From 1f5026a7e21e409c2b9dd54f6dfb9446511fb7c5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Jul 2011 09:58:09 +0200 Subject: memblock: Kill MEMBLOCK_ERROR 25818f0f28 (memblock: Make MEMBLOCK_ERROR be 0) thankfully made MEMBLOCK_ERROR 0 and there already are codes which expect error return to be 0. There's no point in keeping MEMBLOCK_ERROR around. End its misery. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/r/1310457490-3356-6-git-send-email-tj@kernel.org Cc: Yinghai Lu Cc: Benjamin Herrenschmidt Signed-off-by: H. Peter Anvin --- arch/x86/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/setup.c') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index afaf38447ef5..31ffe20d5d27 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -331,7 +331,7 @@ static void __init relocate_initrd(void) ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size, PAGE_SIZE); - if (ramdisk_here == MEMBLOCK_ERROR) + if (!ramdisk_here) panic("Cannot find place for new RAMDISK of size %lld\n", ramdisk_size); @@ -554,7 +554,7 @@ static void __init reserve_crashkernel(void) crash_base = memblock_find_in_range(alignment, CRASH_KERNEL_ADDR_MAX, crash_size, alignment); - if (crash_base == MEMBLOCK_ERROR) { + if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } -- cgit v1.2.3 From 24aa07882b672fff2da2f5c955759f0bd13d32d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Jul 2011 11:16:06 +0200 Subject: memblock, x86: Replace memblock_x86_reserve/free_range() with generic ones Other than sanity check and debug message, the x86 specific version of memblock reserve/free functions are simple wrappers around the generic versions - memblock_reserve/free(). This patch adds debug messages with caller identification to the generic versions and replaces x86 specific ones and kills them. arch/x86/include/asm/memblock.h and arch/x86/mm/memblock.c are empty after this change and removed. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/r/1310462166-31469-14-git-send-email-tj@kernel.org Cc: Yinghai Lu Cc: Benjamin Herrenschmidt Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/memblock.h | 7 ------- arch/x86/kernel/aperture_64.c | 2 +- arch/x86/kernel/check.c | 2 +- arch/x86/kernel/head.c | 2 +- arch/x86/kernel/head32.c | 5 +++-- arch/x86/kernel/head64.c | 5 +++-- arch/x86/kernel/mpparse.c | 6 ++---- arch/x86/kernel/setup.c | 17 ++++++++--------- arch/x86/kernel/trampoline.c | 2 +- arch/x86/mm/Makefile | 2 -- arch/x86/mm/init.c | 6 +++--- arch/x86/mm/memblock.c | 34 ---------------------------------- arch/x86/mm/memtest.c | 2 +- arch/x86/mm/numa.c | 5 ++--- arch/x86/mm/numa_32.c | 6 +++--- arch/x86/mm/numa_emulation.c | 4 ++-- arch/x86/platform/efi/efi.c | 6 ++---- arch/x86/xen/mmu.c | 12 ++++-------- arch/x86/xen/setup.c | 7 +++---- include/linux/memblock.h | 2 -- mm/memblock.c | 5 +++++ mm/nobootmem.c | 6 +++--- 22 files changed, 48 insertions(+), 97 deletions(-) delete mode 100644 arch/x86/include/asm/memblock.h delete mode 100644 arch/x86/mm/memblock.c (limited to 'arch/x86/kernel/setup.c') diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h deleted file mode 100644 index bc5667081aea..000000000000 --- a/arch/x86/include/asm/memblock.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _X86_MEMBLOCK_H -#define _X86_MEMBLOCK_H - -void memblock_x86_reserve_range(u64 start, u64 end, char *name); -void memblock_x86_free_range(u64 start, u64 end); - -#endif diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 56363082bbdf..6e76c191a835 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -94,7 +94,7 @@ static u32 __init allocate_aperture(void) addr, aper_size>>10); return 0; } - memblock_x86_reserve_range(addr, addr + aper_size, "aperture64"); + memblock_reserve(addr, aper_size); /* * Kmemleak should not scan this block as it may not be mapped via the * kernel direct mapping. diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 621cd23bb4e7..5da1269e8ddc 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -91,7 +91,7 @@ void __init setup_bios_corruption_check(void) if (start >= end) continue; - memblock_x86_reserve_range(start, end, "SCAN RAM"); + memblock_reserve(start, end - start); scan_areas[num_scan_areas].addr = start; scan_areas[num_scan_areas].size = end - start; diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index af0699ba48cf..48d9d4ea1020 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -52,5 +52,5 @@ void __init reserve_ebda_region(void) lowmem = 0x9f000; /* reserve all memory between lowmem and the 1MB mark */ - memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved"); + memblock_reserve(lowmem, 0x100000 - lowmem); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 3bb08509a7a1..be9282bcda72 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -33,7 +33,8 @@ void __init i386_start_kernel(void) { memblock_init(); - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -42,7 +43,7 @@ void __init i386_start_kernel(void) u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 