Re: [PATCH RFC] mm: add MAP_EXCLUSIVE to create exclusive user mappings

[David Hildenbrand <david@redhat.com>]

On 27.10.19 11:17, Mike Rapoport wrote:
> From: Mike Rapoport <rppt@linux.ibm.com>
> 
> The mappings created with MAP_EXCLUSIVE are visible only in the context of
> the owning process and can be used by applications to store secret
> information that will not be visible not only to other processes but to the
> kernel as well.
> 
> The pages in these mappings are removed from the kernel direct map and
> marked with PG_user_exclusive flag. When the exclusive area is unmapped,
> the pages are mapped back into the direct map.
> 
> The MAP_EXCLUSIVE flag implies MAP_POPULATE and MAP_LOCKED.
> 
> Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
> ---
>   arch/x86/mm/fault.c                    | 14 ++++++++++
>   fs/proc/task_mmu.c                     |  1 +
>   include/linux/mm.h                     |  9 +++++++
>   include/linux/page-flags.h             |  7 +++++
>   include/linux/page_excl.h              | 49 ++++++++++++++++++++++++++++++++++
>   include/trace/events/mmflags.h         |  9 ++++++-
>   include/uapi/asm-generic/mman-common.h |  1 +
>   kernel/fork.c                          |  3 ++-
>   mm/Kconfig                             |  3 +++
>   mm/gup.c                               |  8 ++++++
>   mm/memory.c                            |  3 +++
>   mm/mmap.c                              | 16 +++++++++++
>   mm/page_alloc.c                        |  5 ++++
>   13 files changed, 126 insertions(+), 2 deletions(-)
>   create mode 100644 include/linux/page_excl.h
> 
> diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
> index 9ceacd1..8f73a75 100644
> --- a/arch/x86/mm/fault.c
> +++ b/arch/x86/mm/fault.c
> @@ -17,6 +17,7 @@
>   #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
>   #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
>   #include <linux/efi.h>			/* efi_recover_from_page_fault()*/
> +#include <linux/page_excl.h>		/* page_is_user_exclusive()	*/
>   #include <linux/mm_types.h>
>   
>   #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
> @@ -1218,6 +1219,13 @@ static int fault_in_kernel_space(unsigned long address)
>   	return address >= TASK_SIZE_MAX;
>   }
>   
> +static bool fault_in_user_exclusive_page(unsigned long address)
> +{
> +	struct page *page = virt_to_page(address);
> +
> +	return page_is_user_exclusive(page);
> +}
> +
>   /*
>    * Called for all faults where 'address' is part of the kernel address
>    * space.  Might get called for faults that originate from *code* that
> @@ -1261,6 +1269,12 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
>   	if (spurious_kernel_fault(hw_error_code, address))
>   		return;
>   
> +	/* FIXME: warn and handle gracefully */
> +	if (unlikely(fault_in_user_exclusive_page(address))) {
> +		pr_err("page fault in user exclusive page at %lx", address);
> +		force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)address);
> +	}
> +
>   	/* kprobes don't want to hook the spurious faults: */
>   	if (kprobe_page_fault(regs, X86_TRAP_PF))
>   		return;
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 9442631..99e14d1 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -655,6 +655,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
>   #ifdef CONFIG_X86_INTEL_MPX
>   		[ilog2(VM_MPX)]		= "mp",
>   #endif
> +		[ilog2(VM_EXCLUSIVE)]	= "xl",
>   		[ilog2(VM_LOCKED)]	= "lo",
>   		[ilog2(VM_IO)]		= "io",
>   		[ilog2(VM_SEQ_READ)]	= "sr",
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index cc29227..9c43375 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -298,11 +298,13 @@ extern unsigned int kobjsize(const void *objp);
>   #define VM_HIGH_ARCH_BIT_2	34	/* bit only usable on 64-bit architectures */
>   #define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
>   #define VM_HIGH_ARCH_BIT_4	36	/* bit only usable on 64-bit architectures */
> +#define VM_HIGH_ARCH_BIT_5	37	/* bit only usable on 64-bit architectures */
>   #define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
>   #define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
>   #define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
>   #define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
>   #define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
> +#define VM_HIGH_ARCH_5	BIT(VM_HIGH_ARCH_BIT_5)
>   #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
>   
>   #ifdef CONFIG_ARCH_HAS_PKEYS
> @@ -340,6 +342,12 @@ extern unsigned int kobjsize(const void *objp);
>   # define VM_MPX		VM_NONE
>   #endif
>   
> +#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
> +# define VM_EXCLUSIVE	VM_HIGH_ARCH_5
> +#else
> +# define VM_EXCLUSIVE	VM_NONE
> +#endif
> +
>   #ifndef VM_GROWSUP
>   # define VM_GROWSUP	VM_NONE
>   #endif
> @@ -2594,6 +2602,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
>   #define FOLL_ANON	0x8000	/* don't do file mappings */
>   #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
>   #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
> +#define FOLL_EXCLUSIVE	0x40000	/* mapping is exclusive to owning mm */
>   
>   /*
>    * NOTE on FOLL_LONGTERM:
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index f91cb88..32d0aee 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -131,6 +131,9 @@ enum pageflags {
>   	PG_young,
>   	PG_idle,
>   #endif
> +#if defined(CONFIG_EXCLUSIVE_USER_PAGES)
> +	PG_user_exclusive,
> +#endif

Last time I tried to introduce a new page flag I learned that this is 
very much frowned upon. Best you can usually do is reuse another flag - 
if valid in that context.

-- 

Thanks,

David / dhildenb