[PATCH v4 0/8] set_memory() routines and STRICT_MODULE_RWX

@@ -24,6 +24,8 @@
 #include <asm/sstep.h>
 #include <asm/sections.h>
 #include <linux/uaccess.h>
+#include <linux/set_memory.h>
+#include <linux/vmalloc.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

@@ -102,6 +104,16 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
 	return addr;
 }
 
+void *alloc_insn_page(void)
+{
+	void *page = vmalloc_exec(PAGE_SIZE);
+
+	if (page)
+		set_memory_ro((unsigned long)page, 1);
+
+	return page;
+}
+
 int arch_prepare_kprobe(struct kprobe *p)
 {
 	int ret = 0;

@@ -124,11 +136,8 @@ int arch_prepare_kprobe(struct kprobe *p)
 	}
 
 	if (!ret) {
-		memcpy(p->ainsn.insn, p->addr,
-				MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+		patch_instruction(p->ainsn.insn, *p->addr);
 		p->opcode = *p->addr;
-		flush_icache_range((unsigned long)p->ainsn.insn,
-			(unsigned long)p->ainsn.insn + sizeof(kprobe_opcode_t));
 	}
 
 	p->ainsn.boostable = 0;

@@ -129,6 +129,7 @@ config PPC
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
+	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_SET_MEMORY_H
+#define _ASM_POWERPC_SET_MEMORY_H
+
+#define SET_MEMORY_RO	0
+#define SET_MEMORY_RW	1
+#define SET_MEMORY_NX	2
+#define SET_MEMORY_X	3
+
+int change_memory_attr(unsigned long addr, int numpages, long action);
+
+static inline int set_memory_ro(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_RO);
+}
+
+static inline int set_memory_rw(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_RW);
+}
+
+static inline int set_memory_nx(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_NX);
+}
+
+static inline int set_memory_x(unsigned long addr, int numpages)
+{
+	return change_memory_attr(addr, numpages, SET_MEMORY_X);
+}
+
+#endif

@@ -5,7 +5,7 @@
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
-obj-y				:= fault.o mem.o pgtable.o mmap.o \
+obj-y				:= fault.o mem.o pgtable.o mmap.o pageattr.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
 				   pgtable-frag.o ioremap.o ioremap_$(BITS).o \
 				   init-common.o mmu_context.o drmem.o

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * MMU-generic set_memory implementation for powerpc
+ *
+ * Copyright 2019, IBM Corporation.
+ */
+
+#include <linux/mm.h>
+#include <linux/set_memory.h>
+
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+
+/*
+ * Updates the attributes of a page in three steps:
+ *
+ * 1. invalidate the page table entry
+ * 2. flush the TLB
+ * 3. install the new entry with the updated attributes
+ *
+ * This is unsafe if the caller is attempting to change the mapping of the
+ * page it is executing from, or if another CPU is concurrently using the
+ * page being altered.
+ *
+ * TODO make the implementation resistant to this.
+ */
+static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
+{
+	long action = (long)data;
+	pte_t pte;
+
+	spin_lock(&init_mm.page_table_lock);
+
+	/* invalidate the PTE so it's safe to modify */
+	pte = ptep_get_and_clear(&init_mm, addr, ptep);
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	/* modify the PTE bits as desired, then apply */
+	switch (action) {
+	case SET_MEMORY_RO:
+		pte = pte_wrprotect(pte);
+		break;
+	case SET_MEMORY_RW:
+		pte = pte_mkwrite(pte);
+		break;
+	case SET_MEMORY_NX:
+		pte = pte_exprotect(pte);
+		break;
+	case SET_MEMORY_X:
+		pte = pte_mkexec(pte);
+		break;
+	default:
+		break;
+	}
+
+	set_pte_at(&init_mm, addr, ptep, pte);
+	spin_unlock(&init_mm.page_table_lock);
+
+	return 0;
+}
+
+int change_memory_attr(unsigned long addr, int numpages, long action)
+{
+	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
+	unsigned long sz = numpages * PAGE_SIZE;
+
+	if (!numpages)
+		return 0;
+
+	return apply_to_page_range(&init_mm, start, sz, change_page_attr, (void *)action);
+}

@@ -370,7 +370,7 @@ config PPC_PTDUMP
 	  If you are unsure, say N.
 
 config PPC_DEBUG_WX
-	bool "Warn on W+X mappings at boot"
+	bool "Warn on W+X mappings at boot & enable manual checks at runtime"
 	depends on PPC_PTDUMP && STRICT_KERNEL_RWX
 	help
 	  Generate a warning if any W+X mappings are found at boot.

