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:   Nadav Amit <namit@vmware.com>
To:     Ingo Molnar <mingo@redhat.com>
CC:     <linux-kernel@vger.kernel.org>, <x86@kernel.org>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>,
        Andy Lutomirski <luto@kernel.org>,
        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>,
        Nadav Amit <namit@vmware.com>,
        Kees Cook <keescook@chromium.org>,
        Dave Hansen <dave.hansen@intel.com>
Subject: [PATCH v7 05/14] x86/alternative: initializing temporary mm for patching
Date:   Tue, 4 Dec 2018 17:33:59 -0800
Message-ID: <20181205013408.47725-6-namit@vmware.com>
In-Reply-To: <20181205013408.47725-1-namit@vmware.com>
References: <20181205013408.47725-1-namit@vmware.com>
MIME-Version: 1.0
Content-Type: text/plain
Received-SPF: None (EX13-EDG-OU-001.vmware.com: namit@vmware.com does not
 designate permitted sender hosts)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

To prevent improper use of the PTEs that are used for text patching, we
want to use a temporary mm struct. We initailize it by copying the init
mm.

The address that will be used for patching is taken from the lower area
that is usually used for the task memory. Doing so prevents the need to
frequently synchronize the temporary-mm (e.g., when BPF programs are
installed), since different PGDs are used for the task memory.

Finally, we randomize the address of the PTEs to harden against exploits
that use these PTEs.

Cc: Kees Cook <keescook@chromium.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Tested-by: Masami Hiramatsu <mhiramat@kernel.org>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Nadav Amit <namit@vmware.com>
---
 arch/x86/include/asm/pgtable.h       |  3 +++
 arch/x86/include/asm/text-patching.h |  2 ++
 arch/x86/kernel/alternative.c        |  3 +++
 arch/x86/mm/init_64.c                | 35 ++++++++++++++++++++++++++++
 init/main.c                          |  3 +++
 5 files changed, 46 insertions(+)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 40616e805292..e8f630d9a2ed 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1021,6 +1021,9 @@ static inline void __meminit init_trampoline_default(void)
 	/* Default trampoline pgd value */
 	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
+
+void __init poking_init(void);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index f8fc8e86cf01..a75eed841eed 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -39,5 +39,7 @@ extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c6a3a10a2fd5..57fdde308bb6 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -678,6 +678,9 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	return addr;
 }
 
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
 static void *__text_poke(void *addr, const void *opcode, size_t len)
 {
 	unsigned long flags;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5fab264948c2..356a28569a19 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -53,6 +53,7 @@
 #include <asm/init.h>
 #include <asm/uv/uv.h>
 #include <asm/setup.h>
+#include <asm/text-patching.h>
 
 #include "mm_internal.h"
 
@@ -1388,6 +1389,40 @@ unsigned long memory_block_size_bytes(void)
 	return memory_block_size_probed;
 }
 
+/*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	poking_mm = copy_init_mm();
+	BUG_ON(!poking_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	poking_addr = TASK_UNMAPPED_BASE +
+		(kaslr_get_random_long("Poking") & PAGE_MASK) %
+		(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		poking_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
diff --git a/init/main.c b/init/main.c
index ee147103ba1b..a461150adfb1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -497,6 +497,8 @@ void __init __weak thread_stack_cache_init(void)
 
 void __init __weak mem_encrypt_init(void) { }
 
+void __init __weak poking_init(void) { }
+
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
@@ -731,6 +733,7 @@ asmlinkage __visible void __init start_kernel(void)
 	taskstats_init_early();
 	delayacct_init();
 
+	poking_init();
 	check_bugs();
 
 	acpi_subsystem_init();
-- 
2.17.1