Merge tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Enable KFENCE for 32-bit.

 - Implement EBPF for 32-bit.

 - Convert 32-bit to do interrupt entry/exit in C.

 - Convert 64-bit BookE to do interrupt entry/exit in C.

 - Changes to our signal handling code to use user_access_begin/end()
   more extensively.

 - Add support for time namespaces (CONFIG_TIME_NS)

 - A series of fixes that allow us to reenable STRICT_KERNEL_RWX.

 - Other smaller features, fixes & cleanups.

Thanks to Alexey Kardashevskiy, Andreas Schwab, Andrew Donnellan, Aneesh
Kumar K.V, Athira Rajeev, Bhaskar Chowdhury, Bixuan Cui, Cédric Le
Goater, Chen Huang, Chris Packham, Christophe Leroy, Christopher M.
Riedl, Colin Ian King, Dan Carpenter, Daniel Axtens, Daniel Henrique
Barboza, David Gibson, Davidlohr Bueso, Denis Efremov, dingsenjie,
Dmitry Safonov, Dominic DeMarco, Fabiano Rosas, Ganesh Goudar, Geert
Uytterhoeven, Geetika Moolchandani, Greg Kurz, Guenter Roeck, Haren
Myneni, He Ying, Jiapeng Chong, Jordan Niethe, Laurent Dufour, Lee
Jones, Leonardo Bras, Li Huafei, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Nathan Chancellor, Nathan Lynch, Nicholas Piggin,
Oliver O'Halloran, Paul Menzel, Pu Lehui, Randy Dunlap, Ravi Bangoria,
Rosen Penev, Russell Currey, Santosh Sivaraj, Sebastian Andrzej Siewior,
Segher Boessenkool, Shivaprasad G Bhat, Srikar Dronamraju, Stephen
Rothwell, Thadeu Lima de Souza Cascardo, Thomas Gleixner, Tony Ambardar,
Tyrel Datwyler, Vaibhav Jain, Vincenzo Frascino, Xiongwei Song, Yang Li,
Yu Kuai, and Zhang Yunkai.

* tag 'powerpc-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (302 commits)
  powerpc/signal32: Fix erroneous SIGSEGV on RT signal return
  powerpc: Avoid clang uninitialized warning in __get_user_size_allowed
  powerpc/papr_scm: Mark nvdimm as unarmed if needed during probe
  powerpc/kvm: Fix build error when PPC_MEM_KEYS/PPC_PSERIES=n
  powerpc/kasan: Fix shadow start address with modules
  powerpc/kernel/iommu: Use largepool as a last resort when !largealloc
  powerpc/kernel/iommu: Align size for IOMMU_PAGE_SIZE() to save TCEs
  powerpc/44x: fix spelling mistake in Kconfig "varients" -> "variants"
  powerpc/iommu: Annotate nested lock for lockdep
  powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
  powerpc/iommu: Allocate it_map by vmalloc
  selftests/powerpc: remove unneeded semicolon
  powerpc/64s: remove unneeded semicolon
  powerpc/eeh: remove unneeded semicolon
  powerpc/selftests: Add selftest to test concurrent perf/ptrace events
  powerpc/selftests/perf-hwbreak: Add testcases for 2nd DAWR
  powerpc/selftests/perf-hwbreak: Coalesce event creation code
  powerpc/selftests/ptrace-hwbreak: Add testcases for 2nd DAWR
  powerpc/configs: Add IBMVNIC to some 64-bit configs
  selftests/powerpc: Add uaccess flush test
  ...