5655c2272adb..fd25b11549b8 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -100,7 +100,8 @@ void __init x86_64_start_reservations(char *real_mode_data) memblock_init(); - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -109,7 +110,7 @@ void __init x86_64_start_reservations(char *real_mode_data) unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 8faeaa0ed2cc..a6b79c16ec78 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -564,9 +564,7 @@ void __init default_get_smp_config(unsigned int early) static void __init smp_reserve_memory(struct mpf_intel *mpf) { - unsigned long size = get_mpc_size(mpf->physptr); - - memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc"); + memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr)); } static int __init smp_scan_config(unsigned long base, unsigned long length) @@ -595,7 +593,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf, (u64)virt_to_phys(mpf)); mem = virt_to_phys(mpf); - memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf"); + memblock_reserve(mem, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 31ffe20d5d27..97d227ec995d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -306,7 +306,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK"); + memblock_reserve(__pa(_brk_start), + __pa(_brk_end) - __pa(_brk_start)); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -337,7 +338,7 @@ static void __init relocate_initrd(void) /* Note: this includes all the lowmem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK"); + memblock_reserve(ramdisk_here, area_size); initrd_start = ramdisk_here + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", @@ -393,7 +394,7 @@ static void __init reserve_initrd(void) initrd_start = 0; if (ramdisk_size >= (end_of_lowmem>>1)) { - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); printk(KERN_ERR "initrd too large to handle, " "disabling initrd\n"); return; @@ -416,7 +417,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else static void __init reserve_initrd(void) @@ -490,15 +491,13 @@ static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; u64 pa_data; - char buf[32]; if (boot_params.hdr.version < 0x0209) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); - sprintf(buf, "setup data %x", data->type); - memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf); + memblock_reserve(pa_data, sizeof(*data) + data->len); pa_data = data->next; early_iounmap(data, sizeof(*data)); } @@ -568,7 +567,7 @@ static void __init reserve_crashkernel(void) return; } } - memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL"); + memblock_reserve(crash_base, crash_size); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -626,7 +625,7 @@ static __init void reserve_ibft_region(void) addr = find_ibft_region(&size); if (size) - memblock_x86_reserve_range(addr, addr + size, "* ibft"); + memblock_reserve(addr, size); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index a1f13ddb06e0..a73b61055ad6 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -18,7 +18,7 @@ void __init setup_trampolines(void) panic("Cannot allocate trampoline\n"); x86_trampoline_base = __va(mem); - memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE"); + memblock_reserve(mem, size); printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", x86_trampoline_base, (unsigned long long)mem, size); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 3d11327c9ab4..23d8e5fecf76 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -27,6 +27,4 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o - obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 13cf05a61605..0b736b99d925 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -81,7 +81,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, void __init native_pagetable_reserve(u64 start, u64 end) { - memblock_x86_reserve_range(start, end, "PGTABLE"); + memblock_reserve(start, end - start); } struct map_range { @@ -280,8 +280,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top) * so that they can be reused for other purposes. * - * On native it just means calling memblock_x86_reserve_range, on Xen it - * also means marking RW the pagetable pages that we allocated before + * On native it just means calling memblock_reserve, on Xen it also + * means marking RW the pagetable pages that we allocated before * but that haven't been used. * * In fact on xen we mark RO the whole range pgt_buf_start - diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c deleted file mode 100644 index 7325c5d8ace5..000000000000 --- a/arch/x86/mm/memblock.c +++ /dev/null @@ -1,34 +0,0 @@ -#include -#include -#include -#include -#include -#include -#include -#include - -void __init memblock_x86_reserve_range(u64 start, u64 end, char *name) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name); - - memblock_reserve(start, end - start); -} - -void __init memblock_x86_free_range(u64 start, u64 end) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1); - - memblock_free(start, end - start); -} diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 46a5ff25eda4..c80b9fb95734 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -34,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad) (unsigned long long) pattern, (unsigned long long) start_bad, (unsigned long long) end_bad); - memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM"); + memblock_reserve(start_bad, end_bad - start_bad); } static void __init memtest(u64 pattern, u64 start_phys, u64 size) diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 88e562729967..496f494593bf 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -364,8 +364,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_x86_free_range(__pa(numa_distance), - __pa(numa_distance) + size); + memblock_free(__pa(numa_distance), size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } @@ -394,7 +393,7 @@ static int __init numa_alloc_distance(void) numa_distance = (void *)1LU; return -ENOMEM; } - memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); + memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 58878b536ef2..534255a36b6b 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -204,7 +204,7 @@ void __init init_alloc_remap(int nid, u64 start, u64 end) size, nid); return; } - memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM"); + memblock_reserve(node_pa, size); remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT, @@ -212,10 +212,10 @@ void __init init_alloc_remap(int nid, u64 start, u64 end) if (!remap_pa) { pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", size, nid); - memblock_x86_free_range(node_pa, node_pa + size); + memblock_free(node_pa, size); return; } - memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG"); + memblock_reserve(remap_pa, size); remap_va = phys_to_virt(remap_pa); /* perform actual remap */ diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 971fe70549b3..46db56845f18 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -361,7 +361,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST"); + memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) @@ -430,7 +430,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) /* free the copied physical distance table */ if (phys_dist) - memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size); + memblock_free(__pa(phys_dist), phys_size); return; no_emu: diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index a4c322ca1a5d..3b4e86bda3cb 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -280,8 +280,7 @@ void __init efi_memblock_x86_reserve_range(void) boot_params.efi_info.efi_memdesc_size; memmap.desc_version = boot_params.efi_info.efi_memdesc_version; memmap.desc_size = boot_params.efi_info.efi_memdesc_size; - memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size, - "EFI memmap"); + memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); } #if EFI_DEBUG @@ -332,8 +331,7 @@ void __init efi_reserve_boot_services(void) "[0x%010llx-0x%010llx]\n", start, start+size-1); } else - memblock_x86_reserve_range(start, start+size, - "EFI Boot"); + memblock_reserve(start, size); } } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 0ccccb67a993..ad54fa10f8a2 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1720,10 +1720,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, __xen_write_cr3(true, __pa(pgd)); xen_mc_issue(PARAVIRT_LAZY_CPU); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE); return pgd; } @@ -1799,10 +1797,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, PFN_DOWN(__pa(initial_page_table))); xen_write_cr3(__pa(initial_page_table)); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE)); return initial_page_table; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 60aeeb56948f..73daaf75801a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -63,7 +63,7 @@ static void __init xen_add_extra_mem(unsigned long pages) e820_add_region(extra_start, size, E820_RAM); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA"); + memblock_reserve(extra_start, size); xen_extra_mem_size += size; @@ -287,9 +287,8 @@ char * __init xen_memory_setup(void) * - xen_start_info * See comment above "struct start_info" in */ - memblock_x86_reserve_range(__pa(xen_start_info->mfn_list), - __pa(xen_start_info->pt_base), - "XEN START INFO"); + memblock_reserve(__pa(xen_start_info->mfn_list), + xen_start_info->pt_base - xen_start_info->mfn_list); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2491355bb6e4..90746318cec4 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -17,8 +17,6 @@ #include #include -#include - #define INIT_MEMBLOCK_REGIONS 128 struct memblock_region { diff --git a/mm/memblock.c b/mm/memblock.c index ebc6119f1280..0cb4da657b9d 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -449,6 +449,9 @@ long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { + memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", + base, base + size, (void *)_RET_IP_); + return __memblock_remove(&memblock.reserved, base, size); } @@ -456,6 +459,8 @@ long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { struct memblock_type *_rgn = &memblock.reserved; + memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n", + base, base + size, (void *)_RET_IP_); BUG_ON(0 == size); return memblock_add_region(_rgn, base, size); diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 7075bc00fa84..29d948ce6d0f 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -47,7 +47,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, ptr = phys_to_virt(addr); memset(ptr, 0, size); - memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); + memblock_reserve(addr, size); /* * The min_count is set to 0 so that bootmem allocated blocks * are never reported as leaks. @@ -175,7 +175,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { kmemleak_free_part(__va(physaddr), size); - memblock_x86_free_range(physaddr, physaddr + size); + memblock_free(physaddr, size); } /** @@ -190,7 +190,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, void __init free_bootmem(unsigned long addr, unsigned long size) { kmemleak_free_part(__va(addr), size); - memblock_x86_free_range(addr, addr + size); + memblock_free(addr, size); } static void * __init ___alloc_bootmem_nopanic(unsigned long size, -- cgit v1.2.3 From e8c7106280a305e1ff2a3a8a4dfce141469fb039 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Fri, 18 Nov 2011 13:09:11 +0000 Subject: x86, efi: Calling __pa() with an ioremap()ed address is invalid If we encounter an efi_memory_desc_t without EFI_MEMORY_WB set in ->attribute we currently call set_memory_uc(), which in turn calls __pa() on a potentially ioremap'd address. On CONFIG_X86_32 this is invalid, resulting in the following oops on some machines: BUG: unable to handle kernel paging request at f7f22280 IP: [] reserve_ram_pages_type+0x89/0x210 [...] Call Trace: [] ? page_is_ram+0x1a/0x40 [] reserve_memtype+0xdf/0x2f0 [] set_memory_uc+0x49/0xa0 [] efi_enter_virtual_mode+0x1c2/0x3aa [] start_kernel+0x291/0x2f2 [] ? loglevel+0x1b/0x1b [] i386_start_kernel+0xbf/0xc8 A better approach to this problem is to map the memory region with the correct attributes from the start, instead of modifying it after the fact. The uncached case can be handled by ioremap_nocache() and the cached by ioremap_cache(). Despite first impressions, it's not possible to use ioremap_cache() to map all cached memory regions on CONFIG_X86_64 because EFI_RUNTIME_SERVICES_DATA regions really don't like being mapped into the vmalloc space, as detailed in the following bug report, https://bugzilla.redhat.com/show_bug.cgi?id=748516 Therefore, we need to ensure that any EFI_RUNTIME_SERVICES_DATA regions are covered by the direct kernel mapping table on CONFIG_X86_64. To accomplish this we now map E820_RESERVED_EFI regions via the direct kernel mapping with the initial call to init_memory_mapping() in setup_arch(), whereas previously these regions wouldn't be mapped if they were after the last E820_RAM region until efi_ioremap() was called. Doing it this way allows us to delete efi_ioremap() completely. Signed-off-by: Matt Fleming Cc: H. Peter Anvin Cc: Matthew Garrett Cc: Zhang Rui Cc: Huang Ying Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1321621751-3650-1-git-send-email-matt@console-pimps.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/e820.h | 8 ++++++++ arch/x86/include/asm/efi.h | 5 ----- arch/x86/kernel/e820.c | 3 ++- arch/x86/kernel/setup.c | 21 ++++++++++++++++++++- arch/x86/platform/efi/efi.c | 29 ++++++++++++++++++----------- arch/x86/platform/efi/efi_64.c | 17 ----------------- 6 files changed, 48 insertions(+), 35 deletions(-) (limited to 'arch/x86/kernel/setup.c') diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 908b96957d88..c9547033e38e 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -53,6 +53,13 @@ */ #define E820_RESERVED_KERN 128 +/* + * Address ranges that need to be mapped by the kernel direct + * mapping. This is used to make sure regions such as + * EFI_RUNTIME_SERVICES_DATA are directly mapped. See setup_arch(). + */ +#define E820_RESERVED_EFI 129 + #ifndef __ASSEMBLY__ #include struct e820entry { @@ -115,6 +122,7 @@ static inline void early_memtest(unsigned long start, unsigned long end) } #endif +extern unsigned long e820_end_pfn(unsigned long limit_pfn, unsigned type); extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 7093e4a6a0bc..b8d8bfcd44a9 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -33,8 +33,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ efi_call_virt(f, a1, a2, a3, a4, a5, a6) -#define efi_ioremap(addr, size, type) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ extern u64 efi_call0(void *fp); @@ -84,9 +82,6 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) -extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, - u32 type); - #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 