linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Joerg Roedel <joro@8bytes.org>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@kernel.org>, "H . Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Juergen Gross <jgross@suse.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Borislav Petkov <bp@alien8.de>, Jiri Kosina <jkosina@suse.cz>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Brian Gerst <brgerst@gmail.com>,
	David Laight <David.Laight@aculab.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	Eduardo Valentin <eduval@amazon.com>,
	Greg KH <gregkh@linuxfoundation.org>,
	Will Deacon <will.deacon@arm.com>,
	aliguori@amazon.com, daniel.gruss@iaik.tugraz.at,
	hughd@google.com, keescook@google.com,
	Andrea Arcangeli <aarcange@redhat.com>,
	Waiman Long <llong@redhat.com>, Pavel Machek <pavel@ucw.cz>,
	"David H . Gutteridge" <dhgutteridge@sympatico.ca>,
	jroedel@suse.de, joro@8bytes.org
Subject: [PATCH 3/3] x86/mm/pti: Clone kernel-image on PTE level for 32 bit
Date: Tue,  7 Aug 2018 12:24:31 +0200	[thread overview]
Message-ID: <1533637471-30953-4-git-send-email-joro@8bytes.org> (raw)
In-Reply-To: <1533637471-30953-1-git-send-email-joro@8bytes.org>

From: Joerg Roedel <jroedel@suse.de>

On 32 bit the kernel sections are not huge-page aligned.
When we clone them on PMD-level we unevitably map some areas
that are normal kernel memory and may contain secrets to
user-space. To prevent that we need to clone the
kernel-image on PTE-level for 32 bit.

Also make the page-table cloning clode more general so that
it can handle PMD and PTE level cloning. This can be
generalized further in the future to also handle clones on
the P4D-level.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/mm/pti.c | 140 ++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 99 insertions(+), 41 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5164c98..1dc5c68 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -54,6 +54,16 @@
 #define __GFP_NOTRACK	0
 #endif
 
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
 static void __init pti_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
@@ -228,7 +238,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	return pmd_offset(pud, address);
 }
 
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /*
  * Walk the shadow copy of the page tables (optionally) trying to allocate
  * page table pages on the way down.  Does not support large pages.
@@ -270,6 +279,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	return pte;
 }
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 static void __init pti_setup_vsyscall(void)
 {
 	pte_t *pte, *target_pte;
@@ -290,8 +300,14 @@ static void __init pti_setup_vsyscall(void)
 static void __init pti_setup_vsyscall(void) { }
 #endif
 
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
 static void
-pti_clone_pmds(unsigned long start, unsigned long end)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level)
 {
 	unsigned long addr;
 
@@ -299,7 +315,8 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 	 * Clone the populated PMDs which cover start to end. These PMD areas
 	 * can have holes.
 	 */
-	for (addr = start; addr < end; addr += PMD_SIZE) {
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
 		pmd_t *pmd, *target_pmd;
 		pgd_t *pgd;
 		p4d_t *p4d;
@@ -315,44 +332,84 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 		p4d = p4d_offset(pgd, addr);
 		if (WARN_ON(p4d_none(*p4d)))
 			return;
+
 		pud = pud_offset(p4d, addr);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
 			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
 			continue;
+		}
 
