From 640e1b38b00550990cecd809021cd37716e45922 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 28 Jan 2017 11:13:08 +0100 Subject: [PATCH] x86/boot/e820: Basic cleanup of e820.c Over the last decade or so e820.c has become an ureadable mess of tinkerware. Perform some very basic cleanups before doing more intricate cleanups, so that my eyes don't start bleeding when I look at it. Here's some of the excesses: - Total disregard of countless aspects of Documentation/CodingStyle. - Totally inconsistent hodge-podge of various coding styles and practices. - Gems like: (unsigned long long) e820_table->entries[i].addr ... which is a completely unnecessary type conversion of an u64 value. - Incomprehensible comments while there are major functions with absolutely no explanation - plus an armada of typos and grammar mistakes. - Mindless checkpatch artifacts such as: if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) { for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { - Actively misleading comments: /* In case someone cares... */ return who; ( The usage site of the return value just a few lines further down makes it clear that we very much care about the return value, we use it to print out the e820 map... ) - Colorfully inconsistent capitalization and punctuation throughout. - etc. This patch fixes only the worst excesses - there's more to fix. No change in functionality. Cc: Alex Thorlton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Huang, Ying Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Paul Jackson Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Tejun Heo Cc: Thomas Gleixner Cc: Wei Yang Cc: Yinghai Lu Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/e820.c | 447 +++++++++++++++++++---------------------- 1 file changed, 207 insertions(+), 240 deletions(-) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 86d6d823e47e..624190fe86a7 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1,12 +1,12 @@ /* - * Handle the memory map. - * The functions here do the job until bootmem takes over. + * Low level x86 E820 memory map handling functions. * - * Getting sanitize_e820_table() in sync with i386 version by applying change: - * - Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach , December 2002. - * Venkatesh Pallipadi + * The firmware and bootloader passes us the "E820 table", which is the primary + * physical memory layout description available about x86 systems. * + * The kernel takes the E820 memory layout and optionally modifies it with + * quirks and other tweaks, and feeds that into the generic Linux memory + * allocation code routines via a platform independent interface (memblock, etc.). */ #include #include @@ -27,13 +27,6 @@ #include /* - * The firmware and bootloader passes us an E820 table that is the primary - * physical memory layout description available about x86 systems. - * - * The kernel takes the e820 memory layout and optionally modifies it with - * quirks and other tweaks, and feeds that into the generic Linux memory - * allocation code routines via a platform independent interface (memblock, etc.). - * * We organize the E820 table into two main data structures: * * - 'e820_table_firmware': the original firmware version passed to us by the @@ -45,16 +38,16 @@ * - the hibernation code uses it to generate a kernel-independent MD5 * fingerprint of the physical memory layout of a system. * - * - kexec, which is a bootloader in disguise, uses the original e820 + * - kexec, which is a bootloader in disguise, uses the original E820 * layout to pass to the kexec-ed kernel. This way the original kernel - * can have a restricted e820 map while the kexec()-ed kexec-kernel + * can have a restricted E820 map while the kexec()-ed kexec-kernel * can have access to full memory - etc. * - * - 'e820_table': this is the main e820 table that is massaged by the + * - 'e820_table': this is the main E820 table that is massaged by the * low level x86 platform code, or modified by boot parameters, before * passed on to higher level MM layers. * - * Once the e820 map has been converted to the standard Linux memory layout + * Once the E820 map has been converted to the standard Linux memory layout * information its role stops - modifying it has no effect and does not get * re-propagated. So itsmain role is a temporary bootstrap storage of firmware * specific memory layout data during early bootup. @@ -75,8 +68,7 @@ EXPORT_SYMBOL(pci_mem_start); * This function checks if any part of the range is mapped * with type. */ -int -e820_any_mapped(u64 start, u64 end, unsigned type) +int e820_any_mapped(u64 start, u64 end, unsigned type) { int i; @@ -94,10 +86,10 @@ e820_any_mapped(u64 start, u64 end, unsigned type) EXPORT_SYMBOL_GPL(e820_any_mapped); /* - * This function checks if the entire range is mapped with type. + * 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 + * Note: this function only works correctly once the E820 table is sorted and + * not-overlapping (at least for the range specified), which is the case normally. */ int __init e820_all_mapped(u64 start, u64 end, unsigned type) { @@ -108,18 +100,21 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) if (type && ei->type != type) continue; - /* is the region (part) in overlap with the current region ?