303a0e48f076..65ffd110a81b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -135,6 +135,7 @@ static void __init e820_print_type(u32 type) printk(KERN_CONT "(usable)"); break; case E820_RESERVED: + case E820_RESERVED_EFI: printk(KERN_CONT "(reserved)"); break; case E820_ACPI: @@ -783,7 +784,7 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) { int i; unsigned long last_pfn = 0; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cf0ef986cb6d..9a9e40fb091c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -691,6 +691,8 @@ early_param("reservelow", parse_reservelow); void __init setup_arch(char **cmdline_p) { + unsigned long end_pfn; + #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); @@ -932,7 +934,24 @@ void __init setup_arch(char **cmdline_p) init_gbpages(); /* max_pfn_mapped is updated here */ - max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<>PAGE_SHIFT, E820_RESERVED_EFI); + if (efi_end > max_low_pfn) + end_pfn = efi_end; + } +#endif + + max_low_pfn_mapped = init_memory_mapping(0, end_pfn << PAGE_SHIFT); max_pfn_mapped = max_low_pfn_mapped; #ifdef CONFIG_X86_64 diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 37718f0f053d..c9718a16be15 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -323,10 +323,13 @@ static void __init do_add_efi_memmap(void) case EFI_UNUSABLE_MEMORY: e820_type = E820_UNUSABLE; break; + case EFI_RUNTIME_SERVICES_DATA: + e820_type = E820_RESERVED_EFI; + break; default: /* * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE - * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO + * EFI_MEMORY_MAPPED_IO * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE */ e820_type = E820_RESERVED; @@ -671,10 +674,21 @@ void __init efi_enter_virtual_mode(void) end_pfn = PFN_UP(end); if (end_pfn <= max_low_pfn_mapped || (end_pfn > (1UL << (32 - PAGE_SHIFT)) - && end_pfn <= max_pfn_mapped)) + && end_pfn <= max_pfn_mapped)) { va = __va(md->phys_addr); - else - va = efi_ioremap(md->phys_addr, size, md->type); + + if (!(md->attribute & EFI_MEMORY_WB)) { + addr = (u64) (unsigned long)va; + npages = md->num_pages; + memrange_efi_to_native(&addr, &npages); + set_memory_uc(addr, npages); + } + } else { + if (!(md->attribute & EFI_MEMORY_WB)) + va = ioremap_nocache(md->phys_addr, size); + else + va = ioremap_cache(md->phys_addr, size); + } md->virt_addr = (u64) (unsigned long) va; @@ -684,13 +698,6 @@ void __init efi_enter_virtual_mode(void) continue; } - if (!(md->attribute & EFI_MEMORY_WB)) { - addr = md->virt_addr; - npages = md->num_pages; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); - } - systab = (u64) (unsigned long) efi_phys.systab; if (md->phys_addr <= systab && systab < end) { systab += md->virt_addr - md->phys_addr; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index ac3aa54e2654..312250c6b2de 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -80,20 +80,3 @@ void __init efi_call_phys_epilog(void) local_irq_restore(efi_flags); early_code_mapping_set_exec(0); } - -void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, - u32 type) -{ - unsigned long last_map_pfn; - - if (type == EFI_MEMORY_MAPPED_IO) - return ioremap(phys_addr, size); - - last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); - if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) { - unsigned long top = last_map_pfn << PAGE_SHIFT; - efi_ioremap(top, size - (top - phys_addr), type); - } - - return (void __iomem *)__va(phys_addr); -} -- cgit v1.2.3 From f7d7d01be53cb47e0ae212c4e968aa28b82d2138 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Tue, 15 Nov 2011 12:56:14 +0000 Subject: x86: Don't use magic strings for EFI loader signature Introduce a symbol, EFI_LOADER_SIGNATURE instead of using the magic strings, which also helps to reduce the amount of ifdeffery. Cc: Matthew Garrett Signed-off-by: Matt Fleming Link: http://lkml.kernel.org/r/1318848017-12301-1-git-send-email-matt@console-pimps.org Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/efi.h | 4 ++++ arch/x86/kernel/setup.c | 7 +------ 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel/setup.c') diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b8d8bfcd44a9..26d8c18d5faa 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,8 @@ #ifdef CONFIG_X86_32 +#define EFI_LOADER_SIGNATURE "EL32" + extern unsigned long asmlinkage efi_call_phys(void *, ...); #define efi_call_phys0(f) efi_call_phys(f) @@ -35,6 +37,8 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #else /* !CONFIG_X86_32 */ +#define EFI_LOADER_SIGNATURE "EL64" + extern u64 efi_call0(void *fp); extern u64 efi_call1(void *fp, u64 arg1); extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 9a9e40fb091c..4d5243c31ac4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -752,12 +752,7 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, -#ifdef CONFIG_X86_32 - "EL32", -#else - "EL64", -#endif - 4)) { + EFI_LOADER_SIGNATURE, 4)) { efi_enabled = 1; efi_memblock_x86_reserve_range(); } -- cgit v1.2.3