---

yaml
---
r: 311576
b: refs/heads/master
c: 3492ee7
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 18068bdd5f59229623b2fa518a6389e346642b0d
+refs/heads/master: 3492ee727439efcd050985c314a85646b7a2bda2

trunk/Documentation/prctl/no_new_privs.txt

@@ -0,0 +1,50 @@
+The execve system call can grant a newly-started program privileges that
+its parent did not have.  The most obvious examples are setuid/setgid
+programs and file capabilities.  To prevent the parent program from
+gaining these privileges as well, the kernel and user code must be
+careful to prevent the parent from doing anything that could subvert the
+child.  For example:
+
+ - The dynamic loader handles LD_* environment variables differently if
+   a program is setuid.
+
+ - chroot is disallowed to unprivileged processes, since it would allow
+   /etc/passwd to be replaced from the point of view of a process that
+   inherited chroot.
+
+ - The exec code has special handling for ptrace.
+
+These are all ad-hoc fixes.  The no_new_privs bit (since Linux 3.5) is a
+new, generic mechanism to make it safe for a process to modify its
+execution environment in a manner that persists across execve.  Any task
+can set no_new_privs.  Once the bit is set, it is inherited across fork,
+clone, and execve and cannot be unset.  With no_new_privs set, execve
+promises not to grant the privilege to do anything that could not have
+been done without the execve call.  For example, the setuid and setgid
+bits will no longer change the uid or gid; file capabilities will not
+add to the permitted set, and LSMs will not relax constraints after
+execve.
+
+Note that no_new_privs does not prevent privilege changes that do not
+involve execve.  An appropriately privileged task can still call
+setuid(2) and receive SCM_RIGHTS datagrams.
+
+There are two main use cases for no_new_privs so far:
+
+ - Filters installed for the seccomp mode 2 sandbox persist across
+   execve and can change the behavior of newly-executed programs.
+   Unprivileged users are therefore only allowed to install such filters
+   if no_new_privs is set.
+
+ - By itself, no_new_privs can be used to reduce the attack surface
+   available to an unprivileged user.  If everything running with a
+   given uid has no_new_privs set, then that uid will be unable to
+   escalate its privileges by directly attacking setuid, setgid, and
+   fcap-using binaries; it will need to compromise something without the
+   no_new_privs bit set first.
+
+In the future, other potentially dangerous kernel features could become
+available to unprivileged tasks if no_new_privs is set.  In principle,
+several options to unshare(2) and clone(2) would be safe when
+no_new_privs is set, and no_new_privs + chroot is considerable less
+dangerous than chroot by itself.

trunk/arch/arm/kernel/vmlinux.lds.S

@@ -183,7 +183,9 @@ SECTIONS
 	}
 #endif
 
+#ifdef CONFIG_SMP
 	PERCPU_SECTION(L1_CACHE_BYTES)
+#endif
 
 #ifdef CONFIG_XIP_KERNEL
 	__data_loc = ALIGN(4);		/* location in binary */

trunk/arch/arm/mm/mmu.c

@@ -791,6 +791,79 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	}
 }
 
+#ifndef CONFIG_ARM_LPAE
+
+/*
+ * The Linux PMD is made of two consecutive section entries covering 2MB
+ * (see definition in include/asm/pgtable-2level.h).  However a call to
+ * create_mapping() may optimize static mappings by using individual
+ * 1MB section mappings.  This leaves the actual PMD potentially half
+ * initialized if the top or bottom section entry isn't used, leaving it
+ * open to problems if a subsequent ioremap() or vmalloc() tries to use
+ * the virtual space left free by that unused section entry.
+ *
+ * Let's avoid the issue by inserting dummy vm entries covering the unused
+ * PMD halves once the static mappings are in place.
+ */
+
+static void __init pmd_empty_section_gap(unsigned long addr)
+{
+	struct vm_struct *vm;
+
+	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
+	vm->addr = (void *)addr;
+	vm->size = SECTION_SIZE;
+	vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
+	vm->caller = pmd_empty_section_gap;
+	vm_area_add_early(vm);
+}
+
+static void __init fill_pmd_gaps(void)
+{
+	struct vm_struct *vm;
+	unsigned long addr, next = 0;
+	pmd_t *pmd;
+
+	/* we're still single threaded hence no lock needed here */
+	for (vm = vmlist; vm; vm = vm->next) {
+		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		addr = (unsigned long)vm->addr;
+		if (addr < next)
+			continue;
+
+		/*
+		 * Check if this vm starts on an odd section boundary.
+		 * If so and the first section entry for this PMD is free
+		 * then we block the corresponding virtual address.
+		 */
+		if ((addr & ~PMD_MASK) == SECTION_SIZE) {
+			pmd = pmd_off_k(addr);
+			if (pmd_none(*pmd))
+				pmd_empty_section_gap(addr & PMD_MASK);
+		}
+
+		/*
+		 * Then check if this vm ends on an odd section boundary.
+		 * If so and the second section entry for this PMD is empty
+		 * then we block the corresponding virtual address.
+		 */
+		addr += vm->size;
+		if ((addr & ~PMD_MASK) == SECTION_SIZE) {
+			pmd = pmd_off_k(addr) + 1;
+			if (pmd_none(*pmd))
+				pmd_empty_section_gap(addr);
+		}
+
+		/* no need to look at any vm entry until we hit the next PMD */
+		next = (addr + PMD_SIZE - 1) & PMD_MASK;
+	}
+}
+
+#else
+#define fill_pmd_gaps() do { } while (0)
+#endif
+
 static void * __initdata vmalloc_min =
 	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
 
