of git-x86 tree and has been tested on x86_64 and i386 platform. Signed-off-by: Huang Ying Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 59 +++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 46 insertions(+), 13 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ed46b7a6bc1..544dd12c70f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -359,6 +359,26 @@ static struct e820entry new_bios[E820_X_MAX] __initdata; return 0; } +static int __init __copy_e820_map(struct e820entry *biosmap, int nr_map) +{ + while (nr_map) { + u64 start = biosmap->addr; + u64 size = biosmap->size; + u64 end = start + size; + u32 type = biosmap->type; + + /* Overflow in 64 bits? Ignore the memory map. */ + if (start > end) + return -1; + + e820_add_region(start, size, type); + + biosmap++; + nr_map--; + } + return 0; +} + /* * Copy the BIOS e820 map into a safe place. * @@ -374,19 +394,7 @@ int __init copy_e820_map(struct e820entry *biosmap, int nr_map) if (nr_map < 2) return -1; - do { - u64 start = biosmap->addr; - u64 size = biosmap->size; - u64 end = start + size; - u32 type = biosmap->type; - - /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) - return -1; - - e820_add_region(start, size, type); - } while (biosmap++, --nr_map); - return 0; + return __copy_e820_map(biosmap, nr_map); } u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, @@ -496,6 +504,31 @@ __init void e820_setup_gap(void) pci_mem_start, gapstart, gapsize); } +/** + * Because of the size limitation of struct boot_params, only first + * 128 E820 memory entries are passed to kernel via + * boot_params.e820_map, others are passed via SETUP_E820_EXT node of + * linked list of struct setup_data, which is parsed here. + */ +void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data) +{ + u32 map_len; + int entries; + struct e820entry *extmap; + + entries = sdata->len / sizeof(struct e820entry); + map_len = sdata->len + sizeof(struct setup_data); + if (map_len > PAGE_SIZE) + sdata = early_ioremap(pa_data, map_len); + extmap = (struct e820entry *)(sdata->data); + __copy_e820_map(extmap, entries); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + if (map_len > PAGE_SIZE) + early_iounmap(sdata, map_len); + printk(KERN_INFO "extended physical RAM map:\n"); + e820_print_map("extended"); +} + #if defined(CONFIG_X86_64) || \ (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) /** -- cgit v1.2.3 From 41c094fd3ca54f1a71233049cf136ff94c91f4ae Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 16 Jun 2008 13:03:31 -0700 Subject: x86: move e820_resource_resources to e820.c and make 32-bit resource registration more like 64 bit. also move probe_roms back to setup_32.c Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 544dd12c70f..432c4917857 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -998,3 +998,35 @@ void __init finish_e820_parsing(void) e820_print_map("user"); } } + +/* + * Mark e820 reserved areas as busy for the resource manager. + */ +void __init e820_reserve_resources(void) +{ + int i; + struct resource *res; + + res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); + for (i = 0; i < e820.nr_map; i++) { + switch (e820.map[i].type) { + case E820_RAM: res->name = "System RAM"; break; + case E820_ACPI: res->name = "ACPI Tables"; break; + case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; + default: res->name = "reserved"; + } + res->start = e820.map[i].addr; + res->end = res->start + e820.map[i].size - 1; +#ifndef CONFIG_RESOURCES_64BIT + if (res->end > 0x100000000ULL) { + res++; + continue; + } +#endif + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + insert_resource(&iomem_resource, res); + res++; + } +} + + -- cgit v1.2.3 From 064d25f12014ae1d97c2882f9ab874995321f2b2 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 16 Jun 2008 19:58:28 -0700 Subject: x86: merge setup_memory_map with e820 ... and kill e820_32/64.c and e820_32/64.h Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 432c4917857..49477484a2f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1029,4 +1029,76 @@ void __init e820_reserve_resources(void) } } +char *__init __attribute__((weak)) machine_specific_memory_setup(void) +{ + char *who = "BIOS-e820"; + int new_nr; + /* + * Try to copy the BIOS-supplied E820-map. + * + * Otherwise fake a memory map; one section from 0k->640k, + * the next section from 1mb->appropriate_mem_k + */ + new_nr = boot_params.e820_entries; + sanitize_e820_map(boot_params.e820_map, + ARRAY_SIZE(boot_params.e820_map), + &new_nr); + boot_params.e820_entries = new_nr; + if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0) { +#ifdef CONFIG_X86_64 + early_panic("Cannot find a valid memory map"); +#else + unsigned long mem_size; + + /* compare results from other methods and take the greater */ + if (boot_params.alt_mem_k + < boot_params.screen_info.ext_mem_k) { + mem_size = boot_params.screen_info.ext_mem_k; + who = "BIOS-88"; + } else { + mem_size = boot_params.alt_mem_k; + who = "BIOS-e801"; + } + + e820.nr_map = 0; + e820_add_region(0, LOWMEMSIZE(), E820_RAM); + e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); +#endif + } + + /* In case someone cares... */ + return who; +} + +/* Overridden in paravirt.c if CONFIG_PARAVIRT */ +char * __init __attribute__((weak)) memory_setup(void) +{ + return machine_specific_memory_setup(); +} + +void __init setup_memory_map(void) +{ + printk(KERN_INFO "BIOS-provided physical RAM map:\n"); + e820_print_map(memory_setup()); +} + +#ifdef CONFIG_X86_64 +int __init arch_get_ram_range(int slot, u64 *addr, u64 *size) +{ + int i; + if (slot < 0 || slot >= e820.nr_map) + return -1; + for (i = slot; i < e820.nr_map; i++) { + if (e820.map[i].type != E820_RAM) + continue; + break; + } + if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT)) + return -1; + *addr = e820.map[i].addr; + *size = min_t(u64, e820.map[i].size + e820.map[i].addr, + max_pfn << PAGE_SHIFT) - *addr; + return i + 1; +} +#endif -- cgit v1.2.3 From 95a71a45c250177854f7c530810c88a8a19a443b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 18 Jun 2008 17:27:08 -0700 Subject: x86: cleanup machine_specific_memory_setup, v2 1. let 64bit support 88 and e801 too 2. introduce default_machine_specific_memory_setup, and reuse it for voyager v2: fix 64 bit compiling Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 49477484a2f..7b613d2efb0 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1029,7 +1029,7 @@ void __init e820_reserve_resources(void) } } -char *__init __attribute__((weak)) machine_specific_memory_setup(void) +char *__init default_machine_specific_memory_setup(void) { char *who = "BIOS-e820"; int new_nr; @@ -1045,10 +1045,7 @@ char *__init __attribute__((weak)) machine_specific_memory_setup(void) &new_nr); boot_params.e820_entries = new_nr; if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0) { -#ifdef CONFIG_X86_64 - early_panic("Cannot find a valid memory map"); -#else - unsigned long mem_size; + u64 mem_size; /* compare results from other methods and take the greater */ if (boot_params.alt_mem_k @@ -1063,13 +1060,17 @@ char *__init __attribute__((weak)) machine_specific_memory_setup(void) e820.nr_map = 0; e820_add_region(0, LOWMEMSIZE(), E820_RAM); e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); -#endif } /* In case someone cares... */ return who; } +char *__init __attribute__((weak)) machine_specific_memory_setup(void) +{ + return default_machine_specific_memory_setup(); +} + /* Overridden in paravirt.c if CONFIG_PARAVIRT */ char * __init __attribute__((weak)) memory_setup(void) { -- cgit v1.2.3 From 7a1fd9866cbb59a00006f1e0fd5726951b167c97 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 21 Jun 2008 14:48:05 -0700 Subject: x86: add e820_remove_range ... so could add real hole in e820 agp check is using request_mem_region, and could fail if e820 is reserved... Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7b613d2efb0..e285ea38c8e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -429,6 +429,41 @@ u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, return real_updated_size; } +/* make e820 not cover the range */ +u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, + int checktype) +{ + int i; + u64 real_removed_size = 0; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + u64 final_start, final_end; + + if (checktype && ei->type != old_type) + continue; + /* totally covered? */ + if (ei->addr >= start && + (ei->addr + ei->size) <= (start + size)) { + real_removed_size += ei->size; + memset(ei, 0, sizeof(struct e820entry)); + continue; + } + /* partially covered */ + final_start = max(start, ei->addr); + final_end = min(start + size, ei->addr + ei->size); + if (final_start >= final_end) + continue; + real_removed_size += final_end - final_start; + + ei->size -= final_end - final_start; + if (ei->addr < final_start) + continue; + ei->addr = final_end; + } + return real_removed_size; +} + void __init update_e820(void) { int nr_map; -- cgit v1.2.3 From 157fabf09594ab064b7ae92c81942af4b94663cb Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sun, 22 Jun 2008 07:21:57 -0700 Subject: x86 boot: e820 code indentation fix Fix indentation. An earlier code merge got the indentation of four lines of code off by a tab. Signed-off-by: Paul Jackson Cc: "Yinghai Lu" Cc: "Jack Steiner" Cc: "Mike Travis" Cc: "Huang Cc: Ying" Cc: "Andi Kleen" Cc: "Andrew Morton" Cc: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e285ea38c8e..8a8afbdeb34 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -207,10 +207,10 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, struct e820entry *pbios; /* pointer to original bios entry */ unsigned long long addr; /* address for this change point */ }; -static struct change_member change_point_list[2*E820_X_MAX] __initdata; -static struct change_member *change_point[2*E820_X_MAX] __initdata; -static struct e820entry *overlap_list[E820_X_MAX] __initdata; -static struct e820entry new_bios[E820_X_MAX] __initdata; + static struct change_member change_point_list[2*E820_X_MAX] __initdata; + static struct change_member *change_point[2*E820_X_MAX] __initdata; + static struct e820entry *overlap_list[E820_X_MAX] __initdata; + static struct e820entry new_bios[E820_X_MAX] __initdata; struct change_member *change_tmp; unsigned long current_type, last_type; unsigned long long last_addr; -- cgit v1.2.3 From c4ba1320b7075e9ce33ad0afaef43ba13260b4c2 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sun, 22 Jun 2008 07:22:07 -0700 Subject: x86 boot: allow overlapping early reserve memory ranges Add support for overlapping early memory reservations. In general, they still can't overlap, and will panic with "Overlapping early reservations" if they do overlap. But if a memory range is reserved with the new call: reserve_early_overlap_ok() rather than with the usual call: reserve_early() then subsequent early reservations are allowed to overlap. This new reserve_early_overlap_ok() call is only used in one place so far, which is the "BIOS reserved" reservation for the the EBDA region, which out of Paranoia reserves more than