search for: pmd

pmd_present() is expected to test positive after pmdp_mknotpresent() as the PMD entry still points to a valid huge page in memory. pmdp_mknotpresent() implies that given PMD entry is just invalidated from MMU perspective while still holding on to pmd_page() referred valid huge page thus also clearing p...

This series renames pmd_mknotpresent() as pmd_mkinvalid(). Before that it drops an existing pmd_mknotpresent() definition from powerpc platform which was never required as it defines it's pmdp_invalidate() through subscribing __HAVE_ARCH_PMDP_INVALIDATE. This does not create any functional change. This rename was sug...

This series renames pmd_mknotpresent() as pmd_mknotvalid(). Before that it drops an existing pmd_mknotpresent() definition from powerpc platform which was never required as it defines it's pmdp_invalidate() through subscribing __HAVE_ARCH_PMDP_INVALIDATE. This does not create any functional change. This rename was su...

On 2 Sep 2020, at 12:58, Ralph Campbell wrote: > A migrating transparent huge page has to already be unmapped. Otherwise, > the page could be modified while it is being copied to a new page and > data could be lost. The function __split_huge_pmd() checks for a PMD > migration entry before calling __split_huge_pmd_locked() leading one to > think that __split_huge_pmd_locked() can handle splitting a migrating PMD. > However, the code always increments the page->_mapcount and adjusts the > memory control group accounting assumi...

A migrating transparent huge page has to already be unmapped. Otherwise, the page could be modified while it is being copied to a new page and data could be lost. The function __split_huge_pmd() checks for a PMD migration entry before calling __split_huge_pmd_locked() leading one to think that __split_huge_pmd_locked() can handle splitting a migrating PMD. However, the code always increments the page->_mapcount and adjusts the memory control group accounting assuming the page is mappe...

A migrating transparent huge page has to already be unmapped. Otherwise, the page could be modified while it is being copied to a new page and data could be lost. The function __split_huge_pmd() checks for a PMD migration entry before calling __split_huge_pmd_locked() leading one to think that __split_huge_pmd_locked() can handle splitting a migrating PMD. However, the code always increments the page->_mapcount and adjusts the memory control group accounting assuming the page is mappe...

....flush_tlb_single = native_flush_tlb_single, + .alloc_pt = (void *)native_nop, + .alloc_pd = (void *)native_nop, + .alloc_pd_clone = (void *)native_nop, + .release_pt = (void *)native_nop, + .release_pd = (void *)native_nop, + .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, .set_pmd = native_set_pmd, =================================================================== --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -62,6 +62,7 @@ static pmd_t * __init one_md_table_init( #ifdef CONFIG_X86_PAE pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); + paravirt_allo...

....flush_tlb_single = native_flush_tlb_single, + .alloc_pt = (void *)native_nop, + .alloc_pd = (void *)native_nop, + .alloc_pd_clone = (void *)native_nop, + .release_pt = (void *)native_nop, + .release_pd = (void *)native_nop, + .set_pte = native_set_pte, .set_pte_at = native_set_pte_at, .set_pmd = native_set_pmd, =================================================================== --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -62,6 +62,7 @@ static pmd_t * __init one_md_table_init( #ifdef CONFIG_X86_PAE pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); + paravirt_allo...

...86/mm/init.c =================================================================== --- linux-2.6.13.orig/arch/i386/mm/init.c 2005-08-24 09:31:05.000000000 -0700 +++ linux-2.6.13/arch/i386/mm/init.c 2005-08-24 09:31:31.000000000 -0700 @@ -79,6 +79,7 @@ static pte_t * __init one_page_table_ini { if (pmd_none(*pmd)) { pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); + SetPagePTE(virt_to_page(page_table)); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); if (page_table != pte_offset_kernel(pmd, 0)) BUG(); Index: linux-2.6.13/arch/i386/mm/pageattr.c ===============...

...86/mm/init.c =================================================================== --- linux-2.6.13.orig/arch/i386/mm/init.c 2005-08-24 09:31:05.000000000 -0700 +++ linux-2.6.13/arch/i386/mm/init.c 2005-08-24 09:31:31.000000000 -0700 @@ -79,6 +79,7 @@ static pte_t * __init one_page_table_ini { if (pmd_none(*pmd)) { pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); + SetPagePTE(virt_to_page(page_table)); set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); if (page_table != pte_offset_kernel(pmd, 0)) BUG(); Index: linux-2.6.13/arch/i386/mm/pageattr.c ===============...

