lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220223052223.1202152-7-junaids@google.com>
Date:   Tue, 22 Feb 2022 21:21:42 -0800
From:   Junaid Shahid <junaids@...gle.com>
To:     linux-kernel@...r.kernel.org
Cc:     kvm@...r.kernel.org, pbonzini@...hat.com, jmattson@...gle.com,
        pjt@...gle.com, oweisse@...gle.com, alexandre.chartre@...cle.com,
        rppt@...ux.ibm.com, dave.hansen@...ux.intel.com,
        peterz@...radead.org, tglx@...utronix.de, luto@...nel.org,
        linux-mm@...ck.org
Subject: [RFC PATCH 06/47] mm: asi: ASI page table allocation and free functions

This adds custom allocation and free functions for ASI page tables.

The alloc functions support allocating memory using different GFP
reclaim flags, in order to be able to support non-sensitive allocations
from both standard and atomic contexts. They also install the page
tables locklessly, which makes it slightly simpler to handle
non-sensitive allocations from interrupts/exceptions.

The free functions recursively free the page tables when the ASI
instance is being torn down.

Signed-off-by: Junaid Shahid <junaids@...gle.com>


---
 arch/x86/mm/asi.c       | 109 +++++++++++++++++++++++++++++++++++++++-
 include/linux/pgtable.h |   3 ++
 2 files changed, 111 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/asi.c b/arch/x86/mm/asi.c
index 2453124f221d..40d772b2e2a8 100644
--- a/arch/x86/mm/asi.c
+++ b/arch/x86/mm/asi.c
@@ -60,6 +60,113 @@ void asi_unregister_class(int index)
 }
 EXPORT_SYMBOL_GPL(asi_unregister_class);
 
+#ifndef mm_inc_nr_p4ds
+#define mm_inc_nr_p4ds(mm)	do {} while (false)
+#endif
+
+#ifndef mm_dec_nr_p4ds
+#define mm_dec_nr_p4ds(mm)	do {} while (false)
+#endif
+
+#define pte_offset		pte_offset_kernel
+
+#define DEFINE_ASI_PGTBL_ALLOC(base, level)				\
+static level##_t * asi_##level##_alloc(struct asi *asi,			\
+				       base##_t *base, ulong addr,	\
+				       gfp_t flags)			\
+{									\
+	if (unlikely(base##_none(*base))) {				\
+		ulong pgtbl = get_zeroed_page(flags);			\
+		phys_addr_t pgtbl_pa;					\
+									\
+		if (pgtbl == 0)						\
+			return NULL;					\
+									\
+		pgtbl_pa = __pa(pgtbl);					\
+		paravirt_alloc_##level(asi->mm, PHYS_PFN(pgtbl_pa));	\
+									\
+		if (cmpxchg((ulong *)base, 0,				\
+			    pgtbl_pa | _PAGE_TABLE) == 0) {		\
+			mm_inc_nr_##level##s(asi->mm);			\
+		} else {						\
+			paravirt_release_##level(PHYS_PFN(pgtbl_pa));	\
+			free_page(pgtbl);				\
+		}							\
+									\
+		/* NOP on native. PV call on Xen. */			\
+		set_##base(base, *base);				\
+	}								\
+	VM_BUG_ON(base##_large(*base));					\
+	return level##_offset(base, addr);				\
+}
+
+DEFINE_ASI_PGTBL_ALLOC(pgd, p4d)
+DEFINE_ASI_PGTBL_ALLOC(p4d, pud)
+DEFINE_ASI_PGTBL_ALLOC(pud, pmd)
+DEFINE_ASI_PGTBL_ALLOC(pmd, pte)
+
+#define asi_free_dummy(asi, addr)
+#define __pmd_free(mm, pmd) free_page((ulong)(pmd))
+#define pud_page_vaddr(pud) ((ulong)pud_pgtable(pud))
+#define p4d_page_vaddr(p4d) ((ulong)p4d_pgtable(p4d))
+
+static inline unsigned long pte_page_vaddr(pte_t pte)
+{
+	return (unsigned long)__va(pte_val(pte) & PTE_PFN_MASK);
+}
+
+#define DEFINE_ASI_PGTBL_FREE(level, LEVEL, next, free)			\
+static void asi_free_##level(struct asi *asi, ulong pgtbl_addr)		\
+{									\
+	uint i;								\
+	level##_t *level = (level##_t *)pgtbl_addr;			\
+									\
+	for (i = 0; i < PTRS_PER_##LEVEL; i++) {			\
+		ulong vaddr;						\
+									\
+		if (level##_none(level[i]))				\
+			continue;					\
+									\
+		vaddr = level##_page_vaddr(level[i]);			\
+									\
+		if (!level##_leaf(level[i]))				\
+			asi_free_##next(asi, vaddr);			\
+		else							\
+			VM_WARN(true, "Lingering mapping in ASI %p at %lx",\
+				asi, vaddr);				\
+	}								\
+	paravirt_release_##level(PHYS_PFN(__pa(pgtbl_addr)));		\
+	free(asi->mm, level);						\
+	mm_dec_nr_##level##s(asi->mm);					\
+}
+
+DEFINE_ASI_PGTBL_FREE(pte, PTE, dummy, pte_free_kernel)
+DEFINE_ASI_PGTBL_FREE(pmd, PMD, pte, __pmd_free)
+DEFINE_ASI_PGTBL_FREE(pud, PUD, pmd, pud_free)
+DEFINE_ASI_PGTBL_FREE(p4d, P4D, pud, p4d_free)
+
+static void asi_free_pgd_range(struct asi *asi, uint start, uint end)
+{
+	uint i;
+
+	for (i = start; i < end; i++)
+		if (pgd_present(asi->pgd[i]))
+			asi_free_p4d(asi, (ulong)p4d_offset(asi->pgd + i, 0));
+}
+
+/*
+ * Free the page tables allocated for the given ASI instance.
+ * The caller must ensure that all the mappings have already been cleared
+ * and appropriate TLB flushes have been issued before calling this function.
+ */
+static void asi_free_pgd(struct asi *asi)
+{
+	VM_BUG_ON(asi->mm == &init_mm);
+
+	asi_free_pgd_range(asi, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD);
+	free_pages((ulong)asi->pgd, PGD_ALLOCATION_ORDER);
+}
+
 static int __init set_asi_param(char *str)
 {
 	if (strcmp(str, "on") == 0)
@@ -102,7 +209,7 @@ void asi_destroy(struct asi *asi)
 	if (!boot_cpu_has(X86_FEATURE_ASI))
 		return;
 
-	free_pages((ulong)asi->pgd, PGD_ALLOCATION_ORDER);
+	asi_free_pgd(asi);
 	memset(asi, 0, sizeof(struct asi));
 }
 EXPORT_SYMBOL_GPL(asi_destroy);
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e24d2c992b11..2fff17a939f0 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1593,6 +1593,9 @@ typedef unsigned int pgtbl_mod_mask;
 #ifndef pmd_leaf
 #define pmd_leaf(x)	0
 #endif
+#ifndef pte_leaf
+#define pte_leaf(x)	1
+#endif
 
 #ifndef pgd_leaf_size
 #define pgd_leaf_size(x) (1ULL << PGDIR_SHIFT)
-- 
2.35.1.473.g83b2b277ed-goog

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