@@ -384,7 +384,9 @@ config PPC_DEBUG_WX
 	  of other unfixed kernel bugs easier.
 
 	  There is no runtime or memory usage effect of this option
-	  once the kernel has booted up - it's a one time check.
+	  once the kernel has booted up, it only automatically checks once.
+
+	  Enables the "check_wx_pages" debugfs entry for checking at runtime.
 
 	  If in doubt, say "Y".
 

@@ -4,7 +4,7 @@
  *
  * This traverses the kernel pagetables and dumps the
  * information about the used sections of memory to
- * /sys/kernel/debug/kernel_pagetables.
+ * /sys/kernel/debug/kernel_page_tables.
  *
  * Derived from the arm64 implementation:
  * Copyright (c) 2014, The Linux Foundation, Laura Abbott.

@@ -413,6 +413,25 @@ void ptdump_check_wx(void)
 	else
 		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
 }
+
+static int check_wx_debugfs_set(void *data, u64 val)
+{
+	if (val != 1ULL)
+		return -EINVAL;
+
+	ptdump_check_wx();
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(check_wx_fops, NULL, check_wx_debugfs_set, "%llu\n");
+
+static int ptdump_check_wx_init(void)
+{
+	return debugfs_create_file("check_wx_pages", 0200, NULL,
+				   NULL, &check_wx_fops) ? 0 : -ENOMEM;
+}
+device_initcall(ptdump_check_wx_init);
 #endif
 
 static int ptdump_init(void)

@@ -131,6 +131,7 @@ config PPC
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION)
+	select ARCH_HAS_STRICT_MODULE_RWX	if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UACCESS_MCSAFE		if PPC64

@@ -51,6 +51,7 @@ CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet"
 # CONFIG_PPC_MEM_KEYS is not set
 CONFIG_JUMP_LABEL=y
 CONFIG_STRICT_KERNEL_RWX=y
+CONFIG_STRICT_MODULE_RWX=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_SIG_FORCE=y

@@ -29,4 +29,6 @@ static inline int set_memory_x(unsigned long addr, int numpages)
 	return change_memory_attr(addr, numpages, SET_MEMORY_X);
 }
 
+int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot);
+
 #endif

@@ -72,3 +72,36 @@ int change_memory_attr(unsigned long addr, int numpages, long action)
 
 	return apply_to_page_range(&init_mm, start, sz, change_page_attr, (void *)action);
 }
+
+/*
+ * Set the attributes of a page:
+ *
+ * This function is used by PPC32 at the end of init to set final kernel memory
+ * protection. It includes changing the maping of the page it is executing from
+ * and data pages it is using.
+ */
+static int set_page_attr(pte_t *ptep, unsigned long addr, void *data)
+{
+	pgprot_t prot = __pgprot((unsigned long)data);
+
+	spin_lock(&init_mm.page_table_lock);
+
+	set_pte_at(&init_mm, addr, ptep, pte_modify(*ptep, prot));
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+	spin_unlock(&init_mm.page_table_lock);
+
+	return 0;
+}
+
+int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot)
+{
+	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
+	unsigned long sz = numpages * PAGE_SIZE;
+
+	if (!numpages)
+		return 0;
+
+	return apply_to_page_range(&init_mm, start, sz, set_page_attr,
+				   (void *)pgprot_val(prot));
+}

@@ -23,6 +23,7 @@
 #include <linux/highmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
+#include <linux/set_memory.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>