what the BIOS might have specified, and which thus might overlap with another legitimate early memory reservation (such as, perhaps, the EFI memmap.) Signed-off-by: Paul Jackson Cc: "Yinghai Lu" Cc: "Jack Steiner" Cc: "Mike Travis" Cc: "Huang Cc: Ying" Cc: "Andi Kleen" Cc: "Andrew Morton" Cc: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 140 +++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 131 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 8a8afbdeb34..600c9de237a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -604,6 +604,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) struct early_res { u64 start, end; char name[16]; + char overlap_ok; }; static struct early_res early_res[MAX_EARLY_RES] __initdata = { { 0, PAGE_SIZE, "BIOS data page" }, /* BIOS data page */ @@ -640,7 +641,93 @@ static int __init find_overlapped_early(u64 start, u64 end) return i; } -void __init reserve_early(u64 start, u64 end, char *name) +/* + * Drop the i-th range from the early reservation map, + * by copying any higher ranges down one over it, and + * clearing what had been the last slot. + */ +static void __init drop_range(int i) +{ + int j; + + 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; +} + +/* + * Split any existing ranges that: + * 1) are marked 'overlap_ok', and + * 2) overlap with the stated range [start, end) + * into whatever portion (if any) of the existing range is entirely + * below or entirely above the stated range. Drop the portion + * of the existing range that overlaps with the stated range, + * which will allow the caller of this routine to then add that + * stated range without conflicting with any existing range. + */ +static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +{ + int i; + struct early_res *r; + u64 lower_start, lower_end; + u64 upper_start, upper_end; + char name[16]; + + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { + r = &early_res[i]; + + /* Continue past non-overlapping ranges */ + if (end <= r->start || start >= r->end) + continue; + + /* + * Leave non-ok overlaps as is; let caller + * panic "Overlapping early reservations" + * when it hits this overlap. + */ + if (!r->overlap_ok) + return; + + /* + * We have an ok overlap. We will drop it from the early + * reservation map, and add back in any non-overlapping + * portions (lower or upper) as separate, overlap_ok, + * non-overlapping ranges. + */ + + /* 1. Note any non-overlapping (lower or upper) ranges. */ + strncpy(name, r->name, sizeof(name) - 1); + + lower_start = lower_end = 0; + upper_start = upper_end = 0; + if (r->start < start) { + lower_start = r->start; + lower_end = start; + } + if (r->end > end) { + upper_start = end; + upper_end = r->end; + } + + /* 2. Drop the original ok overlapping range */ + drop_range(i); + + i--; /* resume for-loop on copied down entry */ + + /* 3. Add back in any non-overlapping ranges. */ + if (lower_end) + reserve_early_overlap_ok(lower_start, lower_end, name); + if (upper_end) + reserve_early_overlap_ok(upper_start, upper_end, name); + } +} + +static void __init __reserve_early(u64 start, u64 end, char *name, + int overlap_ok) { int i; struct early_res *r; @@ -656,14 +743,55 @@ void __init reserve_early(u64 start, u64 end, char *name) r->end - 1, r->name); r->start = start; r->end = end; + r->overlap_ok = overlap_ok; if (name) strncpy(r->name, name, sizeof(r->name) - 1); } +/* + * A few early reservtations come here. + * + * The 'overlap_ok' in the name of this routine does -not- mean it + * is ok for these reservations to overlap an earlier reservation. + * Rather it means that it is ok for subsequent reservations to + * overlap this one. + * + * Use this entry point to reserve early ranges when you are doing + * so out of "Paranoia", reserving perhaps more memory than you need, + * just in case, and don't mind a subsequent overlapping reservation + * that is known to be needed. + * + * The drop_overlaps_that_are_ok() call here isn't really needed. + * It would be needed if we had two colliding 'overlap_ok' + * reservations, so that the second such would not panic on the + * overlap with the first. We don't have any such as of this + * writing, but might as well tolerate such if it happens in + * the future. + */ +void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 1); +} + +/* + * Most early reservations come here. + * + * We first have drop_overlaps_that_are_ok() drop any pre-existing + * 'overlap_ok' ranges, so that we can then reserve this memory + * range without risk of panic'ing on an overlapping overlap_ok + * early reservation. + */ +void __init reserve_early(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 0); +} + void __init free_early(u64 start, u64 end) { struct early_res *r; - int i, j; + int i; i = find_overlapped_early(start, end); r = &early_res[i]; @@ -671,13 +799,7 @@ void __init free_early(u64 start, u64 end) panic("free_early on not reserved area: %llx-%llx!", start, end - 1); - 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; + drop_range(i); } void __init early_res_to_bootmem(u64 start, u64 end) -- cgit v1.2.3 From e2fc252e0ce695b4c4abe27bb073c35bd0d73252 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Sun, 22 Jun 2008 07:22:12 -0700 Subject: x86 boot: show pfn addresses in hex not decimal in some kernel info printks Page frame numbers (the portion of physical addresses above the low order page offsets) are displayed in several kernel debug and info prints in decimal, not hex. Decimal addresse are unreadable. Use hex. Signed-off-by: Paul Jackson Cc: "Yinghai Lu" Cc: "Jack Steiner" Cc: "Mike Travis" Cc: "Huang Cc: Ying" Cc: "Andi Kleen" Cc: "Andrew Morton" Cc: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 600c9de237a..512f779fc6a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -990,7 +990,7 @@ unsigned long __init e820_end_of_ram(void) if (last_pfn > end_user_pfn) last_pfn = end_user_pfn; - printk(KERN_INFO "last_pfn = %lu max_arch_pfn = %lu\n", + printk(KERN_INFO "last_pfn = 0x%lx max_arch_pfn = 0x%lx\n", last_pfn, max_arch_pfn); return last_pfn; } -- cgit v1.2.3 From 976dd4dc99c3eaf45e3802ed46e3cc06a1ad8689 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 24 Jun 2008 14:55:32 -0700 Subject: x86: fix e820_update_range size when overlapping before that we relay on sanitize_e820_map to remove the overlap. but e820_update_range(,,E820_RESERVED, E820_RAM) will not work this patch fix that who is going to use this? Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 512f779fc6a..15b4393ff9b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -425,6 +425,11 @@ u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, e820_add_region(final_start, final_end - final_start, new_type); real_updated_size += final_end - final_start; + + ei->size -= final_end - final_start; + if (ei->addr < final_start) + continue; + ei->addr = final_end; } return real_updated_size; } -- cgit v1.2.3 From 232b957ae93973a5f8619ef61b916744b747478c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 24 Jun 2008 14:58:38 -0700 Subject: x86: change size if e820_update/remove_range in case someone using crazy parameter while calling them. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 15b4393ff9b..1b76b25b4d9 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -405,6 +405,9 @@ u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, BUG_ON(old_type == new_type); + if (size > (ULLONG_MAX - start)) + size = ULLONG_MAX - start; + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; u64 final_start, final_end; @@ -441,6 +444,9 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, int i; u64 real_removed_size = 0; + if (size > (ULLONG_MAX - start)) + size = ULLONG_MAX - start; + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; u64 final_start, final_end; -- cgit v1.2.3 From c987d12f8455b19b3b057d63bac3de161bd809fc Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 24 Jun 2008 22:14:09 -0700 Subject: x86: remove end_pfn in 64bit and use max_pfn directly. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 1b76b25b4d9..3900ff51bc6 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -527,7 +527,7 @@ __init void e820_setup_gap(void) #ifdef CONFIG_X86_64 if (!found) { - gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024; + gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit " "address range\n" KERN_ERR "PCI: Unassigned devices with 32bit resource " -- cgit v1.2.3 From 3381959da5a00ae8289cfbd28b0b6d228f2d1d46 Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Tue, 24 Jun 2008 11:48:30 -0700 Subject: x86: cleanup e820_setup_gap(), add e820_search_gap(), v2 This is a preparatory patch for the next patch in series. Moves some code from e820_setup_gap to a new function e820_search_gap. This patch is a part of a bug fix where we walk the ACPI table to calculate a gap for PCI optional devices. v1->v2: Patch on top of tip/master. Fixes a bug introduced in the last patch about the typeof "last". Also the new function e820_search_gap now returns if we found a gap in e820_map. Signed-off-by: Alok N Kataria Cc: lenb@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 43 ++++++++++++++++++++++++++++--------------- 1 file changed, 28 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 3900ff51bc6..22cfd665224 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -488,26 +488,22 @@ void __init update_e820(void) } /* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. We pass this space to PCI to assign MMIO resources - * for hotplug or unconfigured devices in. - * Hopefully the BIOS let enough space left. + * Search for a gap in the e820 memory space from start_addr to 2^32. */ -__init void e820_setup_gap(void) +__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, + unsigned long start_addr) { - unsigned long gapstart, gapsize, round; - unsigned long long last; - int i; + unsigned long long last = 0x100000000ull; + int i = e820.nr_map; int found = 0; - last = 0x100000000ull; - gapstart = 0x10000000; - gapsize = 0x400000; - i = e820.nr_map; while (--i >= 0) { unsigned long long start = e820.map[i].addr; unsigned long long end = start + e820.map[i].size; + if (end < start_addr) + continue; + /* * Since "last" is at most 4GB, we know we'll * fit in 32 bits if this condition is true @@ -515,15 +511,32 @@ __init void e820_setup_gap(void) if (last > end) { unsigned long gap = last - end; - if (gap > gapsize) { - gapsize = gap; - gapstart = end; + if (gap >= *gapsize) { + *gapsize = gap; + *gapstart = end; found = 1; } } if (start < last) last = start; } + return found; +} + +/* + * Search for the biggest gap in the low 32 bits of the e820 + * memory space. We pass this space to PCI to assign MMIO resources + * for hotplug or unconfigured devices in. + * Hopefully the BIOS let enough space left. + */ +__init void e820_setup_gap(void) +{ + unsigned long gapstart, gapsize, round; + int found; + + gapstart = 0x10000000; + gapsize = 0x400000; + found = e820_search_gap(&gapstart, &gapsize, 0); #ifdef CONFIG_X86_64 if (!found) { -- cgit v1.2.3 From 5dab8ec139be215fbaba216fb4aea914d0f4dac5 