I''m sure everyone has seen the drop of VMI patches for Linux at this point, but just in case, the link is included below. I''ve read this version of the VMI spec and have made my way through most of the patches. While I wasn''t really that impressed with the first spec wrt Xen, the second version seems to be much more palatable. Specifically, the code inlining and

...while it is protected under the pgd lock to correctly copy the shadow. We don't need to allocate pgds in PAE mode, (PDPs in Intel terminology) as they only have 4 entries, and are cached entirely by the processor, which makes shadowing them rather simple. For base page table level allocation, pmd_populate provides the exact hook point we need. Also, we need to allocate pages when splitting a large page, and we must release pages before returning the page to any free pool. Despite being required with these slightly odd semantics for VMI, Xen also uses these hooks to determine the exact mo...

...while it is protected under the pgd lock to correctly copy the shadow. We don't need to allocate pgds in PAE mode, (PDPs in Intel terminology) as they only have 4 entries, and are cached entirely by the processor, which makes shadowing them rather simple. For base page table level allocation, pmd_populate provides the exact hook point we need. Also, we need to allocate pages when splitting a large page, and we must release pages before returning the page to any free pool. Despite being required with these slightly odd semantics for VMI, Xen also uses these hooks to determine the exact mo...

Can someone explain why this: find . -depth -print0 | cpio --null -pmd /tmp/test will copy all files in and below the current directory -and- this: find . -depth -print | grep -v .iso$ | wc -l will count all the non-iso files -and- this: find . -depth -print | grep .iso$ | wc -l will count *only* the iso files -but- this: find . -depth -print0 | grep -v .iso$ |...

On Fri, Mar 20, 2020 at 10:24:17AM +0530, Anshuman Khandual wrote: > pmd_present() is expected to test positive after pmdp_mknotpresent() as the > PMD entry still points to a valid huge page in memory. pmdp_mknotpresent() > implies that given PMD entry is just invalidated from MMU perspective while > still holding on to pmd_page() referred valid huge page thus...

...> > > than order 0 (PAGE_SIZE), there is no indication that the page is mapped > > > using a larger page size. To be fully general, hmm_range_fault() would need > > > to return the mapping size to handle cases like a 1GB compound page being > > > mapped with 2MB PMD entries. However, the most common case is the mapping > > > size is the same as the underlying compound page size. > > > Add a new output flag to indicate this so that callers know it is safe to > > > use a large device page table mapping if one is available. > > &...

...nd_order(page) but if the page is larger > than order 0 (PAGE_SIZE), there is no indication that the page is mapped > using a larger page size. To be fully general, hmm_range_fault() would need > to return the mapping size to handle cases like a 1GB compound page being > mapped with 2MB PMD entries. However, the most common case is the mapping > size is the same as the underlying compound page size. > Add a new output flag to indicate this so that callers know it is safe to > use a large device page table mapping if one is available. But what size should the caller use? You...

...+void prep_compound_page(struct page *page, unsigned int order); > > #ifdef CONFIG_MMU > /* > diff --git a/mm/huge_memory.c b/mm/huge_memory.c > index 78c84bee7e29..25d95f7b1e98 100644 > --- a/mm/huge_memory.c > +++ b/mm/huge_memory.c > @@ -1663,23 +1663,35 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, > } else { > struct page *page = NULL; > int flush_needed = 1; > + bool is_anon = false; > > if (pmd_present(orig_pmd)) { > page = pmd_page(orig_pmd); > + is_anon = PageAnon(page); > page_remove_rma...

...<asm/trap_defs.h> +#include <asm/cmpxchg.h> /* Use the static base for this part of the boot process */ #undef __PAGE_OFFSET #define __PAGE_OFFSET __PAGE_OFFSET_BASE @@ -157,6 +158,139 @@ void initialize_identity_maps(void) write_cr3(top_level_pgt); } +static pte_t *split_large_pmd(struct x86_mapping_info *info, + pmd_t *pmdp, unsigned long __address) +{ + unsigned long page_flags; + unsigned long address; + pte_t *pte; + pmd_t pmd; + int i; + + pte = (pte_t *)info->alloc_pgt_page(info->context); + if (!pte) + return NULL; + + address = __address & PMD_...

...e.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> + +#include <asm/hv_vm.h> + +static DEFINE_MUTEX(hvvm_lock); + +static DECLARE_BITMAP(hvvm_avail_pages, NR_HV_PAGES); + + +static void hvvm_pte_unmap(pmd_t *pmd, unsigned long addr) +{ + pte_t *pte; + pte_t ptent; + + pte = pte_offset_kernel(pmd, addr); + ptent = ptep_get_and_clear(&init_mm, addr, pte); + WARN_ON(!pte_none(ptent) && !pte_present(ptent)); +} + +static inline void hvvm_pmd_unmap(pud_t *pud, unsigned long addr) +{ + pmd_t *...