[PATCH 1/3] x86: Fix typo in mark_rodata_ro

[PATCH 1/3] x86: Fix typo in mark_rodata_ro

[Yinghai Lu]

In the comment, should use cleanup_highmap().
and also remove not needed cast for _brk_end, as it is
unsigned long.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/mm/init_64.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -1145,9 +1145,9 @@ void mark_rodata_ro(void)
 	 * of the PMD will remain mapped executable.
 	 *
 	 * Any PMD which was setup after the one which covers _brk_end
-	 * has been zapped already via cleanup_highmem().
+	 * has been zapped already via cleanup_highmap().
 	 */
-	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
+	all_end = roundup(_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();

[PATCH 2/3] x86, 64bit: add pfn_range_is_highmapped()

[Yinghai Lu]

Need to use it to support holes in highmap when remove not
used range in highmap.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/include/asm/pgtable_64.h |    2 ++
 arch/x86/mm/init_64.c             |   22 ++++++++++++++++++++++
 arch/x86/mm/pageattr.c            |   16 +---------------
 3 files changed, 25 insertions(+), 15 deletions(-)

Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -378,6 +378,23 @@ void __init init_extra_mapping_uc(unsign
 	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC);
 }
 
+/* three holes at most*/
+#define NR_RANGE 4
+static struct range pfn_highmapped[NR_RANGE];
+static int nr_pfn_highmapped;
+
+int pfn_range_is_highmapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_pfn_highmapped; i++)
+		if ((start_pfn >= pfn_highmapped[i].start) &&
+		    (end_pfn <= pfn_highmapped[i].end))
+			return 1;
+
+	return 0;
+}
+
 /*
  * The head.S code sets up the kernel high mapping:
  *
@@ -412,6 +429,11 @@ void __init cleanup_highmap(void)
 		if (vaddr < (unsigned long) _text || vaddr > end)
 			set_pmd(pmd, __pmd(0));
 	}
+
+	nr_pfn_highmapped = add_range(pfn_highmapped, NR_RANGE,
+			nr_pfn_highmapped,
+			__pa_symbol(_text) >> PAGE_SHIFT,
+			__pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT);
 }
 
 static unsigned long __meminit
Index: linux-2.6/arch/x86/mm/pageattr.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/pageattr.c
+++ linux-2.6/arch/x86/mm/pageattr.c
@@ -91,20 +91,6 @@ void arch_report_meminfo(struct seq_file
 static inline void split_page_count(int level) { }
 #endif
 
-#ifdef CONFIG_X86_64
-
-static inline unsigned long highmap_start_pfn(void)
-{
-	return __pa_symbol(_text) >> PAGE_SHIFT;
-}
-
-static inline unsigned long highmap_end_pfn(void)
-{
-	return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
-}
-
-#endif
-
 #ifdef CONFIG_DEBUG_PAGEALLOC
 # define debug_pagealloc 1
 #else
@@ -1255,7 +1241,7 @@ static int cpa_process_alias(struct cpa_
 	 * to touch the high mapped kernel as well:
 	 */
 	if (!within(vaddr, (unsigned long)_text, _brk_end) &&
-	    within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) {
+	    pfn_range_is_highmapped(cpa->pfn, 1)) {
 		unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
 					       __START_KERNEL_map - phys_base;
 		alias_cpa = *cpa;
Index: linux-2.6/arch/x86/include/asm/pgtable_64.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/pgtable_64.h
+++ linux-2.6/arch/x86/include/asm/pgtable_64.h
@@ -167,6 +167,8 @@ static inline int pgd_large(pgd_t pgd) {
 extern int kern_addr_valid(unsigned long addr);
 extern void cleanup_highmap(void);
 
+int pfn_range_is_highmapped(unsigned long start_pfn, unsigned long end_pfn);
+
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 

[PATCH 3/4] x86, 64bit: remove highmap for not needed ranges

[Yinghai Lu]

add cleanup_highmap_late to remove highmap for initmem, around rodata, and
[_brk_end, all_end).

Kernel Layout:

[    0.000000]   .text: [0x01000000-0x0200df88]
[    0.000000] .rodata: [0x02200000-0x02a1dfff]
[    0.000000]   .data: [0x02c00000-0x02e510ff]
[    0.000000]   .init: [0x02e53000-0x03213fff]
[    0.000000]    .bss: [0x03222000-0x0437cfff]
[    0.000000]    .brk: [0x0437d000-0x043a2fff]

Actually used brk:
[    0.270365] memblock_reserve: [0x0000000437d000-0x00000004383fff] flags 0x0 BRK

Before patch:
---[ High Kernel Mapping ]---
---[ High Kernel Mapping ]---
0xffffffff80000000-0xffffffff81000000          16M                           pmd
0xffffffff81000000-0xffffffff82000000          16M     ro         PSE GLB x  pmd
0xffffffff82000000-0xffffffff82011000          68K     ro             GLB x  pte
0xffffffff82011000-0xffffffff82200000        1980K     RW             GLB x  pte
0xffffffff82200000-0xffffffff82a00000           8M     ro         PSE GLB NX pmd
0xffffffff82a00000-0xffffffff82a1e000         120K     ro             GLB NX pte
0xffffffff82a1e000-0xffffffff82c00000        1928K     RW             GLB NX pte
0xffffffff82c00000-0xffffffff82e00000           2M     RW         PSE GLB NX pmd
0xffffffff82e00000-0xffffffff83000000           2M     RW             GLB NX pte
0xffffffff83000000-0xffffffff83200000           2M     RW         PSE GLB NX pmd
0xffffffff83200000-0xffffffff83400000           2M     RW             GLB NX pte
0xffffffff83400000-0xffffffff84400000          16M     RW         PSE GLB NX pmd
0xffffffff84400000-0xffffffffa0000000         444M                           pmd

