[PATCH v2 1/7] powerpc/mm: Implement set_memory() routines

The set_memory_{ro/rw/nx/x}() functions are required for STRICT_MODULE_RWX,
and are generally useful primitives to have.  This implementation is
designed to be completely generic across powerpc's many MMUs.

It's possible that this could be optimised to be faster for specific
MMUs, but the focus is on having a generic and safe implementation for
now.

This implementation does not handle cases where 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.  These cases likely
shouldn't happen, but a more complex implementation with MMU-specific code
could safely handle them, so that is left as a TODO for now.

Signed-off-by: Russell Currey <redacted>
Signed-off-by: Christophe Leroy <redacted>
---
v2:
- use integers instead of pointers for action
- drop action check, nobody should call change_memory_attr() directly.
Should it happen, the function will just do nothing.
- Renamed confusing 'pte_val' var to 'pte' as pte_val() is already a function.
---
 arch/powerpc/Kconfig                  |  1 +
 arch/powerpc/include/asm/set_memory.h | 32 ++++++++++++
 arch/powerpc/mm/Makefile              |  1 +
 arch/powerpc/mm/pageattr.c            | 74 +++++++++++++++++++++++++++
 4 files changed, 108 insertions(+)
 create mode 100644 arch/powerpc/include/asm/set_memory.h
 create mode 100644 arch/powerpc/mm/pageattr.c

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a8fdb36a841e..ae6a27d07406 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig

@@ -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

diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
new file mode 100644
index 000000000000..c3621030a3fb
--- /dev/null
+++ b/arch/powerpc/include/asm/set_memory.h

@@ -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, int 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

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 5e147986400d..d0a0bcbc9289 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile

@@ -20,3 +20,4 @@ obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
 obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
+obj-$(CONFIG_ARCH_HAS_SET_MEMORY) += pageattr.o

diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
new file mode 100644
index 000000000000..0cb5294732b7
--- /dev/null
+++ b/arch/powerpc/mm/pageattr.c

@@ -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)
+{
+	int action = (int)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, int 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);
+}

-- 
2.25.0

With CONFIG_STRICT_KERNEL_RWX=y and CONFIG_KPROBES=y, there will be one
W+X page at boot by default.  This can be tested with
CONFIG_PPC_PTDUMP=y and CONFIG_PPC_DEBUG_WX=y set, and checking the
kernel log during boot.

powerpc doesn't implement its own alloc() for kprobes like other
architectures do, but we couldn't immediately mark RO anyway since we do
a memcpy to the page we allocate later.  After that, nothing should be
allowed to modify the page, and write permissions are removed well
before the kprobe is armed.

The memcpy() would fail if >1 probes were allocated, so use
patch_instruction() instead which is safe for RO.

Reviewed-by: Daniel Axtens <redacted>
Signed-off-by: Russell Currey <redacted>
Signed-off-by: Christophe Leroy <redacted>
---
v2: removed the redundant flush
---
 arch/powerpc/kernel/kprobes.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 2d27ec4feee4..d3e594e6094c 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c

@@ -24,6 +24,7 @@
 #include <asm/sstep.h>
 #include <asm/sections.h>
 #include <linux/uaccess.h>
+#include <linux/set_memory.h>
 
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

@@ -124,13 +125,12 @@ 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));
 	}
 
+	set_memory_ro((unsigned long)p->ainsn.insn, 1);
+
 	p->ainsn.boostable = 0;
 	return ret;
 }

-- 
2.25.0

From: Russell Currey <redacted>

Very rudimentary, just

	echo 1 > [debugfs]/check_wx_pages

and check the kernel log.  Useful for testing strict module RWX.

Updated the Kconfig entry to reflect this.

Also fixed a typo.

Signed-off-by: Russell Currey <redacted>
---
v2: no change
Signed-off-by: Christophe Leroy <redacted>
---
 arch/powerpc/Kconfig.debug      |  6 ++++--
 arch/powerpc/mm/ptdump/ptdump.c | 21 ++++++++++++++++++++-
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 0b063830eea8..e37960ef68c6 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug

@@ -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".
 

diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 206156255247..a15e19a3b14e 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c

@@ -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)

-- 
2.25.0

In addition to the set_memory_xx() functions which allows to change
the memory attributes of not (yet) used memory regions, implement a
set_memory_attr() function to:
- set the final memory protection after init on currently used
kernel regions.
- enable/disable kernel memory regions in the scope of DEBUG_PAGEALLOC.

Unlike the set_memory_xx() which can act in three step as the regions
are unused, this function must modify 'on the fly' as the kernel is
executing from them. At the moment only PPC32 will use it and changing
page attributes on the fly is not an issue.

