Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161733Ab3DENkT (ORCPT ); Fri, 5 Apr 2013 09:40:19 -0400 Received: from aserp1040.oracle.com ([141.146.126.69]:22773 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161548Ab3DENkR (ORCPT ); Fri, 5 Apr 2013 09:40:17 -0400 Date: Fri, 5 Apr 2013 09:38:59 -0400 From: Konrad Rzeszutek Wilk To: Yinghai Lu Cc: Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Andrew Morton , Tejun Heo , Thomas Renninger , Tang Chen , linux-kernel@vger.kernel.org, Pekka Enberg , Jacob Shin Subject: Re: [PATCH v3 21/22] x86, mm: Make init_mem_mapping be able to be called several times Message-ID: <20130405133859.GH20093@phenom.dumpdata.com> References: <1365119186-23487-1-git-send-email-yinghai@kernel.org> <1365119186-23487-22-git-send-email-yinghai@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1365119186-23487-22-git-send-email-yinghai@kernel.org> User-Agent: Mutt/1.5.21 (2010-09-15) X-Source-IP: ucsinet22.oracle.com [156.151.31.94] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8108 Lines: 255 On Thu, Apr 04, 2013 at 04:46:25PM -0700, Yinghai Lu wrote: > Prepare to put page table on local nodes. > > Move calling of init_mem_mapping to early_initmem_init. > > Rework alloc_low_pages to alloc page table in following order: > BRK, local node, low range > > Still only load_cr3 one time, otherwise we would break xen 64bit again. Nope. It should be fixed now. > > Signed-off-by: Yinghai Lu > Cc: Pekka Enberg > Cc: Jacob Shin > Cc: Konrad Rzeszutek Wilk > --- > arch/x86/include/asm/pgtable.h | 2 +- > arch/x86/kernel/setup.c | 1 - > arch/x86/mm/init.c | 88 ++++++++++++++++++++++++++---------------- > arch/x86/mm/numa.c | 24 ++++++++++++ > 4 files changed, 79 insertions(+), 36 deletions(-) > > diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h > index 1e67223..868687c 100644 > --- a/arch/x86/include/asm/pgtable.h > +++ b/arch/x86/include/asm/pgtable.h > @@ -621,7 +621,7 @@ static inline int pgd_none(pgd_t pgd) > #ifndef __ASSEMBLY__ > > extern int direct_gbpages; > -void init_mem_mapping(void); > +void init_mem_mapping(unsigned long begin, unsigned long end); > void early_alloc_pgt_buf(void); > > /* local pte updates need not use xchg for locking */ > diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c > index 6ef3fa2..67ef4bc 100644 > --- a/arch/x86/kernel/setup.c > +++ b/arch/x86/kernel/setup.c > @@ -1105,7 +1105,6 @@ void __init setup_arch(char **cmdline_p) > acpi_boot_table_init(); > early_acpi_boot_init(); > early_initmem_init(); > - init_mem_mapping(); > memblock.current_limit = get_max_mapped(); > early_trap_pf_init(); > > diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c > index 2754e45..8a03283 100644 > --- a/arch/x86/mm/init.c > +++ b/arch/x86/mm/init.c > @@ -24,7 +24,10 @@ static unsigned long __initdata pgt_buf_start; > static unsigned long __initdata pgt_buf_end; > static unsigned long __initdata pgt_buf_top; > > -static unsigned long min_pfn_mapped; > +static unsigned long low_min_pfn_mapped; > +static unsigned long low_max_pfn_mapped; > +static unsigned long local_min_pfn_mapped; > +static unsigned long local_max_pfn_mapped; > > static bool __initdata can_use_brk_pgt = true; > > @@ -52,10 +55,17 @@ __ref void *alloc_low_pages(unsigned int num) > > if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { > unsigned long ret; > - if (min_pfn_mapped >= max_pfn_mapped) > - panic("alloc_low_page: ran out of memory"); > - ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT, > - max_pfn_mapped << PAGE_SHIFT, > + if (local_min_pfn_mapped >= local_max_pfn_mapped) { > + if (low_min_pfn_mapped >= low_max_pfn_mapped) > + panic("alloc_low_page: ran out of memory"); > + ret = memblock_find_in_range( > + low_min_pfn_mapped << PAGE_SHIFT, > + low_max_pfn_mapped << PAGE_SHIFT, > + PAGE_SIZE * num , PAGE_SIZE); > + } else > + ret = memblock_find_in_range( > + local_min_pfn_mapped << PAGE_SHIFT, > + local_max_pfn_mapped << PAGE_SHIFT, > PAGE_SIZE * num , PAGE_SIZE); > if (!ret) > panic("alloc_low_page: can not alloc memory"); > @@ -402,60 +412,75 @@ static unsigned long __init get_new_step_size(unsigned long step_size) > return step_size; > } > > -void __init init_mem_mapping(void) > +void __init init_mem_mapping(unsigned