Commit 672c0ae0 authored by Jan Beulich's avatar Jan Beulich Committed by Ingo Molnar
Browse files

x86/mm: Consider effective protection attributes in W+X check 



Using just the leaf page table entry flags would cause a false warning
in case _PAGE_RW is clear or _PAGE_NX is set in a higher level entry.
Hand through both the current entry's flags as well as the accumulated
effective value (the latter as pgprotval_t instead of pgprot_t, as it's
not an actual entry's value).

This in particular eliminates the false W+X warning when running under
Xen, as commit:

  2cc42bac ("x86-64/Xen: eliminate W+X mappings")

had to make the necessary adjustment in L2 rather than L1 (the reason is
explained there). I.e. _PAGE_RW is clear there in L1, but _PAGE_NX is
set in L2.

Signed-off-by: default avatarJan Beulich <jbeulich@suse.com>
Reviewed-by: default avatarJuergen Gross <jgross@suse.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/5A8FDE8902000078001AABBB@prv-mh.provo.novell.com


Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
parent c46dacb7

arch/x86/mm/dump_pagetables.c

+58 −36
Original line number Diff line number Diff line
@@ -29,6 +29,7 @@ 
struct pg_state {

	int level;

	pgprot_t current_prot;

	pgprotval_t effective_prot;

	unsigned long start_address;

	unsigned long current_address;

	const struct addr_marker *marker;
@@ -235,9 +236,9 @@ static unsigned long normalize_addr(unsigned long u) 
 * print what we collected so far.

 */

static void note_page(struct seq_file *m, struct pg_state *st,

		      pgprot_t new_prot, int level)

		      pgprot_t new_prot, pgprotval_t new_eff, int level)

{

	pgprotval_t prot, cur;

	pgprotval_t prot, cur, eff;

	static const char units[] = "BKMGTPE";



	/*
@@ -247,23 +248,24 @@ static void note_page(struct seq_file *m, struct pg_state *st, 
	 */

	prot = pgprot_val(new_prot);

	cur = pgprot_val(st->current_prot);

	eff = st->effective_prot;



	if (!st->level) {

		/* First entry */

		st->current_prot = new_prot;

		st->effective_prot = new_eff;

		st->level = level;

		st->marker = address_markers;

		st->lines = 0;

		pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",

				   st->marker->name);

	} else if (prot != cur || level != st->level ||

	} else if (prot != cur || new_eff != eff || level != st->level ||

		   st->current_address >= st->marker[1].start_address) {

		const char *unit = units;

		unsigned long delta;

		int width = sizeof(unsigned long) * 2;

		pgprotval_t pr = pgprot_val(st->current_prot);



		if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) {

		if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX)) {

			WARN_ONCE(1,

				  "x86/mm: Found insecure W+X mapping at address %p/%pS\n",

				  (void *)st->start_address,
@@ -317,21 +319,30 @@ static void note_page(struct seq_file *m, struct pg_state *st, 


		st->start_address = st->current_address;

		st->current_prot = new_prot;

		st->effective_prot = new_eff;

		st->level = level;

	}

}



static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, unsigned long P)

static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)

{

	return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |

	       ((prot1 | prot2) & _PAGE_NX);

}



static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,

			   pgprotval_t eff_in, unsigned long P)

{

	int i;

	pte_t *start;

	pgprotval_t prot;

	pgprotval_t prot, eff;



	start = (pte_t *)pmd_page_vaddr(addr);

	for (i = 0; i < PTRS_PER_PTE; i++) {

		prot = pte_flags(*start);

		eff = effective_prot(eff_in, prot);

		st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);

		note_page(m, st, __pgprot(prot), 5);

		note_page(m, st, __pgprot(prot), eff, 5);

		start++;

	}

}
@@ -351,7 +362,7 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, 
	    (pgtable_l5_enabled && __pa(pt) == __pa(kasan_zero_p4d)) ||

	    __pa(pt) == __pa(kasan_zero_pud)) {

		pgprotval_t prot = pte_flags(kasan_zero_pte[0]);

		note_page(m, st, __pgprot(prot), 5);

		note_page(m, st, __pgprot(prot), 0, 5);

		return true;

	}

	return false;
@@ -366,42 +377,45 @@ static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st, 


#if PTRS_PER_PMD > 1



static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, unsigned long P)

static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,

			   pgprotval_t eff_in, unsigned long P)

{

	int i;

	pmd_t *start, *pmd_start;

	pgprotval_t prot;

	pgprotval_t prot, eff;



	pmd_start = start = (pmd_t *)pud_page_vaddr(addr);

	for (i = 0; i < PTRS_PER_PMD; i++) {

		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);

		if (!pmd_none(*start)) {

			if (pmd_large(*start) || !pmd_present(*start)) {

			prot = pmd_flags(*start);

				note_page(m, st, __pgprot(prot), 4);

			eff = effective_prot(eff_in, prot);

			if (pmd_large(*start) || !pmd_present(*start)) {

				note_page(m, st, __pgprot(prot), eff, 4);

