Re: [PATCH v3 4/4] pagemap: switch to the new format and do some cleanup

From: Mark Williamson
Date: Fri Jun 12 2015 - 14:49:56 EST

Next message: Takashi Iwai: "Re: [PATCH v3] ALSA: aoa: convert bus code to use dev_groups"
Previous message: Avi Kivity: "Re: [v4 08/16] KVM: kvm-vfio: User API for IRQ forwarding"
In reply to: Konstantin Khlebnikov: "[PATCH v3 4/4] pagemap: switch to the new format and do some cleanup"
Next in thread: Konstantin Khlebnikov: "[PATCH v4] pagemap: switch to the new format and do some cleanup"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

One tiny nitpick / typo, inline below - functionally, this looks good
from our side...

Reviewed-by: mwilliamson@xxxxxxxxxxxxxxxxx
Tested-by: mwilliamson@xxxxxxxxxxxxxxxxx

On Tue, Jun 9, 2015 at 9:00 PM, Konstantin Khlebnikov <koct9i@xxxxxxxxx> wrote:
> From: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>

<...snip...>

> -#define __PM_SOFT_DIRTY (1LL)
> -#define __PM_MMAP_EXCLUSIVE (2LL)
> -#define PM_PRESENT PM_STATUS(4LL)
> -#define PM_SWAP PM_STATUS(2LL)
> -#define PM_FILE PM_STATUS(1LL)
> -#define PM_NOT_PRESENT(v2) PM_STATUS2(v2, 0)
> +#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
> +#define PM_PFEAME_BITS 54
> +#define PM_PFRAME_MASK GENMASK_ULL(PM_PFEAME_BITS - 1, 0)

s/PM_FEAME_BITS/PM_FRAME_BITS/ I presume?

