| 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
| ||
|
Date: Wed, 22 Jul 2020 11:45:55 +0200
From: David Hildenbrand <david@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: linux-s390@...r.kernel.org, linux-mm@...ck.org,
David Hildenbrand <david@...hat.com>,
Heiko Carstens <heiko.carstens@...ibm.com>,
Vasily Gorbik <gor@...ux.ibm.com>,
Christian Borntraeger <borntraeger@...ibm.com>,
Gerald Schaefer <gerald.schaefer@...ibm.com>
Subject: [PATCH v2 6/9] s390/vmem: cleanup empty page tables
Let's cleanup empty page tables. Consider only page tables that fully
fall into the idendity mapping and the vmemmap range.
As there are no valid accesses to vmem/vmemmap within non-populated ranges,
the single tlb flush at the end should be sufficient.
Cc: Heiko Carstens <heiko.carstens@...ibm.com>
Cc: Vasily Gorbik <gor@...ux.ibm.com>
Cc: Christian Borntraeger <borntraeger@...ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@...ibm.com>
Signed-off-by: David Hildenbrand <david@...hat.com>
---
arch/s390/mm/vmem.c | 102 +++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 101 insertions(+), 1 deletion(-)
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index a2b79681df69d..b831f9f9130aa 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -63,6 +63,15 @@ pte_t __ref *vmem_pte_alloc(void)
return pte;
}
+static void vmem_pte_free(unsigned long *table)
+{
+ /* We don't expect boot memory to be removed ever. */
+ if (!slab_is_available() ||
+ WARN_ON_ONCE(PageReserved(virt_to_page(table))))
+ return;
+ page_table_free(&init_mm, table);
+}
+
/* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */
static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr,
unsigned long end, bool add, bool direct)
@@ -105,6 +114,21 @@ static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr,
return ret;
}
+static void try_free_pte_table(pmd_t *pmd, unsigned long start)
+{
+ pte_t *pte;
+ int i;
+
+ /* We can safely assume this is fully in 1:1 mapping & vmemmap area */
+ pte = pte_offset_kernel(pmd, start);
+ for (i = 0; i < PTRS_PER_PTE; i++, pte++)
+ if (!pte_none(*pte))
+ return;
+
+ vmem_pte_free(__va(pmd_deref(*pmd)));
+ pmd_clear(pmd);
+}
+
/* __ref: we'll only call vmemmap_alloc_block() via vmemmap_populate() */
static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
unsigned long end, bool add, bool direct)
@@ -171,6 +195,8 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
ret = modify_pte_table(pmd, addr, next, add, direct);
if (ret)
goto out;
+ if (!add)
+ try_free_pte_table(pmd, addr & PMD_MASK);
}
ret = 0;
out:
@@ -179,6 +205,29 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
return ret;
}
+static void try_free_pmd_table(pud_t *pud, unsigned long start)
+{
+ const unsigned long end = start + PUD_SIZE;
+ pmd_t *pmd;
+ int i;
+
+ /* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+ if (end > VMALLOC_START)
+ return;
+#ifdef CONFIG_KASAN
+ if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+ return;
+#endif
+
+ pmd = pmd_offset(pud, start);
+ for (i = 0; i < PTRS_PER_PMD; i++, pmd++)
+ if (!pmd_none(*pmd))
+ return;
+
+ vmem_free_pages(pud_deref(*pud), CRST_ALLOC_ORDER);
+ pud_clear(pud);
+}
+
static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
bool add, bool direct)
{
@@ -225,6 +274,8 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
ret = modify_pmd_table(pud, addr, next, add, direct);
if (ret)
goto out;
+ if (!add)
+ try_free_pmd_table(pud, addr & PUD_MASK);
}
ret = 0;
out:
@@ -233,6 +284,29 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end,
return ret;
}
+static void try_free_pud_table(p4d_t *p4d, unsigned long start)
+{
+ const unsigned long end = start + P4D_SIZE;
+ pud_t *pud;
+ int i;
+
+ /* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+ if (end > VMALLOC_START)
+ return;
+#ifdef CONFIG_KASAN
+ if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+ return;
+#endif
+
+ pud = pud_offset(p4d, start);
+ for (i = 0; i < PTRS_PER_PUD; i++, pud++)
+ if (!pud_none(*pud))
+ return;
+
+ vmem_free_pages(p4d_deref(*p4d), CRST_ALLOC_ORDER);
+ p4d_clear(p4d);
+}
+
static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end,
bool add, bool direct)
{
@@ -257,12 +331,37 @@ static int modify_p4d_table(pgd_t *pgd, unsigned long addr, unsigned long end,
ret = modify_pud_table(p4d, addr, next, add, direct);
if (ret)
goto out;
+ if (!add)
+ try_free_pud_table(p4d, addr & P4D_MASK);
}
ret = 0;
out:
return ret;
}
+static void try_free_p4d_table(pgd_t *pgd, unsigned long start)
+{
+ const unsigned long end = start + PGDIR_SIZE;
+ p4d_t *p4d;
+ int i;
+
+ /* Don't mess with any tables not fully in 1:1 mapping & vmemmap area */
+ if (end > VMALLOC_START)
+ return;
+#ifdef CONFIG_KASAN
+ if (start < KASAN_SHADOW_END && KASAN_SHADOW_START > end)
+ return;
+#endif
+
+ p4d = p4d_offset(pgd, start);
+ for (i = 0; i < PTRS_PER_P4D; i++, p4d++)
+ if (!p4d_none(*p4d))
+ return;
+
+ vmem_free_pages(pgd_deref(*pgd), CRST_ALLOC_ORDER);
+ pgd_clear(pgd);
+}
+
static int modify_pagetable(unsigned long start, unsigned long end, bool add,
bool direct)
{
@@ -291,6 +390,8 @@ static int modify_pagetable(unsigned long start, unsigned long end, bool add,
ret = modify_p4d_table(pgd, addr, next, add, direct);
if (ret)
goto out;
+ if (!add)
+ try_free_p4d_table(pgd, addr & PGDIR_MASK);
}
ret = 0;
out:
@@ -319,7 +420,6 @@ static int vmem_add_range(unsigned long start, unsigned long size)
/*
* Remove a physical memory range from the 1:1 mapping.
- * Currently only invalidates page table entries.
*/
static void vmem_remove_range(unsigned long start, unsigned long size)
{
--
2.26.2
Powered by blists - more mailing lists