			} else if (!kasan_page_table(m, st, pmd_start)) {

				walk_pte_level(m, st, *start,

				walk_pte_level(m, st, *start, eff,

					       P + i * PMD_LEVEL_MULT);

			}

		} else

			note_page(m, st, __pgprot(0), 4);

			note_page(m, st, __pgprot(0), 0, 4);

		start++;

	}

}



#else

#define walk_pmd_level(m,s,a,p) walk_pte_level(m,s,__pmd(pud_val(a)),p)

#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p)

#define pud_large(a) pmd_large(__pmd(pud_val(a)))

#define pud_none(a)  pmd_none(__pmd(pud_val(a)))

#endif



#if PTRS_PER_PUD > 1



static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, unsigned long P)

static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,

			   pgprotval_t eff_in, unsigned long P)

{

	int i;

	pud_t *start, *pud_start;

	pgprotval_t prot;

	pgprotval_t prot, eff;

	pud_t *prev_pud = NULL;



	pud_start = start = (pud_t *)p4d_page_vaddr(addr);
@@ -409,15 +423,16 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, 
	for (i = 0; i < PTRS_PER_PUD; i++) {

		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);

		if (!pud_none(*start)) {

			if (pud_large(*start) || !pud_present(*start)) {

			prot = pud_flags(*start);

				note_page(m, st, __pgprot(prot), 3);

			eff = effective_prot(eff_in, prot);

			if (pud_large(*start) || !pud_present(*start)) {

				note_page(m, st, __pgprot(prot), eff, 3);

			} else if (!kasan_page_table(m, st, pud_start)) {

				walk_pmd_level(m, st, *start,

				walk_pmd_level(m, st, *start, eff,

					       P + i * PUD_LEVEL_MULT);

			}

		} else

			note_page(m, st, __pgprot(0), 3);

			note_page(m, st, __pgprot(0), 0, 3);



		prev_pud = start;

		start++;
@@ -425,34 +440,36 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr, 
}



#else

#define walk_pud_level(m,s,a,p) walk_pmd_level(m,s,__pud(p4d_val(a)),p)

#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p)

#define p4d_large(a) pud_large(__pud(p4d_val(a)))

#define p4d_none(a)  pud_none(__pud(p4d_val(a)))

#endif



static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr, unsigned long P)

static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,

			   pgprotval_t eff_in, unsigned long P)

{

	int i;

	p4d_t *start, *p4d_start;

	pgprotval_t prot;

	pgprotval_t prot, eff;



	if (PTRS_PER_P4D == 1)

		return walk_pud_level(m, st, __p4d(pgd_val(addr)), P);

		return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P);



	p4d_start = start = (p4d_t *)pgd_page_vaddr(addr);



	for (i = 0; i < PTRS_PER_P4D; i++) {

		st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);

		if (!p4d_none(*start)) {

			if (p4d_large(*start) || !p4d_present(*start)) {

			prot = p4d_flags(*start);

				note_page(m, st, __pgprot(prot), 2);

			eff = effective_prot(eff_in, prot);

			if (p4d_large(*start) || !p4d_present(*start)) {

				note_page(m, st, __pgprot(prot), eff, 2);

			} else if (!kasan_page_table(m, st, p4d_start)) {

				walk_pud_level(m, st, *start,

				walk_pud_level(m, st, *start, eff,

					       P + i * P4D_LEVEL_MULT);

			}

		} else

			note_page(m, st, __pgprot(0), 2);

			note_page(m, st, __pgprot(0), 0, 2);



		start++;

	}
@@ -483,7 +500,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, 
#else

	pgd_t *start = swapper_pg_dir;

#endif

	pgprotval_t prot;

	pgprotval_t prot, eff;

	int i;

	struct pg_state st = {};
@@ -499,15 +516,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, 
	for (i = 0; i < PTRS_PER_PGD; i++) {

		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);

		if (!pgd_none(*start) && !is_hypervisor_range(i)) {

			if (pgd_large(*start) || !pgd_present(*start)) {

			prot = pgd_flags(*start);

				note_page(m, &st, __pgprot(prot), 1);

#ifdef CONFIG_X86_PAE

			eff = _PAGE_USER | _PAGE_RW;

#else

			eff = prot;

#endif

			if (pgd_large(*start) || !pgd_present(*start)) {

				note_page(m, &st, __pgprot(prot), eff, 1);

			} else {

				walk_p4d_level(m, &st, *start,

				walk_p4d_level(m, &st, *start, eff,

					       i * PGD_LEVEL_MULT);

			}

		} else

			note_page(m, &st, __pgprot(0), 1);

			note_page(m, &st, __pgprot(0), 0, 1);



		cond_resched();

		start++;
@@ -515,7 +537,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, 


	/* Flush out the last page */

	st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);

	note_page(m, &st, __pgprot(0), 0);

	note_page(m, &st, __pgprot(0), 0, 0);

	if (!checkwx)

		return;

	if (st.wx_pages)

CRA Git | Maintained and supported by SUSTech CRA and CCSE