Signed-off-by: Christophe Leroy <redacted>
---
v2: new
---
 arch/powerpc/include/asm/set_memory.h |  2 ++
 arch/powerpc/mm/pageattr.c            | 33 +++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h
index c3621030a3fb..4dadff67e265 100644
--- a/arch/powerpc/include/asm/set_memory.h
+++ b/arch/powerpc/include/asm/set_memory.h

@@ -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

diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c
index 0cb5294732b7..dff6c92cd09b 100644
--- a/arch/powerpc/mm/pageattr.c
+++ b/arch/powerpc/mm/pageattr.c

@@ -72,3 +72,36 @@ int change_memory_attr(unsigned long addr, int numpages, int 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((int)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));
+}

-- 
2.25.0

Use set_memory_attr() instead of the PPC32 specific change_page_attr()

change_page_attr() was checking that the address was not mapped by
blocks and was handling highmem, but that's unneeded because the
affected pages can't be in highmem and block mapping verification
is already done by the callers.

Signed-off-by: Christophe Leroy <redacted>
---
v2: new
---
 arch/powerpc/mm/pgtable_32.c | 95 ++++--------------------------------
 1 file changed, 10 insertions(+), 85 deletions(-)

diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 5fb90edd865e..3d92eaf3ee2f 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c

@@ -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 */

-- 
2.25.0

From: Russell Currey <redacted>

To enable strict module RWX on powerpc, set:

    CONFIG_STRICT_MODULE_RWX=y

You should also have CONFIG_STRICT_KERNEL_RWX=y set to have any real
security benefit.

ARCH_HAS_STRICT_MODULE_RWX is set to require ARCH_HAS_STRICT_KERNEL_RWX.
This is due to a quirk in arch/Kconfig and arch/powerpc/Kconfig that
makes STRICT_MODULE_RWX *on by default* in configurations where
STRICT_KERNEL_RWX is *unavailable*.

Since this doesn't make much sense, and module RWX without kernel RWX
doesn't make much sense, having the same dependencies as kernel RWX
works around this problem.

Signed-off-by: Russell Currey <redacted>
---
v2: no change
Signed-off-by: Christophe Leroy <redacted>
---
 arch/powerpc/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index ae6a27d07406..371e3bef5c32 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig

@@ -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

-- 
2.25.0

From: Russell Currey <redacted>

skiroot_defconfig is the only powerpc defconfig with STRICT_KERNEL_RWX
enabled, and if you want memory protection for kernel text you'd want it
for modules too, so enable STRICT_MODULE_RWX there.

Acked-by: Joel Stanley <redacted>
Signed-off-by: Russell Currey <redacted>
---
v2: no change
Signed-off-by: Christophe Leroy <redacted>
---
 arch/powerpc/configs/skiroot_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 069f67f12731..b74358c3ede8 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig

@@ -31,6 +31,7 @@ CONFIG_PERF_EVENTS=y
 CONFIG_SLAB_FREELIST_HARDENED=y
 CONFIG_JUMP_LABEL=y
 CONFIG_STRICT_KERNEL_RWX=y
+CONFIG_STRICT_MODULE_RWX=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_SIG=y

-- 
2.25.0

Hi Christophe,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on powerpc/next]
[also build test ERROR on next-20200131]
[cannot apply to v5.5]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system. BTW, we also suggest to use '--base' option to specify the
base tree in git format-patch, please see https://stackoverflow.com/a/37406982]

url:    https://github.com/0day-ci/linux/commits/Christophe-Leroy/powerpc-mm-Implement-set_memory-routines/20200203-060234
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-ppc64_defconfig (attached as .config)
compiler: powerpc64-linux-gcc (GCC) 7.5.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        GCC_VERSION=7.5.0 make.cross ARCH=powerpc 

If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <redacted>

All errors (new ones prefixed by >>):

   arch/powerpc/mm/pageattr.c: In function 'change_page_attr':

quoted

arch/powerpc/mm/pageattr.c:32:15: error: cast from pointer to integer of different size [-Werror=pointer-to-int-cast]

     int action = (int)data;
                  ^
   arch/powerpc/mm/pageattr.c: In function 'change_memory_attr':

quoted

arch/powerpc/mm/pageattr.c:73:68: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]

     return apply_to_page_range(&init_mm, start, sz, change_page_attr, (void *)action);
                                                                       ^
   cc1: all warnings being treated as errors