*/ + + /* 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 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' is now at or beyond 'end', we're done, full + * coverage of the desired range exists: */ if (start >= end) return 1; @@ -128,16 +123,14 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) } /* - * Add a memory region to the kernel e820 map. + * Add a memory region to the kernel E820 map. */ static void __init __e820_add_region(struct e820_table *table, u64 start, u64 size, int type) { int x = table->nr_entries; if (x >= ARRAY_SIZE(table->entries)) { - printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", - (unsigned long long) start, - (unsigned long long) (start + size - 1)); + printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1); return; } @@ -155,29 +148,15 @@ void __init e820_add_region(u64 start, u64 size, int type) static void __init e820_print_type(u32 type) { switch (type) { - case E820_RAM: - case E820_RESERVED_KERN: - printk(KERN_CONT "usable"); - break; - case E820_RESERVED: - printk(KERN_CONT "reserved"); - break; - case E820_ACPI: - printk(KERN_CONT "ACPI data"); - break; - case E820_NVS: - printk(KERN_CONT "ACPI NVS"); - break; - case E820_UNUSABLE: - printk(KERN_CONT "unusable"); - break; - case E820_PMEM: - case E820_PRAM: - printk(KERN_CONT "persistent (type %u)", type); - break; - default: - printk(KERN_CONT "type %u", type); - break; + case E820_RAM: /* Fall through: */ + case E820_RESERVED_KERN: printk(KERN_CONT "usable"); break; + case E820_RESERVED: printk(KERN_CONT "reserved"); break; + case E820_ACPI: printk(KERN_CONT "ACPI data"); break; + case E820_NVS: printk(KERN_CONT "ACPI NVS"); break; + case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PMEM: /* Fall through: */ + case E820_PRAM: printk(KERN_CONT "persistent (type %u)", type); break; + default: printk(KERN_CONT "type %u", type); break; } } @@ -187,26 +166,26 @@ void __init e820_print_map(char *who) for (i = 0; i < e820_table->nr_entries; i++) { printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who, - (unsigned long long) e820_table->entries[i].addr, - (unsigned long long) - (e820_table->entries[i].addr + e820_table->entries[i].size - 1)); + e820_table->entries[i].addr, + e820_table->entries[i].addr + e820_table->entries[i].size - 1); + e820_print_type(e820_table->entries[i].type); printk(KERN_CONT "\n"); } } /* - * Sanitize the BIOS e820 map. + * Sanitize the BIOS E820 map. * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps, + * Some E820 responses include overlapping entries. The following + * 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 * e820_entry' 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 + * 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 @@ -257,8 +236,10 @@ void __init e820_print_map(char *who) * ______________________4_ */ struct change_member { - struct e820_entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ + /* Pointer to the original BIOS entry: */ + struct e820_entry *pbios; + /* Address for this change point: */ + unsigned long long addr; }; static int __init cpcompare(const void *a, const void *b) @@ -268,7 +249,7 @@ static int __init cpcompare(const void *a, const void *b) /* * Inputs are pointers to two elements of change_point[]. If their - * addresses are unequal, their difference dominates. If the addresses + * addresses are not equal, their difference dominates. If the addresses * are equal, then consider one that represents the end of its region * to be greater than one that does not. */ @@ -278,8 +259,7 @@ static int __init cpcompare(const void *a, const void *b) return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr); } -int __init sanitize_e820_table(struct e820_entry *biosmap, int max_nr_map, - u32 *pnr_map) +int __init sanitize_e820_table(struct e820_entry *biosmap, int max_nr_map, u32 *pnr_map) { static struct change_member change_point_list[2*E820_X_MAX] __initdata; static struct change_member *change_point[2*E820_X_MAX] __initdata; @@ -293,112 +273,96 @@ int __init sanitize_e820_table(struct e820_entry *biosmap, int max_nr_map, int old_nr, new_nr, chg_nr; int i; - /* if there's only one memory region, don't bother */ + /* If there's only one memory region, don't bother: */ if (*pnr_map < 2) 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++) + /* Bail out if we find any unreasonable addresses in the 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) */ + /* 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 */ + /* + * Record all known change-points (starting and ending addresses), + * omitting 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]; + 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) */ + /* Sort change-point list by memory addresses (low -> high): */ sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL); - /* 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 */ + /* 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 */ + /* Loop through change-points, determining effect 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; + /* 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) - */ + /* 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]; + 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 + * 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++) + 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 - */ + } + + /* Continue building up new BIOS map based on this information: */ if (current_type != last_type || current_type == E820_PRAM) { 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 - */ + 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 ? - */ + /* No more space left for new BIOS entries? */ if (++new_bios_entry >= max_nr_map) break; } if (current_type != 0) { - new_bios[new_bios_entry].addr = - change_point[chgidx]->addr; + 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 */ + + /* 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 e820_entry)); + /* Copy new BIOS mapping into the original location: */ + memcpy(biosmap, new_bios, new_nr*sizeof(struct e820_entry)); *pnr_map = new_nr; return 0; @@ -412,7 +376,7 @@ static int __init __append_e820_table(struct e820_entry *biosmap, int nr_map) u64 end = start + size - 1; u32 type = biosmap->type; - /* Overflow in 64 bits? Ignore the memory map. */ + /* Ignore the entry on 64-bit overflow: */ if (start > end && likely(size)) return -1; @@ -425,7 +389,7 @@ static int __init __append_e820_table(struct e820_entry *biosmap, int nr_map) } /* - * Copy the BIOS e820 map into a safe place. + * Copy the BIOS E820 map into a safe place. * * Sanity-check it while we're at it.. * @@ -442,9 +406,8 @@ static int __init append_e820_table(struct e820_entry *biosmap, int nr_map) return __append_e820_table(biosmap, nr_map); } -static u64 __init __e820_update_range(struct e820_table *table, u64 start, - u64 size, unsigned old_type, - unsigned new_type) +static u64 __init +__e820_update_range(struct e820_table *table, u64 start, u64 size, unsigned old_type, unsigned new_type) { u64 end; unsigned int i; @@ -456,8 +419,7 @@ static u64 __init __e820_update_range(struct e820_table *table, u64 start, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); + printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1); e820_print_type(old_type); printk(KERN_CONT " ==> "); e820_print_type(new_type); @@ -472,14 +434,15 @@ static u64 __init __e820_update_range(struct e820_table *table, u64 start, continue; ei_end = ei->addr + ei->size; - /* totally covered by new range? */ + + /* Completely covered by new range? */ if (ei->addr >= start && ei_end <= end) { ei->type = new_type; real_updated_size += ei->size; continue; } - /* new range is totally covered? */ + /* New range is completely covered? */ if (ei->addr < start && ei_end > end) { __e820_add_region(table, start, size, new_type); __e820_add_region(table, end, ei_end - end, ei->type); @@ -488,45 +451,41 @@ static u64 __init __e820_update_range(struct e820_table *table, u64 start, continue; } - /* partially covered */ + /* Partially covered: */ final_start = max(start, ei->addr); final_end = min(end, ei_end); if (final_start >= final_end) continue; - __e820_add_region(table, final_start, final_end - final_start, - new_type); + __e820_add_region(table, final_start, final_end - final_start, new_type); real_updated_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * its size first: */ ei->size -= final_end - final_start; if (ei->addr < final_start) continue; + ei->addr = final_end; } return real_updated_size; } -u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) +u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type) { return __e820_update_range(e820_table, start, size, old_type, new_type); } -static u64 __init e820_update_range_firmware(u64 start, u64 size, - unsigned old_type, unsigned new_type) +static u64 __init e820_update_range_firmware(u64 start, u64 size, unsigned old_type, unsigned new_type) { - return __e820_update_range(e820_table_firmware, start, size, old_type, - new_type); + return __e820_update_range(e820_table_firmware, 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) +/* Remove a range of memory from the E820 table: */ +u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, int checktype) { int i; u64 end; @@ -536,8 +495,7 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); + printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1); if (checktype) e820_print_type(old_type); printk(KERN_CONT "\n"); @@ -551,14 +509,15 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, continue; ei_end = ei->addr + ei->size; - /* totally covered? */ + + /* Completely covered? */ if (ei->addr >= start && ei_end <= end) { real_removed_size += ei->size; memset(ei, 0, sizeof(struct e820_entry)); continue; } - /* new range is totally covered? */ + /* Is the new range completely covered? */ if (ei->addr < start && ei_end > end) { e820_add_region(end, ei_end - end, ei->type); ei->size = start - ei->addr; @@ -566,20 +525,22 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, continue; } - /* partially covered */ + /* Partially covered: */ final_start = max(start, ei->addr); final_end = min(end, ei_end); if (final_start >= final_end) continue; + real_removed_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * the size first: */ ei->size -= final_end - final_start; if (ei->addr < final_start) continue; + ei->addr = final_end; } return real_removed_size; @@ -589,19 +550,22 @@ void __init update_e820(void) { if (sanitize_e820_table(e820_table->entries, ARRAY_SIZE(e820_table->entries), &e820_table->nr_entries)) return; + printk(KERN_INFO "e820: modified physical RAM map:\n"); e820_print_map("modified"); } + static void __init update_e820_table_firmware(void) { sanitize_e820_table(e820_table_firmware->entries, ARRAY_SIZE(e820_table_firmware->entries), &e820_table_firmware->nr_entries); } + #define MAX_GAP_END 0x100000000ull + /* - * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. + * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB). */ -static int __init e820_search_gap(unsigned long *gapstart, - unsigned long *gapsize) +static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize) { unsigned long long last = MAX_GAP_END; int i = e820_table->nr_entries; @@ -613,7 +577,7 @@ static int __init e820_search_gap(unsigned long *gapstart, /* * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true + * fit in 32 bits if this condition is true: */ if (last > end) { unsigned long gap = last - end; @@ -631,9 +595,11 @@ static int __init e820_search_gap(unsigned long *gapstart, } /* - * 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. + * Search for the biggest gap in the low 32 bits of the E820 + * memory space. We pass this space to the PCI subsystem, so + * that it can assign MMIO resources for hotplug or + * unconfigured devices in. + * * Hopefully the BIOS let enough space left. */ __init void e820_setup_gap(void) @@ -648,8 +614,8 @@ __init void e820_setup_gap(void) #ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; printk(KERN_ERR - "e820: cannot find a gap in the 32bit address range\n" - "e820: PCI devices with unassigned 32bit BARs may break!\n"); + "e820: Cannot find an available gap in the 32-bit address range\n" + "e820: PCI devices with unassigned 32-bit BARs may not work!\n"); #else gapstart = 0x10000000; #endif @@ -660,43 +626,44 @@ __init void e820_setup_gap(void) */ pci_mem_start = gapstart; - printk(KERN_INFO - "e820: [mem %#010lx-%#010lx] available for PCI devices\n", - gapstart, gapstart + gapsize - 1); + printk(KERN_INFO "e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1); } /* * Called late during init, in free_initmem(). * - * Initial e820 and e820_table_firmware are largish __initdata arrays. - * Copy them to (usually much smaller) dynamically allocated area. - * This is done after all tweaks we ever do to them: - * all functions which modify them are __init functions, - * they won't exist after this point. + * Initial e820_table and e820_table_firmware are largish __initdata arrays. + * + * Copy them to a (usually much smaller) dynamically allocated area that is + * sized precisely after the number of e820 entries. + * + * This is done after we've performed all the fixes and tweaks to the tables. + * All functions which modify them are __init