Re: [GIT PULL] x86/mm changes for v3.2

From: hpanvin@xxxxxxxxx
Date: Wed Oct 26 2011 - 12:53:55 EST

Yes... I thought we had agreed that as ugly as the hook it is better than the fragility of second-guessing other code. I would like to see something automatically correct by construction, but that seems to be really difficult for reasons I don't remember, possibly having to do with bad Xen setup APIs.

Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx> wrote:

>On Wed, Oct 26, 2011 at 05:36:00PM +0200, Ingo Molnar wrote:
>> Linus,
>>
>> Please pull the latest x86-mm-for-linus git tree from:
>>
>> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git
>x86-mm-for-linus
>>
>Hey Ingo,
>
>When I spoke to hpa (LinuxCon in Canada) he mentioned that you guys
>decided
>against this patchset and just stick with the
>
>"x86,xen: introduce x86_init.mapping.pagetable_reserve"?
>
>Maybe I am misremembering the conversation - there was a fair amount of
>beer
>involved.
>
>> Thanks,
>>
>> Ingo
>>
>> ------------------>
>> Stefano Stabellini (5):
>> x86, mm: Calculate precisely the memory needed by
>init_memory_mapping
>> Revert "x86,xen: introduce x86_init.mapping.pagetable_reserve"
>> x86, init : Move memblock_x86_reserve_range PGTABLE to
>find_early_table_space
>> x86-64, mm: Do not assume head_64.S used 4KB pages when
>!use_pse
>> x86_32: Calculate additional memory needed by the fixmap
>>
>>
>> arch/x86/include/asm/pgtable_types.h | 1 -
>> arch/x86/include/asm/x86_init.h | 12 ---
>> arch/x86/kernel/x86_init.c | 4 -
>> arch/x86/mm/init.c | 147
>+++++++++++++++++++++++++---------
>> arch/x86/xen/mmu.c | 15 ----
>> 5 files changed, 109 insertions(+), 70 deletions(-)
>>
>> diff --git a/arch/x86/include/asm/pgtable_types.h
>b/arch/x86/include/asm/pgtable_types.h
>> index d56187c..7db7723 100644
>> --- a/arch/x86/include/asm/pgtable_types.h
>> +++ b/arch/x86/include/asm/pgtable_types.h
>> @@ -299,7 +299,6 @@ int phys_mem_access_prot_allowed(struct file
>*file, unsigned long pfn,
>> /* Install a pte for a particular vaddr in kernel space. */
>> void set_pte_vaddr(unsigned long vaddr, pte_t pte);
>>
>> -extern void native_pagetable_reserve(u64 start, u64 end);
>> #ifdef CONFIG_X86_32
>> extern void native_pagetable_setup_start(pgd_t *base);
>> extern void native_pagetable_setup_done(pgd_t *base);
>> diff --git a/arch/x86/include/asm/x86_init.h
>b/arch/x86/include/asm/x86_init.h
>> index d3d8590..643ebf2 100644
>> --- a/arch/x86/include/asm/x86_init.h
>> +++ b/arch/x86/include/asm/x86_init.h
>> @@ -68,17 +68,6 @@ struct x86_init_oem {
>> };
>>
>> /**
>> - * struct x86_init_mapping - platform specific initial kernel
>pagetable setup
>> - * @pagetable_reserve: reserve a range of addresses for kernel
>pagetable usage
>> - *
>> - * For more details on the purpose of this hook, look in
>> - * init_memory_mapping and the commit that added it.
>> - */
>> -struct x86_init_mapping {
>> - void (*pagetable_reserve)(u64 start, u64 end);
>> -};
>> -
>> -/**
>> * struct x86_init_paging - platform specific paging functions
>> * @pagetable_setup_start: platform specific pre paging_init() call
>> * @pagetable_setup_done: platform specific post paging_init() call
>> @@ -134,7 +123,6 @@ struct x86_init_ops {
>> struct x86_init_mpparse mpparse;
>> struct x86_init_irqs irqs;
>> struct x86_init_oem oem;
>> - struct x86_init_mapping mapping;
>> struct x86_init_paging paging;
>> struct x86_init_timers timers;
>> struct x86_init_iommu iommu;
>> diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
>> index 6f164bd..6eee082 100644
>> --- a/arch/x86/kernel/x86_init.c
>> +++ b/arch/x86/kernel/x86_init.c
>> @@ -61,10 +61,6 @@ struct x86_init_ops x86_init __initdata = {
>> .banner = default_banner,
>> },
>>
>> - .mapping = {
>> - .pagetable_reserve = native_pagetable_reserve,
>> - },
>> -
>> .paging = {
>> .pagetable_setup_start = native_pagetable_setup_start,
>> .pagetable_setup_done = native_pagetable_setup_done,
>> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
>> index 3032644..a90ccc4 100644
>> --- a/arch/x86/mm/init.c
>> +++ b/arch/x86/mm/init.c
>> @@ -28,22 +28,110 @@ int direct_gbpages
>> #endif
>> ;