vim +32 arch/powerpc/mm/pageattr.c

    15	
    16	
    17	/*
    18	 * Updates the attributes of a page in three steps:
    19	 *
    20	 * 1. invalidate the page table entry
    21	 * 2. flush the TLB
    22	 * 3. install the new entry with the updated attributes
    23	 *
    24	 * This is unsafe if the caller is attempting to change the mapping of the
    25	 * page it is executing from, or if another CPU is concurrently using the
    26	 * page being altered.
    27	 *
    28	 * TODO make the implementation resistant to this.
    29	 */
    30	static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
    31	{
  > 32		int action = (int)data;
    33		pte_t pte;
    34	
    35		spin_lock(&init_mm.page_table_lock);
    36	
    37		/* invalidate the PTE so it's safe to modify */
    38		pte = ptep_get_and_clear(&init_mm, addr, ptep);
    39		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
    40	
    41		/* modify the PTE bits as desired, then apply */
    42		switch (action) {
    43		case SET_MEMORY_RO:
    44			pte = pte_wrprotect(pte);
    45			break;
    46		case SET_MEMORY_RW:
    47			pte = pte_mkwrite(pte);
    48			break;
    49		case SET_MEMORY_NX:
    50			pte = pte_exprotect(pte);
    51			break;
    52		case SET_MEMORY_X:
    53			pte = pte_mkexec(pte);
    54			break;
    55		default:
    56			break;
    57		}
    58	
    59		set_pte_at(&init_mm, addr, ptep, pte);
    60		spin_unlock(&init_mm.page_table_lock);
    61	
    62		return 0;
    63	}
    64	
    65	int change_memory_attr(unsigned long addr, int numpages, int action)
    66	{
    67		unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
    68		unsigned long sz = numpages * PAGE_SIZE;
    69	
    70		if (!numpages)
    71			return 0;
    72	
  > 73		return apply_to_page_range(&init_mm, start, sz, change_page_attr, (void *)action);

---
0-DAY kernel test infrastructure                 Open Source Technology Center
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org Intel Corporation

On Fri, 2020-01-31 at 13:34 +0000, Christophe Leroy wrote:

Since this can be called multiple times on the same page, can avoid by
implementing:

void *alloc_insn_page(void)
{
	void *page;

	page = vmalloc_exec(PAGE_SIZE);
	if (page)
		set_memory_ro((unsigned long)page, 1);

	return page;
}

Which is pretty much the same as what's in arm64.  Works for me and
passes ftracetest, I was originally doing this but cut it because it
broke with the memcpy, but works with patch_instruction().

 	p->ainsn.boostable = 0;
 	return ret;
 }

Le 03/02/2020 à 05:50, Russell Currey a écrit :

On Fri, 2020-01-31 at 13:34 +0000, Christophe Leroy wrote:

quoted

With CONFIG_STRICT_KERNEL_RWX=y and CONFIG_KPROBES=y, there will be
one
W+X page at boot by default.  This can be tested with
CONFIG_PPC_PTDUMP=y and CONFIG_PPC_DEBUG_WX=y set, and checking the
kernel log during boot.

powerpc doesn't implement its own alloc() for kprobes like other
architectures do, but we couldn't immediately mark RO anyway since we
do
a memcpy to the page we allocate later.  After that, nothing should
be
allowed to modify the page, and write permissions are removed well
before the kprobe is armed.

The memcpy() would fail if >1 probes were allocated, so use
patch_instruction() instead which is safe for RO.

Reviewed-by: Daniel Axtens <redacted>
Signed-off-by: Russell Currey <redacted>
Signed-off-by: Christophe Leroy <redacted>
---
v2: removed the redundant flush
---
  arch/powerpc/kernel/kprobes.c | 8 ++++----
  1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/kprobes.c

b/arch/powerpc/kernel/kprobes.c
index 2d27ec4feee4..d3e594e6094c 100644

--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c

@@ -24,6 +24,7 @@
  #include <asm/sstep.h>
  #include <asm/sections.h>
  #include <linux/uaccess.h>
+#include <linux/set_memory.h>
  
  DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
  DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

@@ -124,13 +125,12 @@ 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));
  	}
  
+	set_memory_ro((unsigned long)p->ainsn.insn, 1);
+

Since this can be called multiple times on the same page, can avoid by
implementing:

void *alloc_insn_page(void)
{
	void *page;

	page = vmalloc_exec(PAGE_SIZE);
	if (page)
		set_memory_ro((unsigned long)page, 1);

	return page;
}

Which is pretty much the same as what's in arm64.  Works for me and
passes ftracetest, I was originally doing this but cut it because it
broke with the memcpy, but works with patch_instruction().

quoted

  	p->ainsn.boostable = 0;
  	return ret;
  }

Ok. I'll send out v3 as patch 1 fails on PPC64, so I'll take that in.

Christophe