@@ -1072,6 +1145,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	if (mdesc->map_io)
 		mdesc->map_io();
+	fill_pmd_gaps();
 
 	/*
 	 * Finally flush the caches and tlb to ensure that we're in a

trunk/arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -810,7 +810,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	lwz	r3,VCORE_NAPPING_THREADS(r5)
 	lwz	r4,VCPU_PTID(r9)
 	li	r0,1
-	sldi	r0,r0,r4
+	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
 	beq	43f
 	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */

trunk/arch/powerpc/xmon/xmon.c

@@ -971,7 +971,7 @@ static int cpu_cmd(void)
 		/* print cpus waiting or in xmon */
 		printf("cpus stopped:");
 		count = 0;
-		for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+		for_each_possible_cpu(cpu) {
 			if (cpumask_test_cpu(cpu, &cpus_in_xmon)) {
 				if (count == 0)
 					printf(" %x", cpu);

trunk/drivers/gpu/drm/drm_edid.c

@@ -1039,6 +1039,24 @@ mode_in_range(const struct drm_display_mode *mode, struct edid *edid,
 	return true;
 }
 
+static bool valid_inferred_mode(const struct drm_connector *connector,
+				const struct drm_display_mode *mode)
+{
+	struct drm_display_mode *m;
+	bool ok = false;
+
+	list_for_each_entry(m, &connector->probed_modes, head) {
+		if (mode->hdisplay == m->hdisplay &&
+		    mode->vdisplay == m->vdisplay &&
+		    drm_mode_vrefresh(mode) == drm_mode_vrefresh(m))
+			return false; /* duplicated */
+		if (mode->hdisplay <= m->hdisplay &&
+		    mode->vdisplay <= m->vdisplay)
+			ok = true;
+	}
+	return ok;
+}
+
 static int
 drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			struct detailed_timing *timing)
@@ -1048,7 +1066,8 @@ drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 	struct drm_device *dev = connector->dev;
 
 	for (i = 0; i < drm_num_dmt_modes; i++) {
-		if (mode_in_range(drm_dmt_modes + i, edid, timing)) {
+		if (mode_in_range(drm_dmt_modes + i, edid, timing) &&
+		    valid_inferred_mode(connector, drm_dmt_modes + i)) {
 			newmode = drm_mode_duplicate(dev, &drm_dmt_modes[i]);
 			if (newmode) {
 				drm_mode_probed_add(connector, newmode);
@@ -1088,7 +1107,8 @@ drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			return modes;
 
 		fixup_mode_1366x768(newmode);
-		if (!mode_in_range(newmode, edid, timing)) {
+		if (!mode_in_range(newmode, edid, timing) ||
+		    !valid_inferred_mode(connector, newmode)) {
 			drm_mode_destroy(dev, newmode);
 			continue;
 		}
@@ -1116,7 +1136,8 @@ drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid,
 			return modes;
 
 		fixup_mode_1366x768(newmode);
-		if (!mode_in_range(newmode, edid, timing)) {
+		if (!mode_in_range(newmode, edid, timing) ||
+		    !valid_inferred_mode(connector, newmode)) {
 			drm_mode_destroy(dev, newmode);
 			continue;
 		}

trunk/drivers/gpu/drm/i915/i915_dma.c

@@ -1401,6 +1401,27 @@ i915_mtrr_setup(struct drm_i915_private *dev_priv, unsigned long base,
 	}
 }
 
