[RFC PATCH 1/7] mm: Add write-protect and clean utilities for address space ranges

[Thomas Hellström (VMware)]

On 9/13/19 11:32 AM, Thomas Hellström (VMware) wrote:
> From: Thomas Hellstrom <thellstrom at vmware.com>
>
> Add two utilities to a) write-protect and b) clean all ptes pointing into
> a range of an address space.
> The utilities are intended to aid in tracking dirty pages (either
> driver-allocated system memory or pci device memory).
> The write-protect utility should be used in conjunction with
> page_mkwrite() and pfn_mkwrite() to trigger write page-faults on page
> accesses. Typically one would want to use this on sparse accesses into
> large memory regions. The clean utility should be used to utilize
> hardware dirtying functionality and avoid the overhead of page-faults,
> typically on large accesses into small memory regions.
>
> The added file "as_dirty_helpers.c" is initially listed as maintained by
> VMware under our DRM driver. If somebody would like it elsewhere,
> that's of course no problem.
>
> Cc: Andrew Morton <akpm at linux-foundation.org>
> Cc: Matthew Wilcox <willy at infradead.org>
> Cc: Will Deacon <will.deacon at arm.com>
> Cc: Peter Zijlstra <peterz at infradead.org>
> Cc: Rik van Riel <riel at surriel.com>
> Cc: Minchan Kim <minchan at kernel.org>
> Cc: Michal Hocko <mhocko at suse.com>
> Cc: Huang Ying <ying.huang at intel.com>
> Cc: Souptick Joarder <jrdr.linux at gmail.com>
> Cc: "Jérôme Glisse" <jglisse at redhat.com>
> Cc: linux-mm at kvack.org
> Cc: linux-kernel at vger.kernel.org
>
> Signed-off-by: Thomas Hellstrom <thellstrom at vmware.com>
> Reviewed-by: Ralph Campbell <rcampbell at nvidia.com> #v1
> ---
>   MAINTAINERS           |   1 +
>   include/linux/mm.h    |  13 +-
>   mm/Kconfig            |   3 +
>   mm/Makefile           |   1 +
>   mm/as_dirty_helpers.c | 392 ++++++++++++++++++++++++++++++++++++++++++
>   5 files changed, 409 insertions(+), 1 deletion(-)
>   create mode 100644 mm/as_dirty_helpers.c
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index c2d975da561f..b596c7cf4a85 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -5287,6 +5287,7 @@ T:	git git://people.freedesktop.org/~thomash/linux
>   S:	Supported
>   F:	drivers/gpu/drm/vmwgfx/
>   F:	include/uapi/drm/vmwgfx_drm.h
> +F:	mm/as_dirty_helpers.c
>   
>   DRM DRIVERS
>   M:	David Airlie <airlied at linux.ie>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 0334ca97c584..27ff341ecbdc 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2657,7 +2657,6 @@ typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
>   extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
>   			       unsigned long size, pte_fn_t fn, void *data);
>   
> -
>   #ifdef CONFIG_PAGE_POISONING
>   extern bool page_poisoning_enabled(void);
>   extern void kernel_poison_pages(struct page *page, int numpages, int enable);
> @@ -2891,5 +2890,17 @@ void __init setup_nr_node_ids(void);
>   static inline void setup_nr_node_ids(void) {}
>   #endif
>   
> +#ifdef CONFIG_AS_DIRTY_HELPERS
> +unsigned long apply_as_clean(struct address_space *mapping,
> +			     pgoff_t first_index, pgoff_t nr,
> +			     pgoff_t bitmap_pgoff,
> +			     unsigned long *bitmap,
> +			     pgoff_t *start,
> +			     pgoff_t *end);
> +
> +unsigned long apply_as_wrprotect(struct address_space *mapping,
> +				 pgoff_t first_index, pgoff_t nr);
> +#endif
> +
>   #endif /* __KERNEL__ */
>   #endif /* _LINUX_MM_H */
> diff --git a/mm/Kconfig b/mm/Kconfig
> index 56cec636a1fc..594350e9d78e 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -736,4 +736,7 @@ config ARCH_HAS_PTE_SPECIAL
>   config ARCH_HAS_HUGEPD
>   	bool
>   
> +config AS_DIRTY_HELPERS
> +        bool
> +
>   endmenu
> diff --git a/mm/Makefile b/mm/Makefile
> index d0b295c3b764..4086f1eefbc6 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -105,3 +105,4 @@ obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
>   obj-$(CONFIG_ZONE_DEVICE) += memremap.o
>   obj-$(CONFIG_HMM_MIRROR) += hmm.o
>   obj-$(CONFIG_MEMFD_CREATE) += memfd.o
> +obj-$(CONFIG_AS_DIRTY_HELPERS) += as_dirty_helpers.o
> diff --git a/mm/as_dirty_helpers.c b/mm/as_dirty_helpers.c
> new file mode 100644
> index 000000000000..3be06fe8f1d2
> --- /dev/null
> +++ b/mm/as_dirty_helpers.c
> @@ -0,0 +1,392 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <linux/mm.h>
> +#include <linux/mm_types.h>
> +#include <linux/hugetlb.h>
> +#include <linux/bitops.h>
> +#include <linux/mmu_notifier.h>
> +#include <asm/cacheflush.h>
> +#include <asm/tlbflush.h>
> +
> +/**
> + * struct as_walk - Argument to as_pte_fn_t

Argument to struct as_walk_ops callbacks

> + * @vma: Pointer to the struct vmw_area_struct currently being walked.
> + *
> + * Embeddable argument to struct as__pte_fn_t

Here as well.


> + */
> +struct as_walk {
> +	struct vm_area_struct *vma;
> +};
> +
> +/**
> + * struct as_walk_ops - Callbacks for entries of various page table levels.
> + * extend for additional level support.
> + */
> +struct as_walk_ops {
> +	/**
> +	 * pte-entry: Callback for PTEs
> +	 * @pte: Pointer to the PTE.
> +	 * @addr: Virtual address.
> +	 * @asw: Struct as_walk argument for the walk. Embed for additional
> +	 * data.
> +	 */
> +	void (*const pte_entry) (pte_t *pte, unsigned long addr,
> +				 struct as_walk *asw);
> +};