long begin, unsigned long end) > { > - unsigned long end, real_end, start, last_start; > + unsigned long real_end, start, last_start; > unsigned long step_size; > unsigned long addr; > unsigned long mapped_ram_size = 0; > unsigned long new_mapped_ram_size; > + bool is_low = false; > + > + if (!begin) { > + probe_page_size_mask(); > + /* the ISA range is always mapped regardless of memory holes */ > + init_memory_mapping(0, ISA_END_ADDRESS); > + begin = ISA_END_ADDRESS; > + is_low = true; > + } > > - probe_page_size_mask(); > - > -#ifdef CONFIG_X86_64 > - end = max_pfn << PAGE_SHIFT; > -#else > - end = max_low_pfn << PAGE_SHIFT; > -#endif > - > - /* the ISA range is always mapped regardless of memory holes */ > - init_memory_mapping(0, ISA_END_ADDRESS); > + if (begin >= end) > + return; > > /* xen has big range in reserved near end of ram, skip it at first.*/ > - addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE); > + addr = memblock_find_in_range(begin, end, PMD_SIZE, PMD_SIZE); > real_end = addr + PMD_SIZE; > > /* step_size need to be small so pgt_buf from BRK could cover it */ > step_size = PMD_SIZE; > - max_pfn_mapped = 0; /* will get exact value next */ > - min_pfn_mapped = real_end >> PAGE_SHIFT; > + local_max_pfn_mapped = begin >> PAGE_SHIFT; > + local_min_pfn_mapped = real_end >> PAGE_SHIFT; > last_start = start = real_end; > - while (last_start > ISA_END_ADDRESS) { > + while (last_start > begin) { > if (last_start > step_size) { > start = round_down(last_start - 1, step_size); > - if (start < ISA_END_ADDRESS) > - start = ISA_END_ADDRESS; > + if (start < begin) > + start = begin; > } else > - start = ISA_END_ADDRESS; > + start = begin; > new_mapped_ram_size = init_range_memory_mapping(start, > last_start); > + if ((last_start >> PAGE_SHIFT) > local_max_pfn_mapped) > + local_max_pfn_mapped = last_start >> PAGE_SHIFT; > + local_min_pfn_mapped = start >> PAGE_SHIFT; > last_start = start; > - min_pfn_mapped = last_start >> PAGE_SHIFT; > /* only increase step_size after big range get mapped */ > if (new_mapped_ram_size > mapped_ram_size) > step_size = get_new_step_size(step_size); > mapped_ram_size += new_mapped_ram_size; > } > > - if (real_end < end) > + if (real_end < end) { > init_range_memory_mapping(real_end, end); > + if ((end >> PAGE_SHIFT) > local_max_pfn_mapped) > + local_max_pfn_mapped = end >> PAGE_SHIFT; > + } > > + if (is_low) { > + low_min_pfn_mapped = local_min_pfn_mapped; > + low_max_pfn_mapped = local_max_pfn_mapped; > + } > +} > + > +#ifndef CONFIG_NUMA > +void __init early_initmem_init(void) > +{ > #ifdef CONFIG_X86_64 > - if (max_pfn > max_low_pfn) { > - /* can we preseve max_low_pfn ?*/ > + init_mem_mapping(0, max_pfn << PAGE_SHIFT); > + if (max_pfn > max_low_pfn) > max_low_pfn = max_pfn; > - } > #else > + init_mem_mapping(0, max_low_pfn << PAGE_SHIFT); > early_ioremap_page_table_range_init(); > #endif > > @@ -464,11 +489,6 @@ void __init init_mem_mapping(void) > > early_memtest(0, max_pfn_mapped << PAGE_SHIFT); > } > - > -#ifndef CONFIG_NUMA > -void __init early_initmem_init(void) > -{ > -} > #endif > > /* > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c > index c2d4653..d3eb0c9 100644 > --- a/arch/x86/mm/numa.c > +++ b/arch/x86/mm/numa.c > @@ -17,8 +17,10 @@ > #include > #include > #include > +#include > > #include "numa_internal.h" > +#include "mm_internal.h" > > int __initdata numa_off; > nodemask_t numa_nodes_parsed __initdata; > @@ -668,9 +670,31 @@ static void __init early_x86_numa_init(void) > numa_init(dummy_numa_init); > } > > +#ifdef CONFIG_X86_64 > +static void __init early_x86_numa_init_mapping(void) > +{ > + init_mem_mapping(0, max_pfn << PAGE_SHIFT); > + if (max_pfn > max_low_pfn) > + max_low_pfn = max_pfn; > +} > +#else > +static void __init early_x86_numa_init_mapping(void) > +{ > + init_mem_mapping(0, max_low_pfn << PAGE_SHIFT); > + early_ioremap_page_table_range_init(); > +} > +#endif > + > void __init early_initmem_init(void) > { > early_x86_numa_init(); > + > + early_x86_numa_init_mapping(); > + > + load_cr3(swapper_pg_dir); > + __flush_tlb_all(); > + > + early_memtest(0, max_pfn_mapped< } > > void __init x86_numa_init(void) > -- > 1.8.1.4 > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/