Mon Sep 17 00:00:00 2001 From: Paul Jackson Date: Wed, 25 Jun 2008 05:44:40 -0700 Subject: mm, generic, x86 boot: more tweaks to hex prints of some pfn addresses Fix some problems with (and applies on top of) a previous patch: x86 boot: show pfn addresses in hex not decimal in some kernel info printks Primarily change "0x%8lx" format, which displays with a right aligned space filled hex number (spaces between the "0x" prefix and the number), into "%0#10lx" format, which zero fills instead of space fills, and which uses the printf flag '#' to request the "0x" prefix instead of hard coding it. Also replace some other "0x%lx" formats with "%#lx", making use of the '#' printf flag again. Signed-off-by: Paul Jackson Cc: "Yinghai Lu" Cc: "Jack Steiner" Cc: "Mike Travis" Cc: "Huang Cc: Ying" Cc: "Andi Kleen" Cc: "Andrew Morton" Cc: Paul Jackson Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 22cfd665224..1dcb66533df 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1014,7 +1014,7 @@ unsigned long __init e820_end_of_ram(void) if (last_pfn > end_user_pfn) last_pfn = end_user_pfn; - printk(KERN_INFO "last_pfn = 0x%lx max_arch_pfn = 0x%lx\n", + printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n", last_pfn, max_arch_pfn); return last_pfn; } -- cgit v1.2.3 From 611dfd7819e525b45f39ff15e0faf5f23551c113 Mon Sep 17 00:00:00 2001 From: Bernhard Walle Date: Wed, 25 Jun 2008 21:39:16 +0200 Subject: x86: limit E820 map when a user-defined memory map is specified This patch brings back limiting of the E820 map when a user-defined E820 map is specified. While the behaviour of i386 (32 bit) was to limit the E820 map (and /proc/iomem), the behaviour of x86-64 (64 bit) was not to limit. That patch limits the E820 map again for both x86 architectures. Code was tested for compilation and booting on a 32 bit and 64 bit system. Signed-off-by: Bernhard Walle Acked-by: Yinghai Lu Cc: kexec@lists.infradead.org Cc: vgoyal@redhat.com Cc: Bernhard Walle Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 1dcb66533df..7b7685b7885 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1117,6 +1117,9 @@ static int __init parse_memopt(char *p) mem_size = memparse(p, &p); end_user_pfn = mem_size>>PAGE_SHIFT; + e820_update_range(mem_size, ULLONG_MAX - mem_size, + E820_RAM, E820_RESERVED); + return 0; } early_param("mem", parse_memopt); @@ -1161,6 +1164,8 @@ static int __init parse_memmap_opt(char *p) e820_add_region(start_at, mem_size, E820_RESERVED); } else { end_user_pfn = (mem_size >> PAGE_SHIFT); + e820_update_range(mem_size, ULLONG_MAX - mem_size, + E820_RAM, E820_RESERVED); } return *p == '\0' ? 0 : -EINVAL; } -- cgit v1.2.3 From ab67715c7201be2fe729888a09007b6ba5bb2326 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 27 Jun 2008 15:36:54 -0700 Subject: x86: early res print out alignment v2 v2: fix print info to cont Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7b7685b7885..fa77cb4185c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -828,16 +828,26 @@ void __init free_early(u64 start, u64 end) void __init early_res_to_bootmem(u64 start, u64 end) { - int i; + int i, count; u64 final_start, final_end; - for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) { + + count = 0; + for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) + count++; + + printk(KERN_INFO "(%d early reservations) ==> bootmem\n", count); + for (i = 0; i < count; i++) { struct early_res *r = &early_res[i]; + printk(KERN_INFO " #%d [ %010llx - %010llx ] %16s", i, + r->start, r->end, r->name); final_start = max(start, r->start); final_end = min(end, r->end); - if (final_start >= final_end) + if (final_start >= final_end) { + printk(KERN_CONT "\n"); continue; - printk(KERN_INFO " early res: %d [%llx-%llx] %s\n", i, - final_start, final_end - 1, r->name); + } + printk(KERN_CONT " ===> [ %010llx - %010llx ]\n", + final_start, final_end); reserve_bootmem_generic(final_start, final_end - final_start, BOOTMEM_DEFAULT); } -- cgit v1.2.3 From b4df32f4aeef8794d0135fc8dc250acb44cfee60 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sat, 28 Jun 2008 17:49:59 -0700 Subject: x86: fix warning in e820_reserve_resources with 32bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit when 64bit resource is not enabled, we get: arch/x86/kernel/e820.c: In function ‘e820_reserve_resources’: arch/x86/kernel/e820.c:1217: warning: comparison is always false due to limited range of data type because res->start/end is resource_t aka u32. it will overflow. fix it with temp end of u64 Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fa77cb4185c..ba5ac880ea1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1202,6 +1202,7 @@ void __init e820_reserve_resources(void) { int i; struct resource *res; + u64 end; res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); for (i = 0; i < e820.nr_map; i++) { @@ -1211,14 +1212,16 @@ void __init e820_reserve_resources(void) case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; default: res->name = "reserved"; } - res->start = e820.map[i].addr; - res->end = res->start + e820.map[i].size - 1; + end = e820.map[i].addr + e820.map[i].size - 1; #ifndef CONFIG_RESOURCES_64BIT - if (res->end > 0x100000000ULL) { + if (end > 0x100000000ULL) { res++; continue; } #endif + res->start = e820.map[i].addr; + res->end = end; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; insert_resource(&iomem_resource, res); res++; -- cgit v1.2.3 From 28bb22379513ca3cac9d13766064a219c5fc21a9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 30 Jun 2008 16:20:54 -0700 Subject: x86: move reserve_setup_data to setup.c Ying Huang would like setup_data to be reserved, but not included in the no save range. Here we try to modify the e820 table to reserve that range early. also add that in early_res in case bootloader messes up with the ramdisk. other solution would be 1. add early_res_to_highmem... 