-		target_pmd = pti_user_pagetable_walk_pmd(addr);
-		if (WARN_ON(!target_pmd))
-			return;
-
-		/*
-		 * Only clone present PMDs.  This ensures only setting
-		 * _PAGE_GLOBAL on present PMDs.  This should only be
-		 * called on well-known addresses anyway, so a non-
-		 * present PMD would be a surprise.
-		 */
-		if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
-			return;
-
-		/*
-		 * Setting 'target_pmd' below creates a mapping in both
-		 * the user and kernel page tables.  It is effectively
-		 * global, so set it as global in both copies.  Note:
-		 * the X86_FEATURE_PGE check is not _required_ because
-		 * the CPU ignores _PAGE_GLOBAL when PGE is not
-		 * supported.  The check keeps consistentency with
-		 * code that only set this bit when supported.
-		 */
-		if (boot_cpu_has(X86_FEATURE_PGE))
-			*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
-
-		/*
-		 * Copy the PMD.  That is, the kernelmode and usermode
-		 * tables will share the last-level page tables of this
-		 * address range
-		 */
-		*target_pmd = *pmd;
+		if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+			target_pmd = pti_user_pagetable_walk_pmd(addr);
+			if (WARN_ON(!target_pmd))
+				return;
+
+			/*
+			 * Only clone present PMDs.  This ensures only setting
+			 * _PAGE_GLOBAL on present PMDs.  This should only be
+			 * called on well-known addresses anyway, so a non-
+			 * present PMD would be a surprise.
+			 */
+			if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+				return;
+
+			/*
+			 * Setting 'target_pmd' below creates a mapping in both
+			 * the user and kernel page tables.  It is effectively
+			 * global, so set it as global in both copies.  Note:
+			 * the X86_FEATURE_PGE check is not _required_ because
+			 * the CPU ignores _PAGE_GLOBAL when PGE is not
+			 * supported.  The check keeps consistentency with
+			 * code that only set this bit when supported.
+			 */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+			/*
+			 * Copy the PMD.  That is, the kernelmode and usermode
+			 * tables will share the last-level page tables of this
+			 * address range
+			 */
+			*target_pmd = *pmd;
+
+			addr += PMD_SIZE;
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr += PAGE_SIZE;
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr += PAGE_SIZE;
+
+		} else {
+			BUG();
+		}
 	}
 }
 
@@ -398,7 +455,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pmds(start, end);
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -417,8 +474,9 @@ static void __init pti_setup_espfix64(void)
  */
 static void pti_clone_entry_text(void)
 {
-	pti_clone_pmds((unsigned long) __entry_text_start,
-		       (unsigned long) __irqentry_text_end);
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __irqentry_text_end,
+			  PTI_CLONE_PMD);
 }
 
 /*
@@ -500,10 +558,10 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end_clone);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
 
 	/*
-	 * pti_clone_pmds() will set the global bit in any PMDs
+	 * pti_clone_pgtable() will set the global bit in any PMDs
 	 * that it clones, but we also need to get any PTEs in
 	 * the last level for areas that are not huge-page-aligned.
 	 */
-- 
2.7.4

  parent reply	other threads:[~2018-08-07 10:24 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-07 10:24 [PATCH 0/3] PTI for x86-32 Fixes Joerg Roedel
2018-08-07 10:24 ` [PATCH 1/3] x86/mm/pti: Fix 32 bit PCID check Joerg Roedel
2018-08-07 10:24 ` [PATCH 2/3] x86/mm/pti: Don't clear permissions in pti_clone_pmd() Joerg Roedel
2018-08-07 18:34   ` Dave Hansen
2018-08-07 19:38     ` Andy Lutomirski
2018-08-07 20:21       ` Thomas Gleixner
2018-08-07 20:28         ` Andy Lutomirski
2018-08-07 10:24 ` Joerg Roedel [this message]
2018-08-17  2:44 ` [PATCH 0/3] PTI for x86-32 Fixes David H. Gutteridge

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1533637471-30953-4-git-send-email-joro@8bytes.org \
    --to=joro@8bytes.org \
    --cc=David.Laight@aculab.com \
    --cc=aarcange@redhat.com \
    --cc=aliguori@amazon.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=daniel.gruss@iaik.tugraz.at \
    --cc=dave.hansen@intel.com \
    --cc=dhgutteridge@sympatico.ca \
    --cc=dvlasenk@redhat.com \
    --cc=eduval@amazon.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jgross@suse.com \
    --cc=jkosina@suse.cz \
    --cc=jpoimboe@redhat.com \
    --cc=jroedel@suse.de \
    --cc=keescook@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=llong@redhat.com \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=pavel@ucw.cz \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).