[PATCH OLK-6.6 147/717] x86/pat: Fix W^X violation false-positives when running as Xen PV guest

From: Juergen Gross jgross@suse.com

stable inclusion from stable-v6.6.33 commit edcdeb8a4fdf3bd1ea44b079bfa1a5f11a8a1d86 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAD6H2

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

[ Upstream commit 5bc8b0f5dac04cd4ebe47f8090a5942f2f2647ef ]

When running as Xen PV guest in some cases W^X violation WARN()s have been observed. Those WARN()s are produced by verify_rwx(), which looks into the PTE to verify that writable kernel pages have the NX bit set in order to avoid code modifications of the kernel by rogue code.

As the NX bits of all levels of translation entries are or-ed and the RW bits of all levels are and-ed, looking just into the PTE isn't enough for the decision that a writable page is executable, too.

When running as a Xen PV guest, the direct map PMDs and kernel high map PMDs share the same set of PTEs. Xen kernel initialization will set the NX bit in the direct map PMD entries, and not the shared PTEs.

Fixes: 652c5bf380ad ("x86/mm: Refuse W^X violations") Reported-by: Jason Andryuk jandryuk@gmail.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lore.kernel.org/r/20240412151258.9171-5-jgross@suse.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Wang Hai wanghai38@huawei.com --- arch/x86/mm/pat/set_memory.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index a2dd773b1cd2..2d850f6bae70 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -619,7 +619,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start, * Validate strict W^X semantics. */ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start, - unsigned long pfn, unsigned long npg) + unsigned long pfn, unsigned long npg, + bool nx, bool rw) { unsigned long end;

@@ -641,6 +642,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW) return new;

+ /* Non-leaf translation entries can disable writing or execution. */ + if (!rw || nx) + return new; + end = start + npg * PAGE_SIZE - 1; WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n", (unsigned long long)pgprot_val(old), @@ -742,7 +747,7 @@ pte_t *lookup_address(unsigned long address, unsigned int *level) EXPORT_SYMBOL_GPL(lookup_address);

static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, - unsigned int *level) + unsigned int *level, bool *nx, bool *rw) { pgd_t *pgd;

@@ -751,7 +756,7 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address, else pgd = cpa->pgd + pgd_index(address);

- return lookup_address_in_pgd(pgd, address, level); + return lookup_address_in_pgd_attr(pgd, address, level, nx, rw); }

/* @@ -875,12 +880,13 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, pgprot_t old_prot, new_prot, req_prot, chk_prot; pte_t new_pte, *tmp; enum pg_level level; + bool nx, rw;

/* * Check for races, another CPU might have split this page * up already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) return 1;

@@ -991,7 +997,8 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address, new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages, psize, CPA_DETECT);

- new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages); + new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages, + nx, rw);

/* * If there is a conflict, split the large page. @@ -1072,6 +1079,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, pte_t *pbase = (pte_t *)page_address(base); unsigned int i, level; pgprot_t ref_prot; + bool nx, rw; pte_t *tmp;

spin_lock(&pgd_lock); @@ -1079,7 +1087,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, * Check for races, another CPU might have split this page * up for us already: */ - tmp = _lookup_address_cpa(cpa, address, &level); + tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (tmp != kpte) { spin_unlock(&pgd_lock); return 1; @@ -1620,10 +1628,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) int do_split, err; unsigned int level; pte_t *kpte, old_pte; + bool nx, rw;

address = __cpa_addr(cpa, cpa->curpage); repeat: - kpte = _lookup_address_cpa(cpa, address, &level); + kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw); if (!kpte) return __cpa_process_fault(cpa, address, primary);

@@ -1645,7 +1654,8 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) new_prot = static_protections(new_prot, address, pfn, 1, 0, CPA_PROTECT);

- new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1); + new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1, + nx, rw);

new_prot = pgprot_clear_protnone_bits(new_prot);