2. early_res_to_e820... but they could reserve another type memory wrongly, if early_res has some resource reserved early, and not needed later, but it is not removed from early_res in time. Like the RAMDISK (already handled). Signed-off-by: Yinghai Lu Cc: andi@firstfloor.org Tested-by: Huang, Ying Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ba5ac880ea1..e03b89ac8f2 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -120,6 +120,7 @@ void __init e820_print_map(char *who) (e820.map[i].addr + e820.map[i].size)); switch (e820.map[i].type) { case E820_RAM: + case E820_RESERVED_KERN: printk(KERN_CONT "(usable)\n"); break; case E820_RESERVED: @@ -611,7 +612,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) register_nosave_region(pfn, PFN_UP(ei->addr)); pfn = PFN_DOWN(ei->addr + ei->size); - if (ei->type != E820_RAM) + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) register_nosave_region(PFN_UP(ei->addr), pfn); if (pfn >= limit_pfn) @@ -1207,6 +1208,7 @@ void __init e820_reserve_resources(void) res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); for (i = 0; i < e820.nr_map; i++) { switch (e820.map[i].type) { + case E820_RESERVED_KERN: case E820_RAM: res->name = "System RAM"; break; case E820_ACPI: res->name = "ACPI Tables"; break; case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; -- cgit v1.2.3 From fd6493e16625b92a506fba13deda31c0be5f1cd4 Mon Sep 17 00:00:00 2001 From: Alok Kataria Date: Wed, 25 Jun 2008 11:02:42 -0700 Subject: x86: cleanup e820_setup_gap(), v2 e820_search_gap also take a end_addr parameter to limit search from start_addr to end_addr. Signed-off-by: AloK N Kataria Acked-by: Yinghai Lu Cc: "lenb@kernel.org" Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e03b89ac8f2..d3f6c5f6d3b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -487,17 +487,19 @@ void __init update_e820(void) printk(KERN_INFO "modified physical RAM map:\n"); e820_print_map("modified"); } - +#define MAX_GAP_END 0x100000000ull /* - * Search for a gap in the e820 memory space from start_addr to 2^32. + * Search for a gap in the e820 memory space from start_addr to end_addr. */ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, - unsigned long start_addr) + unsigned long start_addr, unsigned long long end_addr) { - unsigned long long last = 0x100000000ull; + unsigned long long last; int i = e820.nr_map; int found = 0; + last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END; + while (--i >= 0) { unsigned long long start = e820.map[i].addr; unsigned long long end = start + e820.map[i].size; @@ -537,7 +539,7 @@ __init void e820_setup_gap(void) gapstart = 0x10000000; gapsize = 0x400000; - found = e820_search_gap(&gapstart, &gapsize, 0); + found = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END); #ifdef CONFIG_X86_64 if (!found) { -- cgit v1.2.3 From dc8e8120ad291074a5fb93cfb0418466c62f6019 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 1 Jul 2008 20:02:16 -0700 Subject: x86: change copy_e820_map to append_e820_map so it has a more meaningful name. also change it to static. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d3f6c5f6d3b..b01fa0d0dc7 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -360,7 +360,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, return 0; } -static int __init __copy_e820_map(struct e820entry *biosmap, int nr_map) +static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) { while (nr_map) { u64 start = biosmap->addr; @@ -389,13 +389,13 @@ static int __init __copy_e820_map(struct e820entry *biosmap, int nr_map) * will have given us a memory map that we can use to properly * set up memory. If we aren't, we'll fake a memory map. */ -int __init copy_e820_map(struct e820entry *biosmap, int nr_map) +static int __init append_e820_map(struct e820entry *biosmap, int nr_map) { /* Only one memory region (or negative)? Ignore it */ if (nr_map < 2) return -1; - return __copy_e820_map(biosmap, nr_map); + return __append_e820_map(biosmap, nr_map); } u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, @@ -583,7 +583,7 @@ void __init parse_e820_ext(struct setup_data *sdata, unsigned long pa_data) if (map_len > PAGE_SIZE) sdata = early_ioremap(pa_data, map_len); extmap = (struct e820entry *)(sdata->data); - __copy_e820_map(extmap, entries); + __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); if (map_len > PAGE_SIZE) early_iounmap(sdata, map_len); @@ -1247,7 +1247,8 @@ char *__init default_machine_specific_memory_setup(void) ARRAY_SIZE(boot_params.e820_map), &new_nr); boot_params.e820_entries = new_nr; - if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0) { + if (append_e820_map(boot_params.e820_map, boot_params.e820_entries) + < 0) { u64 mem_size; /* compare results from other methods and take the greater */ -- cgit v1.2.3 From 4fcc545a7479135332f511a54611820c9f4208a0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 1 Jul 2008 20:03:11 -0700 Subject: x86: make early_res_to_bootmem print out less 80 width chars Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b01fa0d0dc7..d0335853ff5 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -841,7 +841,7 @@ void __init early_res_to_bootmem(u64 start, u64 end) printk(KERN_INFO "(%d