>>
>> -static void __init find_early_table_space(unsigned long end, int
>use_pse,
>> - int use_gbpages)
>> +static unsigned long __init find_early_fixmap_space(void)
>> {
>> - unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
>> + unsigned long size = 0;
>> +#ifdef CONFIG_X86_32
>> + int kmap_begin_pmd_idx, kmap_end_pmd_idx;
>> + int fixmap_begin_pmd_idx, fixmap_end_pmd_idx;
>> + int btmap_begin_pmd_idx;
>> +
>> + fixmap_begin_pmd_idx =
>> + __fix_to_virt(__end_of_fixed_addresses - 1) >> PMD_SHIFT;
>> + /*
>> + * fixmap_end_pmd_idx is the end of the fixmap minus the PMD that
>> + * has been defined in the data section by head_32.S (see
>> + * initial_pg_fixmap).
>> + * Note: This is similar to what
>early_ioremap_page_table_range_init
>> + * does except that the "end" has PMD_SIZE expunged as per previous
>> + * comment.
>> + */
>> + fixmap_end_pmd_idx = (FIXADDR_TOP - 1) >> PMD_SHIFT;
>> + btmap_begin_pmd_idx = __fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT;
>> + kmap_begin_pmd_idx = __fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
>> + kmap_end_pmd_idx = __fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
>> +
>> + size = fixmap_end_pmd_idx - fixmap_begin_pmd_idx;
>> + /*
>> + * early_ioremap_init has already allocated a PMD at
>> + * btmap_begin_pmd_idx
>> + */
>> + if (btmap_begin_pmd_idx < fixmap_end_pmd_idx)
>> + size--;
>> +
>> +#ifdef CONFIG_HIGHMEM
>> + /*
>> + * see page_table_kmap_check: if the kmap spans multiple PMDs, make
>> + * sure the pte pages are allocated contiguously. It might need up
>> + * to two additional pte pages to replace the page declared by
>> + * head_32.S and the one allocated by early_ioremap_init, if they
>> + * are even partially used for the kmap.
>> + */
>> + if (kmap_begin_pmd_idx != kmap_end_pmd_idx) {
>> + if (kmap_end_pmd_idx == fixmap_end_pmd_idx)
>> + size++;
>> + if (btmap_begin_pmd_idx >= kmap_begin_pmd_idx &&
>> + btmap_begin_pmd_idx <= kmap_end_pmd_idx)
>> + size++;
>> + }
>> +#endif
>> +#endif
>> + return (size * PMD_SIZE + PAGE_SIZE - 1) >> PAGE_SHIFT;
>> +}
>> +
>> +static void __init find_early_table_space(unsigned long start,
>> + unsigned long end, int use_pse, int use_gbpages)
>> +{
>> + unsigned long pmds = 0, ptes = 0, tables = 0, good_end = end,
>> + pud_mapped = 0, pmd_mapped = 0, size = end - start;
>> phys_addr_t base;
>>
>> - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
>> - tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
>> + pud_mapped = DIV_ROUND_UP(PFN_PHYS(max_pfn_mapped),
>> + (PUD_SIZE * PTRS_PER_PUD));
>> + pud_mapped *= (PUD_SIZE * PTRS_PER_PUD);
>> + pmd_mapped = DIV_ROUND_UP(PFN_PHYS(max_pfn_mapped),
>> + (PMD_SIZE * PTRS_PER_PMD));
>> + pmd_mapped *= (PMD_SIZE * PTRS_PER_PMD);
>> +
>> + /*
>> + * On x86_64 do not limit the size we need to cover with 4KB pages
>> + * depending on the initial allocation because head_64.S always
>uses
>> + * 2MB pages.
>> + */
>> +#ifdef CONFIG_X86_32
>> + if (start < PFN_PHYS(max_pfn_mapped)) {
>> + if (PFN_PHYS(max_pfn_mapped) < end)
>> + size -= PFN_PHYS(max_pfn_mapped) - start;
>> + else
>> + size = 0;
>> + }
>> +#endif
>> +
>> +#ifndef __PAGETABLE_PUD_FOLDED
>> + if (end > pud_mapped) {
>> + unsigned long puds;
>> + if (start < pud_mapped)
>> + puds = (end - pud_mapped + PUD_SIZE - 1) >> PUD_SHIFT;
>> + else
>> + puds = (end - start + PUD_SIZE - 1) >> PUD_SHIFT;
>> + tables += roundup(puds * sizeof(pud_t), PAGE_SIZE);
>> + }
>> +#endif
>>
>> if (use_gbpages) {
>> unsigned long extra;
>>
>> extra = end - ((end>>PUD_SHIFT) << PUD_SHIFT);
>> pmds = (extra + PMD_SIZE - 1) >> PMD_SHIFT;
>> - } else
>> - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
>> + }
>> +#ifndef __PAGETABLE_PMD_FOLDED
>> + else if (end > pmd_mapped) {
>> + if (start < pmd_mapped)
>> + pmds = (end - pmd_mapped + PMD_SIZE - 1) >> PMD_SHIFT;
>> + else
>> + pmds = (end - start + PMD_SIZE - 1) >> PMD_SHIFT;
>> + }
>> +#endif
>>
>> tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
>>
>> @@ -51,23 +139,22 @@ static void __init
>find_early_table_space(unsigned long end, int use_pse,
>> unsigned long extra;
>>
>> extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