+static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
+{
+	struct apertures_struct *ap;
+	struct pci_dev *pdev = dev_priv->dev->pdev;
+	bool primary;
+
+	ap = alloc_apertures(1);
+	if (!ap)
+		return;
+
+	ap->ranges[0].base = dev_priv->dev->agp->base;
+	ap->ranges[0].size =
+		dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT;
+	primary =
+		pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
+
+	remove_conflicting_framebuffers(ap, "inteldrmfb", primary);
+
+	kfree(ap);
+}
+
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -1446,6 +1467,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto free_priv;
 	}
 
+	dev_priv->mm.gtt = intel_gtt_get();
+	if (!dev_priv->mm.gtt) {
+		DRM_ERROR("Failed to initialize GTT\n");
+		ret = -ENODEV;
+		goto put_bridge;
+	}
+
+	i915_kick_out_firmware_fb(dev_priv);
+
 	pci_set_master(dev->pdev);
 
 	/* overlay on gen2 is broken and can't address above 1G */
@@ -1471,13 +1501,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto put_bridge;
 	}
 
-	dev_priv->mm.gtt = intel_gtt_get();
-	if (!dev_priv->mm.gtt) {
-		DRM_ERROR("Failed to initialize GTT\n");
-		ret = -ENODEV;
-		goto out_rmmap;
-	}
-
 	aperture_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT;
 
 	dev_priv->mm.gtt_mapping =

trunk/drivers/gpu/drm/radeon/radeon_gart.c

@@ -289,8 +289,9 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 	rdev->vm_manager.enabled = false;
 
 	/* mark first vm as always in use, it's the system one */
+	/* allocate enough for 2 full VM pts */
 	r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-				      rdev->vm_manager.max_pfn * 8,
+				      rdev->vm_manager.max_pfn * 8 * 2,
 				      RADEON_GEM_DOMAIN_VRAM);
 	if (r) {
 		dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
@@ -633,7 +634,15 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 	mutex_init(&vm->mutex);
 	INIT_LIST_HEAD(&vm->list);
 	INIT_LIST_HEAD(&vm->va);
-	vm->last_pfn = 0;
+	/* SI requires equal sized PTs for all VMs, so always set
+	 * last_pfn to max_pfn.  cayman allows variable sized
+	 * pts so we can grow then as needed.  Once we switch
+	 * to two level pts we can unify this again.
+	 */
+	if (rdev->family >= CHIP_TAHITI)
+		vm->last_pfn = rdev->vm_manager.max_pfn;
+	else
+		vm->last_pfn = 0;
 	/* map the ib pool buffer at 0 in virtual address space, set
 	 * read only
 	 */

trunk/drivers/gpu/drm/radeon/radeon_gem.c

@@ -292,6 +292,7 @@ int radeon_gem_mmap_ioctl(struct drm_device *dev, void *data,
 int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_busy *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -317,13 +318,14 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(robj->rdev, r);
+	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 
 int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp)
 {
+	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_wait_idle *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -336,10 +338,10 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_wait(robj, NULL, false);
 	/* callback hw specific functions if any */
-	if (robj->rdev->asic->ioctl_wait_idle)
-		robj->rdev->asic->ioctl_wait_idle(robj->rdev, robj);
+	if (rdev->asic->ioctl_wait_idle)
+		robj->rdev->asic->ioctl_wait_idle(rdev, robj);
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(robj->rdev, r);
+	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 

trunk/drivers/gpu/drm/radeon/si.c

@@ -2365,12 +2365,12 @@ int si_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(0x15DC, 0);
 
 	/* empty context1-15 */
-	/* FIXME start with 1G, once using 2 level pt switch to full
+	/* FIXME start with 4G, once using 2 level pt switch to full
 	 * vm size space
 	 */
 	/* set vm size, must be a multiple of 4 */
 	WREG32(VM_CONTEXT1_PAGE_TABLE_START_ADDR, 0);
-	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, (1 << 30) / RADEON_GPU_PAGE_SIZE);
+	WREG32(VM_CONTEXT1_PAGE_TABLE_END_ADDR, rdev->vm_manager.max_pfn);
 	for (i = 1; i < 16; i++) {
 		if (i < 8)
 			WREG32(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR + (i << 2),