From: Dmitry Safonov <dsafonov@virtuozzo.com>
To: <linux-kernel@vger.kernel.org>
CC: <0x7f454c46@gmail.com>, Dmitry Safonov <dsafonov@virtuozzo.com>,
        "Thomas Gleixner" <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, Andy Lutomirski <luto@kernel.org>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        <x86@kernel.org>
Subject: [RFC 3/4] x86/mm: define TASK_SIZE as current->mm->task_size
Date: Fri, 30 Dec 2016 18:56:33 +0300
Message-ID: <20161230155634.8692-4-dsafonov@virtuozzo.com>
In-Reply-To: <20161230155634.8692-1-dsafonov@virtuozzo.com>
References: <20161230155634.8692-1-dsafonov@virtuozzo.com>
MIME-Version: 1.0
Content-Type: text/plain
SpamDiagnosticOutput: 1:99
SpamDiagnosticMetadata: NSPM
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 30 Dec 2016 16:00:16.6935 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-Transport-CrossTenantHeadersStamped: HE1PR0801MB1740
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 5161
Lines: 141

Keep task's virtual address space size as mm_struct field which
exists for a long time - it's initialized in setup_new_exec()
depending on the new task's personality.
This way TASK_SIZE will always be the same as current->mm->task_size.
Previously, there could be an issue about different values of
TASK_SIZE and current->mm->task_size: e.g, a 32-bit process can unset
ADDR_LIMIT_3GB personality (with personality syscall) and
so TASK_SIZE will be 4Gb, which is larger than mm->task_size = 3Gb.
As TASK_SIZE *and* current->mm->task_size are used both in code
frequently, this difference creates a subtle situations, for example:
one can mmap addresses > 3Gb, but they will be hidden in
/proc/pid/pagemap as it checks mm->task_size.
I've moved initialization of mm->task_size earlier in setup_new_exec()
as arch_pick_mmap_layout() initializes mmap_legacy_base with
TASK_UNMAPPED_BASE, which depends on TASK_SIZE.

Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
---
 arch/x86/include/asm/processor.h | 17 +++++++++--------
 arch/x86/um/asm/segment.h        |  2 +-
 arch/x86/xen/mmu.c               |  4 ++--
 fs/exec.c                        | 17 +++++++++++------
 4 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dbc7dec5fa84..47ebde614f06 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -768,10 +768,8 @@ static inline void spin_lock_prefetch(const void *x)
 /*
  * User space process size: 3GB (default).
  */
-#define TASK_SIZE		PAGE_OFFSET
-#define TASK_SIZE_MAX		TASK_SIZE
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		STACK_TOP
+#define TASK_SIZE_MAX		PAGE_OFFSET
+#define INIT_TASK_SIZE		TASK_SIZE_MAX
 
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
@@ -817,12 +815,9 @@ static inline void spin_lock_prefetch(const void *x)
 #define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
 					0xc0000000 : 0xFFFFe000)
 
-#define TASK_SIZE		(current->personality & ADDR_LIMIT_32BIT ? \
+#define INIT_TASK_SIZE		(current->personality & ADDR_LIMIT_32BIT ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		TASK_SIZE_MAX
-
 #define INIT_THREAD  {						\
 	.sp0			= TOP_OF_INIT_STACK,		\
 	.addr_limit		= KERNEL_DS,			\
@@ -833,6 +828,12 @@ extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */
 
+#define TASK_SIZE							\
+		((current->mm) ? current->mm->task_size : TASK_SIZE_MAX)
+
+#define STACK_TOP		TASK_SIZE
+#define STACK_TOP_MAX		TASK_SIZE_MAX
+
 extern unsigned long thread_saved_pc(struct task_struct *tsk);
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
diff --git a/arch/x86/um/asm/segment.h b/arch/x86/um/asm/segment.h
index 41dd5e1f3cd7..3a9aa9f050df 100644
--- a/arch/x86/um/asm/segment.h
+++ b/arch/x86/um/asm/segment.h
@@ -13,6 +13,6 @@ typedef struct {
 
 #define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
 #define KERNEL_DS	MAKE_MM_SEG(~0UL)
-#define USER_DS		MAKE_MM_SEG(TASK_SIZE)
+#define USER_DS		MAKE_MM_SEG(TASK_SIZE_MAX)
 
 #endif
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 7d5afdb417cc..264ca3b7be58 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -830,7 +830,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 #else /* CONFIG_X86_32 */
 #ifdef CONFIG_X86_PAE
 	/* Need to make sure unshared kernel PMD is pinnable */
-	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
+	xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE_MAX)]),
 		     PT_PMD);
 #endif
 	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
@@ -949,7 +949,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
 	/* Need to make sure unshared kernel PMD is unpinned */
-	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
+	xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE_MAX)]),
 		       PT_PMD);
 #endif
 
diff --git a/fs/exec.c b/fs/exec.c
index e57946610733..826b73600fc2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1303,8 +1303,19 @@ void would_dump(struct linux_binprm *bprm, struct file *file)
 }
 EXPORT_SYMBOL(would_dump);
 
+#ifndef INIT_TASK_SIZE
+#define INIT_TASK_SIZE TASK_SIZE
+#endif
+
 void setup_new_exec(struct linux_binprm * bprm)
 {
+
+	/* Set the new mm task size. We have to do that late because it may
+	 * depend on TIF_32BIT which is only updated in flush_thread() on
+	 * some architectures like powerpc
+	 */
+	current->mm->task_size = INIT_TASK_SIZE;
+
 	arch_pick_mmap_layout(current->mm);
 
 	/* This is the point of no return */
@@ -1318,12 +1329,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	perf_event_exec();
 	__set_task_comm(current, kbasename(bprm->filename), true);
 
-	/* Set the new mm task size. We have to do that late because it may
-	 * depend on TIF_32BIT which is only updated in flush_thread() on
-	 * some architectures like powerpc
-	 */
-	current->mm->task_size = TASK_SIZE;
-
 	/* install the new credentials */
 	if (!uid_eq(bprm->cred->uid, current_euid()) ||
 	    !gid_eq(bprm->cred->gid, current_egid())) {
-- 
2.11.0