@@ -121,99 +122,20 @@ void __init mapin_ram(void)
 	}
 }
 
-/* Scan the real Linux page tables and return a PTE pointer for
- * a virtual address in a context.
- * Returns true (1) if PTE was found, zero otherwise.  The pointer to
- * the PTE pointer is unmodified if PTE is not found.
- */
-static int
-get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
-{
-        pgd_t	*pgd;
-	pud_t	*pud;
-        pmd_t	*pmd;
-        pte_t	*pte;
-        int     retval = 0;
-
-        pgd = pgd_offset(mm, addr & PAGE_MASK);
-        if (pgd) {
-		pud = pud_offset(pgd, addr & PAGE_MASK);
-		if (pud && pud_present(*pud)) {
-			pmd = pmd_offset(pud, addr & PAGE_MASK);
-			if (pmd_present(*pmd)) {
-				pte = pte_offset_map(pmd, addr & PAGE_MASK);
-				if (pte) {
-					retval = 1;
-					*ptep = pte;
-					if (pmdp)
-						*pmdp = pmd;
-					/* XXX caller needs to do pte_unmap, yuck */
-				}
-			}
-		}
-        }
-        return(retval);
-}
-
-static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
-{
-	pte_t *kpte;
-	pmd_t *kpmd;
-	unsigned long address;
-
-	BUG_ON(PageHighMem(page));
-	address = (unsigned long)page_address(page);
-
-	if (v_block_mapped(address))
-		return 0;
-	if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
-		return -EINVAL;
-	__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
-	pte_unmap(kpte);
-
-	return 0;
-}
-
-/*
- * Change the page attributes of an page in the linear mapping.
- *
- * THIS DOES NOTHING WITH BAT MAPPINGS, DEBUG USE ONLY
- */
-static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
-{
-	int i, err = 0;
-	unsigned long flags;
-	struct page *start = page;
-
-	local_irq_save(flags);
-	for (i = 0; i < numpages; i++, page++) {
-		err = __change_page_attr_noflush(page, prot);
-		if (err)
-			break;
-	}
-	wmb();
-	local_irq_restore(flags);
-	flush_tlb_kernel_range((unsigned long)page_address(start),
-			       (unsigned long)page_address(page));
-	return err;
-}
-
 void mark_initmem_nx(void)
 {
-	struct page *page = virt_to_page(_sinittext);
 	unsigned long numpages = PFN_UP((unsigned long)_einittext) -
 				 PFN_DOWN((unsigned long)_sinittext);
 
 	if (v_block_mapped((unsigned long)_stext + 1))
 		mmu_mark_initmem_nx();
 	else
-		change_page_attr(page, numpages, PAGE_KERNEL);
+		set_memory_attr((unsigned long)_sinittext, numpages, PAGE_KERNEL);
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
 void mark_rodata_ro(void)
 {
-	struct page *page;
 	unsigned long numpages;
 
 	if (v_block_mapped((unsigned long)_sinittext)) {

@@ -222,20 +144,18 @@ void mark_rodata_ro(void)
 		return;
 	}
 
-	page = virt_to_page(_stext);
 	numpages = PFN_UP((unsigned long)_etext) -
 		   PFN_DOWN((unsigned long)_stext);
 
-	change_page_attr(page, numpages, PAGE_KERNEL_ROX);
+	set_memory_attr((unsigned long)_stext, numpages, PAGE_KERNEL_ROX);
 	/*
 	 * mark .rodata as read only. Use __init_begin rather than __end_rodata
 	 * to cover NOTES and EXCEPTION_TABLE.
 	 */
-	page = virt_to_page(__start_rodata);
 	numpages = PFN_UP((unsigned long)__init_begin) -
 		   PFN_DOWN((unsigned long)__start_rodata);
 
-	change_page_attr(page, numpages, PAGE_KERNEL_RO);
+	set_memory_attr((unsigned long)__start_rodata, numpages, PAGE_KERNEL_RO);
 
 	// mark_initmem_nx() should have already run by now
 	ptdump_check_wx();

@@ -245,9 +165,14 @@ void mark_rodata_ro(void)
 #ifdef CONFIG_DEBUG_PAGEALLOC
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
+	unsigned long addr = (unsigned long)page_address(page);
+
 	if (PageHighMem(page))
 		return;
 
-	change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0));
+	if (enable)
+		set_memory_attr(addr, numpages, PAGE_KERNEL);
+	else
+		set_memory_attr(addr, numpages, __pgprot(0));
 }
 #endif /* CONFIG_DEBUG_PAGEALLOC */

@@ -96,12 +96,17 @@ static int set_page_attr(pte_t *ptep, unsigned long addr, void *data)
 
 int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot)
 {
-	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
-	unsigned long sz = numpages * PAGE_SIZE;
+	unsigned long start, size;
+
+	if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		return 0;
 
 	if (!numpages)
 		return 0;
 
-	return apply_to_page_range(&init_mm, start, sz, set_page_attr,
+	start = ALIGN_DOWN(addr, PAGE_SIZE);
+	size = numpages * PAGE_SIZE;
+
+	return apply_to_page_range(&init_mm, start, size, set_page_attr,
 				   (void *)pgprot_val(prot));
 }