[pve-kernel.git] / patches / kernel / 0192-x86-mm-pti-Add-mapping-helper-functions.patch

From 1cb923a3733ac738f0d96fe4738bdf159db86cfd Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Mon, 4 Dec 2017 15:07:37 +0100
Subject: [PATCH 192/241] x86/mm/pti: Add mapping helper functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

CVE-2017-5754

Add the pagetable helper functions do manage the separate user space page
tables.

[ tglx: Split out from the big combo kaiser patch. Folded Andys
        simplification and made it out of line as Boris suggested ]

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
(cherry picked from commit 61e9b3671007a5da8127955a1a3bda7e0d5f42e8)
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>
(cherry picked from commit fb45c59197f3134db6e223bb4fec0529774c07e1)
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
 arch/x86/include/asm/pgtable.h    |  6 ++-
 arch/x86/include/asm/pgtable_64.h | 92 +++++++++++++++++++++++++++++++++++++++
 arch/x86/mm/pti.c                 | 41 +++++++++++++++++
 3 files changed, 138 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index bb8e9ea7deb4..abbb47c75467 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -894,7 +894,11 @@ static inline int pgd_none(pgd_t pgd)
  * pgd_offset() returns a (pgd_t *)
  * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
  */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
 /*
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2160c1fee920..1ac15b03cf30 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -130,9 +130,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+       unsigned long __ptr = (unsigned long)ptr;
+
+       __ptr |= BIT(bit);
+       return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+       unsigned long __ptr = (unsigned long)ptr;
+
+       __ptr &= ~BIT(bit);
+       return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+       return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+       return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+       return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+       return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+       unsigned long ptr = (unsigned long)__ptr;
+
+       return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+       if (!static_cpu_has(X86_FEATURE_PTI))
+               return pgd;
+       return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+       return pgd;
+}
+#endif
+
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+       p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
        *p4dp = p4d;
+#endif
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -146,7 +234,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+       *pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
        *pgdp = pgd;
+#endif
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index a13f6b109865..69a983365392 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -96,6 +96,47 @@ void __init pti_check_boottime_disable(void)
        setup_force_cpu_cap(X86_FEATURE_PTI);
 }
 
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+       /*
+        * Changes to the high (kernel) portion of the kernelmode page
+        * tables are not automatically propagated to the usermode tables.
+        *
+        * Users should keep in mind that, unlike the kernelmode tables,
+        * there is no vmalloc_fault equivalent for the usermode tables.
+        * Top-level entries added to init_mm's usermode pgd after boot
+        * will not be automatically propagated to other mms.
+        */
+       if (!pgdp_maps_userspace(pgdp))
+               return pgd;
+
+       /*
+        * The user page tables get the full PGD, accessible from
+        * userspace:
+        */
+       kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+       /*
+        * If this is normal user memory, make it NX in the kernel
+        * pagetables so that, if we somehow screw up and return to
+        * usermode with the kernel CR3 loaded, we'll get a page fault
+        * instead of allowing user code to execute with the wrong CR3.
+        *
+        * As exceptions, we don't set NX if:
+        *  - _PAGE_USER is not set.  This could be an executable
+        *     EFI runtime mapping or something similar, and the kernel
+        *     may execute from it
+        *  - we don't have NX support
+        *  - we're clearing the PGD (i.e. the new pgd is not present).
+        */
+       if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+           (__supported_pte_mask & _PAGE_NX))
+               pgd.pgd |= _PAGE_NX;
+
+       /* return the copy of the PGD we want the kernel to use: */
+       return pgd;
+}
+
 /*
  * Initialize kernel page table isolation
  */
-- 
2.14.2