early reservations) ==> bootmem\n", count); for (i = 0; i < count; i++) { struct early_res *r = &early_res[i]; - printk(KERN_INFO " #%d [ %010llx - %010llx ] %16s", i, + printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, r->start, r->end, r->name); final_start = max(start, r->start); final_end = min(end, r->end); @@ -849,7 +849,7 @@ void __init early_res_to_bootmem(u64 start, u64 end) printk(KERN_CONT "\n"); continue; } - printk(KERN_CONT " ===> [ %010llx - %010llx ]\n", + printk(KERN_CONT " ==> [%010llx - %010llx]\n", final_start, final_end); reserve_bootmem_generic(final_start, final_end - final_start, BOOTMEM_DEFAULT); -- cgit v1.2.3 From 5dfcf14d5b28174f94cbe9b4fb35d415db61c64a Mon Sep 17 00:00:00 2001 From: Bernhard Walle Date: Fri, 27 Jun 2008 13:12:55 +0200 Subject: x86: use FIRMWARE_MEMMAP on x86/E820 This patch uses the /sys/firmware/memmap interface provided in the last patch on the x86 architecture when E820 is used. The patch copies the E820 memory map very early, and registers the E820 map afterwards via firmware_map_add_early(). Signed-off-by: Bernhard Walle Acked-by: Greg KH Acked-by: Vivek Goyal Cc: kexec@lists.infradead.org Cc: yhlu.kernel@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 44 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d0335853ff5..fc1d579f212 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -27,7 +28,22 @@ #include #include +/* + * The e820 map is the map that gets modified e.g. with command line parameters + * and that is also registered with modifications in the kernel resource tree + * with the iomem_resource as parent. + * + * The e820_saved is directly saved after the BIOS-provided memory map is + * copied. It doesn't get modified afterwards. It's registered for the + * /sys/firmware/memmap interface. + * + * That memory map is not modified and is used as base for kexec. The kexec'd + * kernel should get the same memory map as the firmware provides. Then the + * user can e.g. boot the original kernel with mem=1G while still booting the + * next kernel with full memory. + */ struct e820map e820; +struct e820map e820_saved; /* For PCI or other memory-mapped resources */ unsigned long pci_mem_start = 0xaeedbabe; @@ -1198,6 +1214,17 @@ void __init finish_e820_parsing(void) } } +static inline const char *e820_type_to_string(int e820_type) +{ + switch (e820_type) { + case E820_RESERVED_KERN: + case E820_RAM: return "System RAM"; + case E820_ACPI: return "ACPI Tables"; + case E820_NVS: return "ACPI Non-volatile Storage"; + default: return "reserved"; + } +} + /* * Mark e820 reserved areas as busy for the resource manager. */ @@ -1209,13 +1236,6 @@ void __init e820_reserve_resources(void) res = alloc_bootmem_low(sizeof(struct resource) * e820.nr_map); for (i = 0; i < e820.nr_map; i++) { - switch (e820.map[i].type) { - case E820_RESERVED_KERN: - case E820_RAM: res->name = "System RAM"; break; - case E820_ACPI: res->name = "ACPI Tables"; break; - case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; - default: res->name = "reserved"; - } end = e820.map[i].addr + e820.map[i].size - 1; #ifndef CONFIG_RESOURCES_64BIT if (end > 0x100000000ULL) { @@ -1223,6 +1243,7 @@ void __init e820_reserve_resources(void) continue; } #endif + res->name = e820_type_to_string(e820.map[i].type); res->start = e820.map[i].addr; res->end = end; @@ -1230,6 +1251,13 @@ void __init e820_reserve_resources(void) insert_resource(&iomem_resource, res); res++; } + + for (i = 0; i < e820_saved.nr_map; i++) { + struct e820entry *entry = &e820_saved.map[i]; + firmware_map_add_early(entry->addr, + entry->addr + entry->size - 1, + e820_type_to_string(entry->type)); + } } char *__init default_machine_specific_memory_setup(void) @@ -1266,6 +1294,8 @@ char *__init default_machine_specific_memory_setup(void) e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); } + memcpy(&e820_saved, &e820, sizeof(struct e820map)); + /* In case someone cares... */ return who; } -- cgit v1.2.3 From 0be15526beb4c228e0477221c62ec8ab0fc7440f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 3 Jul 2008 11:35:37 -0700 Subject: x86: move saving e820_saved to setup_memory_map so other path that will override memory_setup or machine_specific_memory_setup could have e820_saved too. Signed-off-by: Yinghai Lu Cc: Jeremy Fitzhardinge Cc: Bernhard Walle Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fc1d579f212..13e32986cb5 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1294,8 +1294,6 @@ char *__init default_machine_specific_memory_setup(void) e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); } - memcpy(&e820_saved, &e820, sizeof(struct e820map)); - /* In case someone cares... */ return who; } @@ -1313,8 +1311,12 @@ char * __init __attribute__((weak)) memory_setup(void) void __init setup_memory_map(void) { + char *who; + + who = memory_setup(); + memcpy(&e820_saved, &e820, sizeof(struct e820map)); printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - e820_print_map(memory_setup()); + e820_print_map(who); } #ifdef CONFIG_X86_64 -- cgit v1.2.3 From fc9036ea1a4b14229788e6df3936b451a6abac98 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 3 Jul 2008 11:39:00 -0700 Subject: x86: let early_reserve_e820 update e820_saved too so when it is called after early_param, e820_saved get updated too. esp for mpc update. Signed-off-by: Yinghai Lu Cc: Bernhard Walle Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 13e32986cb5..e07d4019e26 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -414,8 +414,9 @@ static int __init