>> -#ifdef CONFIG_X86_32
>> - extra += PMD_SIZE;
>> -#endif
>> ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
>> } else
>> - ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
>> + ptes = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
>> +
>> + ptes += find_early_fixmap_space();
>>
>> tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
>>
>> -#ifdef CONFIG_X86_32
>> - /* for fixmap */
>> - tables += roundup(__end_of_fixed_addresses * sizeof(pte_t),
>PAGE_SIZE);
>> + if (!tables)
>> + return;
>>
>> +#ifdef CONFIG_X86_32
>> good_end = max_pfn_mapped << PAGE_SHIFT;
>> #endif
>>
>> - base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
>> + base = memblock_find_in_range(0x00, good_end, tables, PAGE_SIZE);
>> if (base == MEMBLOCK_ERROR)
>> panic("Cannot find space for the kernel page tables");
>>
>> @@ -77,11 +164,10 @@ static void __init
>find_early_table_space(unsigned long end, int use_pse,
>>
>> printk(KERN_DEBUG "kernel direct mapping tables up to %lx @
>%lx-%lx\n",
>> end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
>> -}
>>
>> -void __init native_pagetable_reserve(u64 start, u64 end)
>> -{
>> - memblock_x86_reserve_range(start, end, "PGTABLE");
>> + if (pgt_buf_top > pgt_buf_start)
>> + memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
>> + pgt_buf_top << PAGE_SHIFT, "PGTABLE");
>> }
>>
>> struct map_range {
>> @@ -261,7 +347,7 @@ unsigned long __init_refok
>init_memory_mapping(unsigned long start,
>> * nodes are discovered.
>> */
>> if (!after_bootmem)
>> - find_early_table_space(end, use_pse, use_gbpages);
>> + find_early_table_space(start, end, use_pse, use_gbpages);
>>
>> for (i = 0; i < nr_range; i++)
>> ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
>> @@ -275,24 +361,9 @@ unsigned long __init_refok
>init_memory_mapping(unsigned long start,
>>
>> __flush_tlb_all();
>>
>> - /*
>> - * Reserve the kernel pagetable pages we used (pgt_buf_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
>> - * but that haven't been used.
>> - *
>> - * In fact on xen we mark RO the whole range pgt_buf_start -
>> - * pgt_buf_top, because we have to make sure that when
>> - * init_memory_mapping reaches the pagetable pages area, it maps
>> - * RO all the pagetable pages, including the ones that are beyond
>> - * pgt_buf_end at that time.
>> - */
>> - if (!after_bootmem && pgt_buf_end > pgt_buf_start)
>> - x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
>> - PFN_PHYS(pgt_buf_end));
>> + if (pgt_buf_end != pgt_buf_top)
>> + printk(KERN_DEBUG "initial kernel pagetable allocation wasted %lx"
>> + " pages\n", pgt_buf_top - pgt_buf_end);
>>
>> if (!after_bootmem)
>> early_memtest(start, end);
>> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
>> index dc708dc..2004f1e 100644
>> --- a/arch/x86/xen/mmu.c
>> +++ b/arch/x86/xen/mmu.c
>> @@ -1153,20 +1153,6 @@ static void __init
>xen_pagetable_setup_start(pgd_t *base)
>> {
>> }
>>
>> -static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
>> -{
>> - /* reserve the range used */
>> - native_pagetable_reserve(start, end);
>> -
>> - /* set as RW the rest */
>> - printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
>> - PFN_PHYS(pgt_buf_top));
>> - while (end < PFN_PHYS(pgt_buf_top)) {
>> - make_lowmem_page_readwrite(__va(end));
>> - end += PAGE_SIZE;
>> - }
>> -}
>> -
>> static void xen_post_allocator_init(void);
>>
>> static void __init xen_pagetable_setup_done(pgd_t *base)
>> @@ -1997,7 +1983,6 @@ static const struct pv_mmu_ops xen_mmu_ops
>__initconst = {
>>
>> void __init xen_init_mmu_ops(void)
>> {
>> - x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
>> x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
>> x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
>> pv_mmu_ops = xen_mmu_ops;
>> --
>> To unsubscribe from this list: send the line "unsubscribe
>linux-kernel" in
>> the body of a message to majordomo@xxxxxxxxxxxxxxx
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>> Please read the FAQ at http://www.tux.org/lkml/

--
Sent from my Android phone with K-9 Mail. Please excuse my brevity.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/