1 files changed, 123 insertions, 15 deletions

diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index e839a906fdf2..717f2c9a7573 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -18,6 +18,7 @@
 #include <linux/security.h>
 #include <linux/memblock.h>
 #include <linux/syscalls.h>
+#include <linux/time_namespace.h>
 #include <vdso/datapage.h>
 
 #include <asm/syscall.h>
@@ -50,15 +51,21 @@ static union {
 } vdso_data_store __page_aligned_data;
 struct vdso_arch_data *vdso_data = &vdso_data_store.data;
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
 		       unsigned long text_size)
 {
 	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
 
-	if (new_size != text_size + PAGE_SIZE)
+	if (new_size != text_size)
 		return -EINVAL;
 
-	current->mm->context.vdso = (void __user *)new_vma->vm_start + PAGE_SIZE;
+	current->mm->context.vdso = (void __user *)new_vma->vm_start;
 
 	return 0;
 }
@@ -73,6 +80,14 @@ static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_str
 	return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
 }
 
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf);
+
+static struct vm_special_mapping vvar_spec __ro_after_init = {
+	.name = "[vvar]",
+	.fault = vvar_fault,
+};
+
 static struct vm_special_mapping vdso32_spec __ro_after_init = {
 	.name = "[vdso]",
 	.mremap = vdso32_mremap,
@@ -83,17 +98,105 @@ static struct vm_special_mapping vdso64_spec __ro_after_init = {
 	.mremap = vdso64_mremap,
 };
 
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return ((struct vdso_arch_data *)vvar_page)->data;
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, &vvar_spec))
+			zap_page_range(vma, vma->vm_start, size);
+	}
+
+	mmap_read_unlock(mm);
+	return 0;
+}
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = virt_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = virt_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
 /*
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
  */
 static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
-	struct mm_struct *mm = current->mm;
+	unsigned long vdso_size, vdso_base, mappings_size;
 	struct vm_special_mapping *vdso_spec;
+	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
+	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long vdso_size;
-	unsigned long vdso_base;
 
 	if (is_32bit_task()) {
 		vdso_spec = &vdso32_spec;
@@ -110,8 +213,8 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 		vdso_base = 0;
 	}
 
-	/* Add a page to the vdso size for the data page */
-	vdso_size += PAGE_SIZE;
+	mappings_size = vdso_size + vvar_size;
+	mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK;
 
 	/*
 	 * pick a base address for the vDSO in process space. We try to put it
@@ -119,9 +222,7 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	 * and end up putting it elsewhere.
 	 * Add enough to the size so that the result can be aligned.
 	 */
-	vdso_base = get_unmapped_area(NULL, vdso_base,
-				      vdso_size + ((VDSO_ALIGNMENT - 1) & PAGE_MASK),
-				      0, 0);
+	vdso_base = get_unmapped_area(NULL, vdso_base, mappings_size, 0, 0);
 	if (IS_ERR_VALUE(vdso_base))
 		return vdso_base;
 
@@ -133,7 +234,13 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	 * install_special_mapping or the perf counter mmap tracking code
 	 * will fail to recognise it as a vDSO.
 	 */
-	mm->context.vdso = (void __user *)vdso_base + PAGE_SIZE;
+	mm->context.vdso = (void __user *)vdso_base + vvar_size;
+
+	vma = _install_special_mapping(mm, vdso_base, vvar_size,
+				       VM_READ | VM_MAYREAD | VM_IO |
+				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
 	/*
 	 * our vma flags don't have VM_WRITE so by default, the process isn't
@@ -145,9 +252,12 @@ static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_int
 	 * It's fine to use that for setting breakpoints in the vDSO code
 	 * pages though.
 	 */
-	vma = _install_special_mapping(mm, vdso_base, vdso_size,
+	vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size,
 				       VM_READ | VM_EXEC | VM_MAYREAD |
 				       VM_MAYWRITE | VM_MAYEXEC, vdso_spec);
+	if (IS_ERR(vma))
+		do_munmap(mm, vdso_base, vvar_size, NULL);
+
 	return PTR_ERR_OR_ZERO(vma);
 }
 
@@ -249,10 +359,8 @@ static struct page ** __init vdso_setup_pages(void *start, void *end)
 	if (!pagelist)
 		panic("%s: Cannot allocate page list for VDSO", __func__);
 
-	pagelist[0] = virt_to_page(vdso_data);
-
 	for (i = 0; i < pages; i++)
-		pagelist[i + 1] = virt_to_page(start + i * PAGE_SIZE);
+		pagelist[i] = virt_to_page(start + i * PAGE_SIZE);
 
 	return pagelist;
 }