> +#define PM_SOFT_DIRTY BIT_ULL(55)
> +#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
> +#define PM_FILE BIT_ULL(61)
> +#define PM_SWAP BIT_ULL(62)
> +#define PM_PRESENT BIT_ULL(63)
> +
> #define PM_END_OF_BUFFER 1
>
> -static inline pagemap_entry_t make_pme(u64 val)
> +static inline pagemap_entry_t make_pme(u64 frame, u64 flags)
> {
> - return (pagemap_entry_t) { .pme = val };
> + return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags };
> }
>
> static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
> @@ -1013,7 +977,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
>
> while (addr < end) {
> struct vm_area_struct *vma = find_vma(walk->mm, addr);
> - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
> + pagemap_entry_t pme = make_pme(0, 0);
> /* End of address space hole, which we mark as non-present. */
> unsigned long hole_end;
>
> @@ -1033,7 +997,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
>
> /* Addresses in the VMA. */
> if (vma->vm_flags & VM_SOFTDIRTY)
> - pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
> + pme = make_pme(0, PM_SOFT_DIRTY);
> for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
> err = add_to_pagemap(addr, &pme, pm);
> if (err)
> @@ -1044,50 +1008,44 @@ out:
> return err;
> }
>
> -static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
> +static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
> struct vm_area_struct *vma, unsigned long addr, pte_t pte)
> {
> - u64 frame = 0, flags;
> + u64 frame = 0, flags = 0;
> struct page *page = NULL;
> - int flags2 = 0;
>
> if (pte_present(pte)) {
> if (pm->show_pfn)
> frame = pte_pfn(pte);
> - flags = PM_PRESENT;
> + flags |= PM_PRESENT;
> page = vm_normal_page(vma, addr, pte);
> if (pte_soft_dirty(pte))
> - flags2 |= __PM_SOFT_DIRTY;
> + flags |= PM_SOFT_DIRTY;
> } else if (is_swap_pte(pte)) {
> swp_entry_t entry;
> if (pte_swp_soft_dirty(pte))
> - flags2 |= __PM_SOFT_DIRTY;
> + flags |= PM_SOFT_DIRTY;
> entry = pte_to_swp_entry(pte);
> frame = swp_type(entry) |
> (swp_offset(entry) << MAX_SWAPFILES_SHIFT);
> - flags = PM_SWAP;
> + flags |= PM_SWAP;
> if (is_migration_entry(entry))
> page = migration_entry_to_page(entry);
> - } else {
> - if (vma->vm_flags & VM_SOFTDIRTY)
> - flags2 |= __PM_SOFT_DIRTY;
> - *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
> - return;
> }
>
> if (page && !PageAnon(page))
> flags |= PM_FILE;
> if (page && page_mapcount(page) == 1)
> - flags2 |= __PM_MMAP_EXCLUSIVE;
> - if ((vma->vm_flags & VM_SOFTDIRTY))
> - flags2 |= __PM_SOFT_DIRTY;
> + flags |= PM_MMAP_EXCLUSIVE;
> + if (vma->vm_flags & VM_SOFTDIRTY)
> + flags |= PM_SOFT_DIRTY;
>
> - *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
> + return make_pme(frame, flags);
> }
>
> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> -static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
> - pmd_t pmd, int offset, int pmd_flags2)
> +static pagemap_entry_t thp_pmd_to_pagemap_entry(struct pagemapread *pm,
> + pmd_t pmd, int offset, u64 flags)
> {
> u64 frame = 0;
>
> @@ -1099,15 +1057,16 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p
> if (pmd_present(pmd)) {
> if (pm->show_pfn)
> frame = pmd_pfn(pmd) + offset;
> - *pme = make_pme(PM_PFRAME(frame) | PM_PRESENT |
> - PM_STATUS2(pm->v2, pmd_flags2));
> - } else
> - *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
> + flags |= PM_PRESENT;
> + }
> +
> + return make_pme(frame, flags);
> }
> #else
> -static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
> - pmd_t pmd, int offset, int pmd_flags2)
> +static pagemap_entry_t thp_pmd_to_pagemap_entry(struct pagemapread *pm,
> + pmd_t pmd, int offset, u64 flags)
> {
> + return make_pme(0, 0);
> }
> #endif
>
> @@ -1121,18 +1080,16 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> int err = 0;
>
> if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
> - int pmd_flags2;
> + u64 flags = 0;
>
> if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
> - pmd_flags2 = __PM_SOFT_DIRTY;
> - else
> - pmd_flags2 = 0;
> + flags |= PM_SOFT_DIRTY;
>
> if (pmd_present(*pmd)) {
> struct page *page = pmd_page(*pmd);
>
> if (page_mapcount(page) == 1)
> - pmd_flags2 |= __PM_MMAP_EXCLUSIVE;
> + flags |= PM_MMAP_EXCLUSIVE;
> }
>
> for (; addr != end; addr += PAGE_SIZE) {
> @@ -1141,7 +1098,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
>
> offset = (addr & ~PAGEMAP_WALK_MASK) >>
> PAGE_SHIFT;
> - thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
> + pme = thp_pmd_to_pagemap_entry(pm, *pmd, offset, flags);
> err = add_to_pagemap(addr, &pme, pm);
> if (err)
> break;
> @@ -1161,7 +1118,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> for (; addr < end; pte++, addr += PAGE_SIZE) {
> pagemap_entry_t pme;
>
> - pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
> + pme = pte_to_pagemap_entry(pm, vma, addr, *pte);
> err = add_to_pagemap(addr, &pme, pm);
> if (err)
> break;
> @@ -1174,19 +1131,18 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> }
>
> #ifdef CONFIG_HUGETLB_PAGE
> -static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
> - pte_t pte, int offset, int flags2)
> +static pagemap_entry_t huge_pte_to_pagemap_entry(struct pagemapread *pm,
> + pte_t pte, int offset, u64 flags)
> {
> u64 frame = 0;
>
> if (pte_present(pte)) {
> if (pm->show_pfn)
> frame = pte_pfn(pte) + offset;
> - *pme = make_pme(PM_PFRAME(frame) | PM_PRESENT |
> - PM_STATUS2(pm->v2, flags2));
> - } else
> - *pme = make_pme(PM_NOT_PRESENT(pm->v2) |
> - PM_STATUS2(pm->v2, flags2));
> + flags |= PM_PRESENT;
> + }
> +
> + return make_pme(frame, flags);
> }
>
> /* This function walks within one hugetlb entry in the single call */
> @@ -1197,17 +1153,15 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
> struct pagemapread *pm = walk->private;
> struct vm_area_struct *vma = walk->vma;
> int err = 0;
> - int flags2;
> + u64 flags = 0;
> pagemap_entry_t pme;
>
> if (vma->vm_flags & VM_SOFTDIRTY)
> - flags2 = __PM_SOFT_DIRTY;
> - else
> - flags2 = 0;
> + flags |= PM_SOFT_DIRTY;
>
> for (; addr != end; addr += PAGE_SIZE) {
> int offset = (addr & ~hmask) >> PAGE_SHIFT;
> - huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
> + pme = huge_pte_to_pagemap_entry(pm, *pte, offset, flags);
> err = add_to_pagemap(addr, &pme, pm);
> if (err)
> return err;
> @@ -1228,7 +1182,9 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
> * Bits 0-54 page frame number (PFN) if present
> * Bits 0-4 swap type if swapped
> * Bits 5-54 swap offset if swapped
> - * Bits 55-60 page shift (page size = 1<<page shift)
> + * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
> + * Bit 56 page exclusively mapped
> + * Bits 57-60 zero
> * Bit 61 page is file-page or shared-anon
> * Bit 62 page swapped
> * Bit 63 page present
> @@ -1269,7 +1225,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
>
> /* do not disclose physical addresses: attack vector */
> pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN);
> - pm.v2 = soft_dirty_cleared;
> pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
> pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
> ret = -ENOMEM;
> @@ -1339,10 +1294,6 @@ static int pagemap_open(struct inode *inode, struct file *file)
> {
> struct mm_struct *mm;
>
> - pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
> - "to stop being page-shift some time soon. See the "
> - "linux/Documentation/vm/pagemap.txt for details.\n");
> -
> mm = proc_mem_open(inode, PTRACE_MODE_READ);
> if (IS_ERR(mm))
> return PTR_ERR(mm);
> diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
> index 3a9f193..1fa872e 100644
> --- a/tools/vm/page-types.c
> +++ b/tools/vm/page-types.c
> @@ -57,26 +57,15 @@
> * pagemap kernel ABI bits
> */
>
> -#define PM_ENTRY_BYTES sizeof(uint64_t)
> -#define PM_STATUS_BITS 3
> -#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
> -#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
> -#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
> -#define PM_PSHIFT_BITS 6
> -#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
> -#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
> -#define __PM_PSHIFT(x) (((uint64_t) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
> -#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1)
> -#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
> -
> -#define __PM_SOFT_DIRTY (1LL)
> -#define __PM_MMAP_EXCLUSIVE (2LL)
> -#define PM_PRESENT PM_STATUS(4LL)
> -#define PM_SWAP PM_STATUS(2LL)
> -#define PM_FILE PM_STATUS(1LL)
> -#define PM_SOFT_DIRTY __PM_PSHIFT(__PM_SOFT_DIRTY)
> -#define PM_MMAP_EXCLUSIVE __PM_PSHIFT(__PM_MMAP_EXCLUSIVE)
> -
> +#define PM_ENTRY_BYTES 8
> +#define PM_PFEAME_BITS 54
> +#define PM_PFRAME_MASK ((1LL << PM_PFEAME_BITS) - 1)
> +#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
> +#define PM_SOFT_DIRTY (1ULL << 55)
> +#define PM_MMAP_EXCLUSIVE (1ULL << 56)
> +#define PM_FILE (1ULL << 61)
> +#define PM_SWAP (1ULL << 62)
> +#define PM_PRESENT (1ULL << 63)
>
> /*
> * kernel page flags
>
--
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/

Next message: Takashi Iwai: "Re: [PATCH v3] ALSA: aoa: convert bus code to use dev_groups"
Previous message: Avi Kivity: "Re: [v4 08/16] KVM: kvm-vfio: User API for IRQ forwarding"
In reply to: Konstantin Khlebnikov: "[PATCH v3 4/4] pagemap: switch to the new format and do some cleanup"
Next in thread: Konstantin Khlebnikov: "[PATCH v4] pagemap: switch to the new format and do some cleanup"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]