After patch:
---[ High Kernel Mapping ]---
0xffffffff80000000-0xffffffff81000000          16M                           pmd
0xffffffff81000000-0xffffffff82000000          16M     ro         PSE GLB x  pmd
0xffffffff82000000-0xffffffff82012000          72K     ro             GLB x  pte
0xffffffff82012000-0xffffffff82200000        1976K                           pte
0xffffffff82200000-0xffffffff82a00000           8M     ro         PSE GLB NX pmd
0xffffffff82a00000-0xffffffff82a1e000         120K     ro             GLB NX pte
0xffffffff82a1e000-0xffffffff82c00000        1928K                           pte
0xffffffff82c00000-0xffffffff82e00000           2M     RW         PSE GLB NX pmd
0xffffffff82e00000-0xffffffff82e53000         332K     RW             GLB NX pte
0xffffffff82e53000-0xffffffff83000000        1716K                           pte
0xffffffff83000000-0xffffffff83200000           2M                           pmd
0xffffffff83200000-0xffffffff83214000          80K                           pte
0xffffffff83214000-0xffffffff83400000        1968K     RW             GLB NX pte
0xffffffff83400000-0xffffffff84200000          14M     RW         PSE GLB NX pmd
0xffffffff84200000-0xffffffff84384000        1552K     RW             GLB NX pte
0xffffffff84384000-0xffffffff84400000         496K                           pte
0xffffffff84400000-0xffffffffa0000000         444M                           pmd

So remove some range before rodata with RW+x.

-v4: adapt it to all_end change.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>

---
 arch/x86/mm/init_64.c |   62 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c
+++ linux-2.6/arch/x86/mm/init_64.c
@@ -1101,6 +1101,61 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_DEBUG_RODATA
+static void remove_highmap_2m(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud = (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr);
+	pmd_t *pmd = (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+
+	set_pmd(pmd, __pmd(0));
+}
+
+static void remove_highmap_2m_partial(unsigned long addr, unsigned long end)
+{
+	int i;
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud = (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr);
+	pmd_t *pmd = (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd) + pte_index(addr);
+
+	for (i = pte_index(addr); i < pte_index(end - 1) + 1; i++, pte++)
+		set_pte(pte, __pte(0));
+}
+
+static void cleanup_highmap_late(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+	unsigned long start_2m_aligned = roundup(start, PMD_SIZE);
+	unsigned long end_2m_aligned = rounddown(end, PMD_SIZE);
+
+	start = PFN_ALIGN(start);
+	end &= PAGE_MASK;
+
+	if (start >= end)
+		return;
+
+	if (start < start_2m_aligned) {
+		unsigned long tmp = min(start_2m_aligned, end);
+
+		set_memory_4k(start, (tmp - start) >> PAGE_SHIFT);
+		remove_highmap_2m_partial(start, tmp);
+	}
+
+	for (addr = start_2m_aligned; addr < end_2m_aligned; addr += PMD_SIZE)
+		remove_highmap_2m(addr);
+
+	if (start <= end_2m_aligned && end_2m_aligned < end) {
+		set_memory_4k(end_2m_aligned,
+				(end - end_2m_aligned) >> PAGE_SHIFT);
+		remove_highmap_2m_partial(end_2m_aligned, end);
+	}
+
+	subtract_range(pfn_highmapped, NR_RANGE,
+			__pa_symbol(start) >> PAGE_SHIFT,
+			__pa_symbol(end) >> PAGE_SHIFT);
+	nr_pfn_highmapped = clean_sort_range(pfn_highmapped, NR_RANGE);
+}
+
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
@@ -1149,6 +1204,7 @@ void mark_rodata_ro(void)
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
 	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
 	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
+	unsigned long data_start = PFN_ALIGN(&_sdata);
 	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
@@ -1172,6 +1228,12 @@ void mark_rodata_ro(void)
 	all_end = roundup(_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
+	cleanup_highmap_late(text_end, rodata_start);
+	cleanup_highmap_late(rodata_end, data_start);
+	cleanup_highmap_late(PFN_ALIGN(_brk_end), all_end);
+	cleanup_highmap_late((unsigned long)(&__init_begin),
+				(unsigned long)(&__init_end));
+
 	rodata_test();
 
 #ifdef CONFIG_CPA_DEBUG

Re: [PATCH 3/4] x86, 64bit: remove highmap for not needed ranges

[Yinghai Lu]

On Tue, Nov 18, 2014 at 5:44 PM, Yinghai Lu <yinghai@kernel.org> wrote:
> add cleanup_highmap_late to remove highmap for initmem, around rodata, and
> [_brk_end, all_end).

Sorry, title should be 3/3 instead of 3/4.

Thanks

Yinghai