Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Rick Edgecombe <rick.p.edgecombe@intel.com>
To:     Andy Lutomirski <luto@kernel.org>, Ingo Molnar <mingo@redhat.com>
Cc:     linux-kernel@vger.kernel.org, x86@kernel.org, hpa@zytor.com,
        Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>,
        Nadav Amit <nadav.amit@gmail.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>, linux_dti@icloud.com,
        linux-integrity@vger.kernel.org,
        linux-security-module@vger.kernel.org, akpm@linux-foundation.org,
        kernel-hardening@lists.openwall.com, linux-mm@kvack.org,
        will.deacon@arm.com, ard.biesheuvel@linaro.org,
        kristen@linux.intel.com, deneen.t.dock@intel.com,
        Nadav Amit <namit@vmware.com>,
        Kees Cook <keescook@chromium.org>,
        Dave Hansen <dave.hansen@intel.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>
Subject: [PATCH v2 06/20] x86/alternative: use temporary mm for text poking
Date:   Mon, 28 Jan 2019 16:34:08 -0800
Message-Id: <20190129003422.9328-7-rick.p.edgecombe@intel.com>
In-Reply-To: <20190129003422.9328-1-rick.p.edgecombe@intel.com>
References: <20190129003422.9328-1-rick.p.edgecombe@intel.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Nadav Amit <namit@vmware.com>

text_poke() can potentially compromise the security as it sets temporary
PTEs in the fixmap. These PTEs might be used to rewrite the kernel code
from other cores accidentally or maliciously, if an attacker gains the
ability to write onto kernel memory.

Moreover, since remote TLBs are not flushed after the temporary PTEs are
removed, the time-window in which the code is writable is not limited if
the fixmap PTEs - maliciously or accidentally - are cached in the TLB.
To address these potential security hazards, we use a temporary mm for
patching the code.

Finally, text_poke() is also not conservative enough when mapping pages,
as it always tries to map 2 pages, even when a single one is sufficient.
So try to be more conservative, and do not map more than needed.

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
---
 arch/x86/include/asm/fixmap.h |   2 -
 arch/x86/kernel/alternative.c | 106 +++++++++++++++++++++++++++-------
 arch/x86/xen/mmu_pv.c         |   2 -
 3 files changed, 84 insertions(+), 26 deletions(-)

diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 50ba74a34a37..9da8cccdf3fb 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -103,8 +103,6 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
-	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
-	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ae05fbb50171..76d482a2b716 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
 #include <linux/stop_machine.h>
 #include <linux/slab.h>
 #include <linux/kdebug.h>
+#include <linux/mmu_context.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -683,41 +684,102 @@ __ro_after_init unsigned long poking_addr;
 
 static void *__text_poke(void *addr, const void *opcode, size_t len)
 {
+	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
+	temporary_mm_state_t prev;
+	struct page *pages[2] = {NULL};
 	unsigned long flags;
-	char *vaddr;
-	struct page *pages[2];
-	int i;
+	pte_t pte, *ptep;
+	spinlock_t *ptl;
+	pgprot_t prot;
 
 	/*
-	 * While boot memory allocator is runnig we cannot use struct
-	 * pages as they are not yet initialized.
+	 * While boot memory allocator is running we cannot use struct pages as
+	 * they are not yet initialized.
 	 */
 	BUG_ON(!after_bootmem);
 
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
-		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
+		if (cross_page_boundary)
+			pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
 	} else {
 		pages[0] = virt_to_page(addr);
 		WARN_ON(!PageReserved(pages[0]));
-		pages[1] = virt_to_page(addr + PAGE_SIZE);
+		if (cross_page_boundary)
+			pages[1] = virt_to_page(addr + PAGE_SIZE);
 	}
-	BUG_ON(!pages[0]);
+	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
+
 	local_irq_save(flags);
-	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
-	if (pages[1])
-		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
-	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
-	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	clear_fixmap(FIX_TEXT_POKE0);
-	if (pages[1])
-		clear_fixmap(FIX_TEXT_POKE1);
-	local_flush_tlb();
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
-	for (i = 0; i < len; i++)
-		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
+
+	/*
+	 * The lock is not really needed, but this allows to avoid open-coding.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+
+	/*
+	 * This must not fail; preallocated in poking_init().
+	 */
+	VM_BUG_ON(!ptep);
+
+	/*
+	 * flush_tlb_mm_range() would be called when the poking_mm is not
+	 * loaded. When PCID is in use, the flush would be deferred to the time
+	 * the poking_mm is loaded again. Set the PTE as non-global to prevent
+	 * it from being used when we are done.
+	 */
+	prot = __pgprot(pgprot_val(PAGE_KERNEL) & ~_PAGE_GLOBAL);
+
+	pte = mk_pte(pages[0], prot);
+	set_pte_at(poking_mm, poking_addr, ptep, pte);
+
+	if (cross_page_boundary) {
+		pte = mk_pte(pages[1], prot);
+		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+	}
+
+	/*
+	 * Loading the temporary mm behaves as a compiler barrier, which
+	 * guarantees that the PTE will be set at the time memcpy() is done.
+	 */
+	prev = use_temporary_mm(poking_mm);
+
+	kasan_disable_current();
+	memcpy((u8 *)poking_addr + offset_in_page(addr), opcode, len);
+	kasan_enable_current();
+
+	/*
+	 * Ensure that the PTE is only cleared after the instructions of memcpy
+	 * were issued by using a compiler barrier.
+	 */
+	barrier();
+
+	pte_clear(poking_mm, poking_addr, ptep);
+	if (cross_page_boundary)
+		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+
+	/*
+	 * Loading the previous page-table hierarchy requires a serializing
+	 * instruction that already allows the core to see the updated version.
+	 * Xen-PV is assumed to serialize execution in a similar manner.
+	 */
+	unuse_temporary_mm(prev);
+
+	/*
+	 * Flushing the TLB might involve IPIs, which would require enabled
+	 * IRQs, but not if the mm is not used, as it is in this point.
+	 */
+	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
+			   PAGE_SHIFT, false);
+
+	pte_unmap_unlock(ptep, ptl);
+	/*
+	 * If the text doesn't match what we just wrote; something is
+	 * fundamentally screwy, there's nothing we can really do about that.
+	 */
+	BUG_ON(memcmp(addr, opcode, len));
+
 	local_irq_restore(flags);
 	return addr;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 0f4fe206dcc2..82b181fcefe5 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2319,8 +2319,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
-	case FIX_TEXT_POKE0:
-	case FIX_TEXT_POKE1:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
-- 
2.17.1