Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752437AbbEGRmm (ORCPT ); Thu, 7 May 2015 13:42:42 -0400 Received: from mga11.intel.com ([192.55.52.93]:61918 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752184AbbEGRlb (ORCPT ); Thu, 7 May 2015 13:41:31 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.13,384,1427785200"; d="scan'208";a="490684818" Subject: [PATCH 08/12] x86, pkeys: arch-specific protection bits To: dave@sr71.net Cc: linux-kernel@vger.kernel.org, x86@kernel.org From: Dave Hansen Date: Thu, 07 May 2015 10:41:35 -0700 References: <20150507174132.34AF8FAF@viggo.jf.intel.com> In-Reply-To: <20150507174132.34AF8FAF@viggo.jf.intel.com> Message-Id: <20150507174135.81194600@viggo.jf.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4580 Lines: 116 Lots of things seem to do: vma->vm_page_prot = vm_get_page_prot(flags); and the ptes get created right from things we pull out of ->vm_page_prot. So it is very convenient if we can store the protection key in flags and vm_page_prot, just like the existing permission bits (_PAGE_RW/PRESENT). It greatly reduces the amount of plumbing and arch-specific hacking we have to do in generic code. This also takes the new PROT_PKEY{0,1,2,3} flags and turns *those* in to VM_ flags for vma->vm_flags. The protection key values are stored in 4 places: 1. "prot" argument to system calls 2. vma->vm_flags, filled from the mmap "prot" 3. vma->vm_page prot, filled from vma->vm_flags 4. the PTE itself. The pseudocode for these for steps are as follows: mmap(PROT_PKEY*) vma->vm_flags = ... | arch_calc_vm_prot_bits(mmap_prot); vma->vm_page_prot = ... | arch_vm_get_page_prot(vma->vm_flags); pte = pfn | vma->vm_page_prot Note that these are new definitions for x86: arch_vm_get_page_prot() arch_calc_vm_prot_bits() --- b/arch/x86/include/asm/pgtable_types.h | 12 ++++++++++-- b/arch/x86/include/uapi/asm/mman.h | 17 +++++++++++++++++ b/include/linux/mm.h | 4 ++++ 3 files changed, 31 insertions(+), 2 deletions(-) diff -puN arch/x86/include/asm/pgtable_types.h~pkeys-7-store-pkey-in-vma arch/x86/include/asm/pgtable_types.h --- a/arch/x86/include/asm/pgtable_types.h~pkeys-7-store-pkey-in-vma 2015-05-07 10:31:43.740293543 -0700 +++ b/arch/x86/include/asm/pgtable_types.h 2015-05-07 10:31:43.747293858 -0700 @@ -104,7 +104,12 @@ #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ _PAGE_DIRTY) -/* Set of bits not changed in pte_modify */ +/* + * Set of bits not changed in pte_modify. The pte's + * protection key is treated like _PAGE_RW, for + * instance, and is *not* included in this mask since + * pte_modify() does modify it. + */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ _PAGE_SOFT_DIRTY) @@ -220,7 +225,10 @@ enum page_cache_mode { /* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ #define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) -/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */ +/* + * PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t + * This includes the protection key value. + */ #define PTE_FLAGS_MASK (~PTE_PFN_MASK) typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; diff -puN arch/x86/include/uapi/asm/mman.h~pkeys-7-store-pkey-in-vma arch/x86/include/uapi/asm/mman.h --- a/arch/x86/include/uapi/asm/mman.h~pkeys-7-store-pkey-in-vma 2015-05-07 10:31:43.742293633 -0700 +++ b/arch/x86/include/uapi/asm/mman.h 2015-05-07 10:31:43.747293858 -0700 @@ -6,6 +6,23 @@ #define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) #define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) +/* + * Take the 4 protection key bits out of the vma->vm_flags + * value and turn them in to the bits that we can put in + * to a pte. + */ +#define arch_vm_get_page_prot(vm_flags) __pgprot( \ + ((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) | \ + ((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) | \ + ((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) | \ + ((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0)) + +#define arch_calc_vm_prot_bits(prot) ( \ + ((prot) & PROT_PKEY0 ? VM_PKEY_BIT0 : 0) | \ + ((prot) & PROT_PKEY1 ? VM_PKEY_BIT1 : 0) | \ + ((prot) & PROT_PKEY2 ? VM_PKEY_BIT2 : 0) | \ + ((prot) & PROT_PKEY3 ? VM_PKEY_BIT3 : 0)) + #include #endif /* _ASM_X86_MMAN_H */ diff -puN include/linux/mm.h~pkeys-7-store-pkey-in-vma include/linux/mm.h --- a/include/linux/mm.h~pkeys-7-store-pkey-in-vma 2015-05-07 10:31:43.744293723 -0700 +++ b/include/linux/mm.h 2015-05-07 10:31:43.748293904 -0700 @@ -162,6 +162,10 @@ extern unsigned int kobjsize(const void #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ +# define VM_PKEY_BIT0 VM_HIGH_ARCH_1 /* A protection key is a 4-bit value */ +# define VM_PKEY_BIT1 VM_HIGH_ARCH_2 +# define VM_PKEY_BIT2 VM_HIGH_ARCH_3 +# define VM_PKEY_BIT3 VM_HIGH_ARCH_4 #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) _ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/