[patch V149 27/50] x86/mm/pti: Add functions to clone kernel PMDs

From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, Linus Torvalds <torvalds@linux-foundation.org>,
	Andy Lutomirsky <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Borislav Petkov <bpetkov@suse.de>,
	Greg KH <gregkh@linuxfoundation.org>,
	keescook@google.com, hughd@google.com,
	Brian Gerst <brgerst@gmail.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Denys Vlasenko <dvlasenk@redhat.com>,
	Rik van Riel <riel@redhat.com>,
	Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Juergen Gross <jgross@suse.com>,
	David Laight <David.Laight@aculab.com>,
	Eduardo Valentin <eduval@amazon.com>,
	aliguori@amazon.com, Will Deacon <will.deacon@arm.com>,
	daniel.gruss@iaik.tugraz.at, Ingo Molnar <mingo@kernel.org>,
	Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>
Subject: [patch V149 27/50] x86/mm/pti: Add functions to clone kernel PMDs
Date: Sat, 16 Dec 2017 22:24:21 +0100	[thread overview]
Message-ID: <20171216213138.640571556@linutronix.de> (raw)
In-Reply-To: 20171216212354.120930222@linutronix.de

[-- Attachment #1: 0036-x86-mm-pti-Add-functions-to-clone-kernel-PMDs.patch --]
[-- Type: text/plain, Size: 4990 bytes --]

From: Andy Lutomirski <luto@kernel.org>

Provide infrastructure to:

 - find a kernel PMD for a mapping which must be visible to user space for
   the entry/exit code to work.

 - walk an address range and share the kernel PMD with it.

This reuses a small part of the original KAISER patches to populate the
user space page table.

[ tglx: Made it universally usable so it can be used for any kind of shared
	mapping. Add a mechanism to clear specific bits in the user space
	visible PMD entry. Folded Andys simplifactions ]

Originally-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.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
---
 arch/x86/mm/pti.c |  127 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 127 insertions(+)

--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -48,6 +48,11 @@
 #undef pr_fmt
 #define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
 
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK	0
+#endif
+
 void __init pti_check_boottime_disable(void)
 {
 	bool enable = true;
@@ -65,6 +70,128 @@ void __init pti_check_boottime_disable(v
 }
 
 /*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+	pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+	if (address < PAGE_OFFSET) {
+		WARN_ONCE(1, "attempt to walk user address\n");
+		return NULL;
+	}
+
+	if (pgd_none(*pgd)) {
+		unsigned long new_p4d_page = __get_free_page(gfp);
+		if (!new_p4d_page)
+			return NULL;
+
+		if (pgd_none(*pgd)) {
+			set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+			new_p4d_page = 0;
+		}
+		if (new_p4d_page)
+			free_page(new_p4d_page);
+	}
+	BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+	return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+	pud_t *pud;
+
+	BUILD_BUG_ON(p4d_large(*p4d) != 0);
+	if (p4d_none(*p4d)) {
+		unsigned long new_pud_page = __get_free_page(gfp);
+		if (!new_pud_page)
+			return NULL;
+
+		if (p4d_none(*p4d)) {
+			set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+			new_pud_page = 0;
+		}
+		if (new_pud_page)
+			free_page(new_pud_page);
+	}
+
+	pud = pud_offset(p4d, address);
+	/* The user page tables do not use large mappings: */
+	if (pud_large(*pud)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pud_none(*pud)) {
+		unsigned long new_pmd_page = __get_free_page(gfp);
+		if (!new_pmd_page)
+			return NULL;
+
+		if (pud_none(*pud)) {
+			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+			new_pmd_page = 0;
+		}
+		if (new_pmd_page)
+			free_page(new_pmd_page);
+	}
+
+	return pmd_offset(pud, address);
+}
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+	unsigned long addr;
+
+	/*
+	 * Clone the populated PMDs which cover start to end. These PMD areas
+	 * can have holes.
+	 */
+	for (addr = start; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd, *target_pmd;
+		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
+
+		pgd = pgd_offset_k(addr);
+		if (WARN_ON(pgd_none(*pgd)))
+			return;
+		p4d = p4d_offset(pgd, addr);
+		if (WARN_ON(p4d_none(*p4d)))
+			return;
+		pud = pud_offset(p4d, addr);
+		if (pud_none(*pud))
+			continue;
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd))
+			continue;
+
+		target_pmd = pti_user_pagetable_walk_pmd(addr);
+		if (WARN_ON(!target_pmd))
+			return;
+
+		/*
+		 * Copy the PMD.  That is, the kernelmode and usermode
+		 * tables will share the last-level page tables of this
+		 * address range
+		 */
+		*target_pmd = pmd_clear_flags(*pmd, clear);
+	}
+}
+
+/*
  * Initialize kernel page table isolation
  */
 void __init pti_init(void)