append_e820_map(struct e820entry *biosmap, int nr_map) return __append_e820_map(biosmap, nr_map); } -u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) +static u64 __init e820_update_range_map(struct e820map *e820x, u64 start, + u64 size, unsigned old_type, + unsigned new_type) { int i; u64 real_updated_size = 0; @@ -426,7 +427,7 @@ u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, size = ULLONG_MAX - start; for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; + struct e820entry *ei = &e820x->map[i]; u64 final_start, final_end; if (ei->type != old_type) continue; @@ -454,6 +455,19 @@ u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, return real_updated_size; } +u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, + unsigned new_type) +{ + return e820_update_range_map(&e820, start, size, old_type, new_type); +} + +static u64 __init e820_update_range_saved(u64 start, u64 size, + unsigned old_type, unsigned new_type) +{ + return e820_update_range_map(&e820_saved, start, size, old_type, + new_type); +} + /* make e820 not cover the range */ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype) @@ -503,6 +517,15 @@ void __init update_e820(void) printk(KERN_INFO "modified physical RAM map:\n"); e820_print_map("modified"); } +static void __init update_e820_saved(void) +{ + int nr_map; + + nr_map = e820_saved.nr_map; + if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) + return; + e820_saved.nr_map = nr_map; +} #define MAX_GAP_END 0x100000000ull /* * Search for a gap in the e820 memory space from start_addr to end_addr. @@ -1007,8 +1030,10 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) addr = round_down(start + size - sizet, align); e820_update_range(addr, sizet, E820_RAM, E820_RESERVED); + e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); printk(KERN_INFO "update e820 for early_reserve_e820\n"); update_e820(); + update_e820_saved(); return addr; } -- cgit v1.2.3 From 2dc807b37b7b8c7df445513ad2b415df4ebcaf6d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 8 Jul 2008 18:56:38 -0700 Subject: x86: make max_pfn cover acpi table below 4g When system have 4g less ram installed, and acpi table sit near end of ram, make max_pfn cover them too, so 64bit kernel don't need to mess up fixmap. Signed-off-by: Yinghai Lu Cc: "Suresh Siddha" Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index e07d4019e26..2e08619a9c5 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1056,12 +1056,20 @@ unsigned long __initdata end_user_pfn = MAX_ARCH_PFN; /* * Find the highest page frame number we have available */ -unsigned long __init e820_end_of_ram(void) +unsigned long __init e820_end(void) { - unsigned long last_pfn; + int i; + unsigned long last_pfn = 0; unsigned long max_arch_pfn = MAX_ARCH_PFN; - last_pfn = find_max_pfn_with_active_regions(); + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long end_pfn; + + end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; + if (end_pfn > last_pfn) + last_pfn = end_pfn; + } if (last_pfn > max_arch_pfn) last_pfn = max_arch_pfn; @@ -1192,9 +1200,7 @@ static int __init parse_memmap_opt(char *p) * the real mem size before original memory map is * reset. */ - e820_register_active_regions(0, 0, -1UL); - saved_max_pfn = e820_end_of_ram(); - remove_all_active_ranges(); + saved_max_pfn = e820_end(); #endif e820.nr_map = 0; userdef = 1; -- cgit v1.2.3 From c22d4c1885130db9c07f6441ab461208a1ba16b2 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 9 Jul 2008 03:01:14 -0700 Subject: x86: make e820_end return max ram type only for 32 bit to avoid warning from find_low_pfn_range for high pages size etc Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2e08619a9c5..292ebc7fe4d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1066,6 +1066,11 @@ unsigned long __init e820_end(void) struct e820entry *ei = &e820.map[i]; unsigned long end_pfn; +#ifdef CONFIG_X86_32 + if (ei->type != E820_RAM) + continue; +#endif + end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; if (end_pfn > last_pfn) last_pfn = end_pfn; -- cgit v1.2.3 From a737abd11ac4eb9f4226fa8c9f1d9b5be12a96c1 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Sat, 5 Jul 2008 15:53:39 +0400 Subject: x86: e820 memmap - add checking for NULL early param Signed-off-by: Cyrill Gorcunov Cc: Cyrill Gorcunov Cc: akpm@linux-foundation.org Cc: andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 292ebc7fe4d..66fd5bd7831 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1198,6 +1198,9 @@ static int __init parse_memmap_opt(char *p) char *oldp; u64 start_at, mem_size; + if (!p) + return -EINVAL; + if (!strcmp(p, "exactmap")) { #ifdef CONFIG_CRASH_DUMP /* -- cgit v1.2.3 From 3d43ecd286e442792f2e899e6e06eb23ab3d99f6 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 9 Jul 2008 20:17:50 -0700 Subject: x86: make e820_end return end_of_ram again for 64bit even on 64bit systems with less than 4G RAM, we can now use fixmap to handle acpi SIT near end of ram. change e820_end to e820_end_of_ram again? or e820_ram_pfn? Signed-off-by: Yinghai Lu Cc: Suresh Siddha Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/kernel/e820.c') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 66fd5bd7831..9836a079cfd 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1066,10 +1066,8 @@ unsigned long __init e820_end(void) struct e820entry *ei = &e820.map[i]; unsigned long end_pfn; -#ifdef CONFIG_X86_32 if (ei->type != E820_RAM) continue; -#endif end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; if (end_pfn > last_pfn) -- cgit v1.2.3