functions, which won't exist + * after free_initmem(). */ __init void e820_reallocate_tables(void) { struct e820_table *n; int size; - size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * e820_table->nr_entries; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); memcpy(n, e820_table, size); e820_table = n; - size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * e820_table_firmware->nr_entries; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); memcpy(n, e820_table_firmware, size); e820_table_firmware = n; } -/** - * Because of the size limitation of struct boot_params, only first - * 128 E820 memory entries are passed to kernel via - * boot_params.e820_table, others are passed via SETUP_E820_EXT node of - * linked list of struct setup_data, which is parsed here. +/* + * Because of the small fixed size of struct boot_params, only the first + * 128 E820 memory entries are passed to the kernel via boot_params.e820_table, + * the remaining (if any) entries are passed via the SETUP_E820_EXT node of + * struct setup_data, which is parsed here. */ void __init parse_e820_ext(u64 phys_addr, u32 data_len) { @@ -707,8 +674,10 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) sdata = early_memremap(phys_addr, data_len); entries = sdata->len / sizeof(struct e820_entry); extmap = (struct e820_entry *)(sdata->data); + __append_e820_table(extmap, entries); sanitize_e820_table(e820_table->entries, ARRAY_SIZE(e820_table->entries), &e820_table->nr_entries); + early_memunmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); @@ -716,10 +685,10 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) /** * 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). + * 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 + * This function requires the E820 map to be sorted and without any * overlapping entries. */ void __init e820_mark_nosave_regions(unsigned long limit_pfn) @@ -744,9 +713,9 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) } #ifdef CONFIG_ACPI -/** - * Mark ACPI NVS memory region, so that we can save/restore it during - * hibernation and the subsequent resume. +/* + * Register ACPI NVS memory regions, so that we can save/restore them during + * hibernation and the subsequent resume: */ static int __init e820_mark_nvs_memory(void) { @@ -828,6 +797,7 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) last_pfn, max_arch_pfn); return last_pfn; } + unsigned long __init e820_end_of_ram_pfn(void) { return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); @@ -846,7 +816,7 @@ static void __init early_panic(char *msg) static int userdef __initdata; -/* "mem=nopentium" disables the 4MB page tables. */ +/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */ static int __init parse_memopt(char *p) { u64 mem_size; @@ -866,9 +836,11 @@ static int __init parse_memopt(char *p) userdef = 1; mem_size = memparse(p, &p); - /* don't remove all of memory when handling "mem={invalid}" param */ + + /* Don't remove all memory when getting "mem={invalid}" parameter: */ if (mem_size == 0) return -EINVAL; + e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); return 0; @@ -887,7 +859,7 @@ static int __init parse_memmap_one(char *p) #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 + * the real memory size before the original memory map is * reset. */ saved_max_pfn = e820_end_of_ram_pfn(); @@ -915,11 +887,13 @@ static int __init parse_memmap_one(char *p) } else if (*p == '!') { start_at = memparse(p+1, &p); e820_add_region(start_at, mem_size, E820_PRAM); - } else + } else { e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + } return *p == '\0' ? 0 : -EINVAL; } + static int __init parse_memmap_opt(char *str) { while (str) { @@ -939,8 +913,7 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - if (sanitize_e820_table(e820_table->entries, ARRAY_SIZE(e820_table->entries), - &e820_table->nr_entries) < 0) + if (sanitize_e820_table(e820_table->entries, ARRAY_SIZE(e820_table->entries), &e820_table->nr_entries) < 0) early_panic("Invalid user supplied memory map"); printk(KERN_INFO "e820: user-defined physical RAM map:\n"); @@ -951,49 +924,42 @@ void __init finish_e820_parsing(void) static const char *__init 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"; - case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent Memory (legacy)"; - case E820_PMEM: return "Persistent Memory"; - default: return "reserved"; + case E820_RESERVED_KERN: /* Fall-through: */ + case E820_RAM: return "System RAM"; + case E820_ACPI: return "ACPI Tables"; + case E820_NVS: return "ACPI Non-volatile Storage"; + case E820_UNUSABLE: return "Unusable memory"; + case E820_PRAM: return "Persistent Memory (legacy)"; + case E820_PMEM: return "Persistent Memory"; + default: return "Reserved"; } } static unsigned long __init e820_type_to_iomem_type(int e820_type) { switch (e820_type) { - case E820_RESERVED_KERN: - case E820_RAM: - return IORESOURCE_SYSTEM_RAM; - case E820_ACPI: - case E820_NVS: - case E820_UNUSABLE: - case E820_PRAM: - case E820_PMEM: - default: - return IORESOURCE_MEM; + case E820_RESERVED_KERN: /* Fall-through: */ + case E820_RAM: return IORESOURCE_SYSTEM_RAM; + case E820_ACPI: /* Fall-through: */ + case E820_NVS: /* Fall-through: */ + case E820_UNUSABLE: /* Fall-through: */ + case E820_PRAM: /* Fall-through: */ + case E820_PMEM: /* Fall-through: */ + default: return IORESOURCE_MEM; } } static unsigned long __init e820_type_to_iores_desc(int e820_type) { switch (e820_type) { - case E820_ACPI: - return IORES_DESC_ACPI_TABLES; - case E820_NVS: - return IORES_DESC_ACPI_NV_STORAGE; - case E820_PMEM: - return IORES_DESC_PERSISTENT_MEMORY; - case E820_PRAM: - return IORES_DESC_PERSISTENT_MEMORY_LEGACY; - case E820_RESERVED_KERN: - case E820_RAM: - case E820_UNUSABLE: - default: - return IORES_DESC_NONE; + case E820_ACPI: return IORES_DESC_ACPI_TABLES; + case E820_NVS: return IORES_DESC_ACPI_NV_STORAGE; + case E820_PMEM: return IORES_DESC_PERSISTENT_MEMORY; + case E820_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY; + case E820_RESERVED_KERN: /* Fall-through: */ + case E820_RAM: /* Fall-through: */ + case E820_UNUSABLE: /* Fall-through: */ + default: return IORES_DESC_NONE; } } @@ -1018,9 +984,11 @@ static bool __init do_mark_busy(u32 type, struct resource *res) } /* - * Mark e820 reserved areas as busy for the resource manager. + * Mark E820 reserved areas as busy for the resource manager: */ + static struct resource __initdata *e820_res; + void __init e820_reserve_resources(void) { int i; @@ -1056,9 +1024,8 @@ void __init e820_reserve_resources(void) for (i = 0; i < e820_table_firmware->nr_entries; i++) { struct e820_entry *entry = &e820_table_firmware->entries[i]; - firmware_map_add_early(entry->addr, - entry->addr + entry->size, - e820_type_to_string(entry->type)); + + firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry->type)); } } @@ -1094,7 +1061,7 @@ void __init e820_reserve_resources_late(void) } /* - * Try to bump up RAM regions to reasonable boundaries to + * Try to bump up RAM regions to reasonable boundaries, to * avoid stolen RAM: */ for (i = 0; i < e820_table->nr_entries; i++) { @@ -1103,24 +1070,27 @@ void __init e820_reserve_resources_late(void) if (entry->type != E820_RAM) continue; + start = entry->addr + entry->size; end = round_up(start, ram_alignment(start)) - 1; if (end > MAX_RESOURCE_SIZE) end = MAX_RESOURCE_SIZE; if (start >= end) continue; - printk(KERN_DEBUG - "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", - start, end); - reserve_region_with_split(&iomem_resource, start, end, - "RAM buffer"); + + printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end); + reserve_region_with_split(&iomem_resource, start, end, "RAM buffer"); } } +/* + * Pass the firmware (bootloader) E820 map to the kernel and process it: + */ char *__init e820__memory_setup_default(void) { char *who = "BIOS-e820"; u32 new_nr; + /* * Try to copy the BIOS-supplied E820-map. * @@ -1128,17 +1098,14 @@ char *__init e820__memory_setup_default(void) * the next section from 1mb->appropriate_mem_k */ new_nr = boot_params.e820_entries; - sanitize_e820_table(boot_params.e820_table, - ARRAY_SIZE(boot_params.e820_table), - &new_nr); + sanitize_e820_table(boot_params.e820_table, ARRAY_SIZE(boot_params.e820_table), &new_nr); boot_params.e820_entries = new_nr; - if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) - < 0) { + + if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) { u64 mem_size; - /* compare results from other methods and take the greater */ - if (boot_params.alt_mem_k - < boot_params.screen_info.ext_mem_k) { + /* Compare results from other methods and take the one that gives more RAM: */ + 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 { @@ -1151,7 +1118,6 @@ char *__init e820__memory_setup_default(void) e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); } - /* In case someone cares... */ return who; } @@ -1165,7 +1131,9 @@ void __init e820__memory_setup(void) char *who; who = x86_init.resources.memory_setup(); + memcpy(e820_table_firmware, e820_table, sizeof(struct e820_table)); + printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n"); e820_print_map(who); } @@ -1221,8 +1189,7 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, - NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn)