| 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
| ||
|
Message-Id: <20251218194750.395301-2-yeoreum.yun@arm.com>
Date: Thu, 18 Dec 2025 19:47:49 +0000
From: Yeoreum Yun <yeoreum.yun@....com>
To: catalin.marinas@....com,
will@...nel.org,
ryan.roberts@....com,
akpm@...ux-foundation.org,
david@...nel.org,
kevin.brodsky@....com,
quic_zhenhuah@...cinc.com,
dev.jain@....com,
yang@...amperecomputing.com,
chaitanyas.prakash@....com,
bigeasy@...utronix.de,
clrkwllms@...nel.org,
rostedt@...dmis.org,
lorenzo.stoakes@...cle.com,
ardb@...nel.org,
jackmanb@...gle.com,
vbabka@...e.cz,
mhocko@...e.com
Cc: linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org,
linux-rt-devel@...ts.linux.dev,
Yeoreum Yun <yeoreum.yun@....com>
Subject: [PATCH v3 1/2] arm64: mmu: avoid allocating pages while splitting the linear mapping
linear_map_split_to_ptes() currently allocates page tables while
splitting the linear mapping into PTEs under stop_machine() using GFP_ATOMIC.
This is fine for non-PREEMPT_RT configurations.
However, it becomes problematic on PREEMPT_RT, because
generic memory allocation/free APIs (e.g. pgtable_alloc(), __get_free_pages(), etc.)
cannot be called from a non-preemptible context, except for the _nolock() variants.
This is because generic memory allocation/free paths are sleepable,
as they rely on spin_lock(), which becomes sleepable on PREEMPT_RT.
In other words, even calling pgtable_alloc() with GFP_ATOMIC is not permitted
in __linear_map_split_to_pte() when it is executed by the stopper thread,
where preemption is disabled on PREEMPT_RT.
To address this, the required number of page tables is first collected
and preallocated, and the preallocated page tables are then used
when splitting the linear mapping in __linear_map_split_to_pte().
Fixes: 3df6979d222b ("arm64: mm: split linear mapping if BBML2 unsupported on secondary CPUs")
Signed-off-by: Yeoreum Yun <yeoreum.yun@....com>
---
arch/arm64/mm/mmu.c | 232 +++++++++++++++++++++++++++++++++++---------
1 file changed, 184 insertions(+), 48 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 9ae7ce00a7ef..96a9fa505e71 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -527,18 +527,15 @@ static void early_create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
panic("Failed to create page tables\n");
}
-static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp,
- enum pgtable_type pgtable_type)
-{
- /* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
- struct ptdesc *ptdesc = pagetable_alloc(gfp & ~__GFP_ZERO, 0);
- phys_addr_t pa;
-
- if (!ptdesc)
- return INVALID_PHYS_ADDR;
-
- pa = page_to_phys(ptdesc_page(ptdesc));
+static struct ptdesc **split_pgtables;
+static int split_pgtables_order;
+static unsigned long split_pgtables_count;
+static unsigned long split_pgtables_idx;
+static __always_inline void __pgd_pgtable_init(struct mm_struct *mm,
+ struct ptdesc *ptdesc,
+ enum pgtable_type pgtable_type)
+{
switch (pgtable_type) {
case TABLE_PTE:
BUG_ON(!pagetable_pte_ctor(mm, ptdesc));
@@ -554,19 +551,28 @@ static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp,
break;
}
- return pa;
}
-static phys_addr_t
-pgd_pgtable_alloc_init_mm_gfp(enum pgtable_type pgtable_type, gfp_t gfp)
+static phys_addr_t __pgd_pgtable_alloc(struct mm_struct *mm, gfp_t gfp,
+ enum pgtable_type pgtable_type)
{
- return __pgd_pgtable_alloc(&init_mm, gfp, pgtable_type);
+ /* Page is zeroed by init_clear_pgtable() so don't duplicate effort. */
+ struct ptdesc *ptdesc = pagetable_alloc(gfp & ~__GFP_ZERO, 0);
+
+ if (!ptdesc)
+ return INVALID_PHYS_ADDR;
+
+ __pgd_pgtable_init(mm, ptdesc, pgtable_type);
+
+ return page_to_phys(ptdesc_page(ptdesc));
}
+typedef phys_addr_t (split_pgtable_alloc_fn)(enum pgtable_type);
+
static phys_addr_t __maybe_unused
pgd_pgtable_alloc_init_mm(enum pgtable_type pgtable_type)
{
- return pgd_pgtable_alloc_init_mm_gfp(pgtable_type, GFP_PGTABLE_KERNEL);
+ return __pgd_pgtable_alloc(&init_mm, GFP_PGTABLE_KERNEL, pgtable_type);
}
static phys_addr_t
@@ -575,6 +581,23 @@ pgd_pgtable_alloc_special_mm(enum pgtable_type pgtable_type)
return __pgd_pgtable_alloc(NULL, GFP_PGTABLE_KERNEL, pgtable_type);
}
+static phys_addr_t
+pgd_pgtable_get_preallocated(enum pgtable_type pgtable_type)
+{
+ struct ptdesc *ptdesc;
+
+ if (WARN_ON(split_pgtables_idx >= split_pgtables_count))
+ return INVALID_PHYS_ADDR;
+
+ ptdesc = split_pgtables[split_pgtables_idx++];
+ if (!ptdesc)
+ return INVALID_PHYS_ADDR;
+
+ __pgd_pgtable_init(&init_mm, ptdesc, pgtable_type);
+
+ return page_to_phys(ptdesc_page(ptdesc));
+}
+
static void split_contpte(pte_t *ptep)
{
int i;
@@ -584,7 +607,9 @@ static void split_contpte(pte_t *ptep)
__set_pte(ptep, pte_mknoncont(__ptep_get(ptep)));
}
-static int split_pmd(pmd_t *pmdp, pmd_t pmd, gfp_t gfp, bool to_cont)
+static int split_pmd(pmd_t *pmdp, pmd_t pmd,
+ split_pgtable_alloc_fn *pgtable_alloc_fn,
+ bool to_cont)
{
pmdval_t tableprot = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
unsigned long pfn = pmd_pfn(pmd);
@@ -593,7 +618,7 @@ static int split_pmd(pmd_t *pmdp, pmd_t pmd, gfp_t gfp, bool to_cont)
pte_t *ptep;
int i;
- pte_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PTE, gfp);
+ pte_phys = pgtable_alloc_fn(TABLE_PTE);
if (pte_phys == INVALID_PHYS_ADDR)
return -ENOMEM;
ptep = (pte_t *)phys_to_virt(pte_phys);
@@ -628,7 +653,9 @@ static void split_contpmd(pmd_t *pmdp)
set_pmd(pmdp, pmd_mknoncont(pmdp_get(pmdp)));
}
-static int split_pud(pud_t *pudp, pud_t pud, gfp_t gfp, bool to_cont)
+static int split_pud(pud_t *pudp, pud_t pud,
+ split_pgtable_alloc_fn *pgtable_alloc_fn,
+ bool to_cont)
{
pudval_t tableprot = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
unsigned int step = PMD_SIZE >> PAGE_SHIFT;
@@ -638,7 +665,7 @@ static int split_pud(pud_t *pudp, pud_t pud, gfp_t gfp, bool to_cont)
pmd_t *pmdp;
int i;
- pmd_phys = pgd_pgtable_alloc_init_mm_gfp(TABLE_PMD, gfp);
+ pmd_phys = pgtable_alloc_fn(TABLE_PMD);
if (pmd_phys == INVALID_PHYS_ADDR)
return -ENOMEM;
pmdp = (pmd_t *)phys_to_virt(pmd_phys);
@@ -707,7 +734,7 @@ static int split_kernel_leaf_mapping_locked(unsigned long addr)
if (!pud_present(pud))
goto out;
if (pud_leaf(pud)) {
- ret = split_pud(pudp, pud, GFP_PGTABLE_KERNEL, true);
+ ret = split_pud(pudp, pud, pgd_pgtable_alloc_init_mm, true);
if (ret)
goto out;
}
@@ -732,7 +759,7 @@ static int split_kernel_leaf_mapping_locked(unsigned long addr)
*/
if (ALIGN_DOWN(addr, PMD_SIZE) == addr)
goto out;
- ret = split_pmd(pmdp, pmd, GFP_PGTABLE_KERNEL, true);
+ ret = split_pmd(pmdp, pmd, pgd_pgtable_alloc_init_mm, true);
if (ret)
goto out;
}
@@ -831,34 +858,35 @@ int split_kernel_leaf_mapping(unsigned long start, unsigned long end)
static int split_to_ptes_pud_entry(pud_t *pudp, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
- gfp_t gfp = *(gfp_t *)walk->private;
+ split_pgtable_alloc_fn *pgtable_alloc_fn = walk->private;
pud_t pud = pudp_get(pudp);
- int ret = 0;
- if (pud_leaf(pud))
- ret = split_pud(pudp, pud, gfp, false);
+ if (!pud_leaf(pud))
+ return 0;
- return ret;
+ return split_pud(pudp, pud, pgtable_alloc_fn, false);
}
static int split_to_ptes_pmd_entry(pmd_t *pmdp, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
- gfp_t gfp = *(gfp_t *)walk->private;
+ split_pgtable_alloc_fn *pgtable_alloc_fn = walk->private;
pmd_t pmd = pmdp_get(pmdp);
- int ret = 0;
+ int ret;
- if (pmd_leaf(pmd)) {
- if (pmd_cont(pmd))
- split_contpmd(pmdp);
- ret = split_pmd(pmdp, pmd, gfp, false);
+ if (!pmd_leaf(pmd))
+ return 0;
- /*
- * We have split the pmd directly to ptes so there is no need to
- * visit each pte to check if they are contpte.
- */
- walk->action = ACTION_CONTINUE;
- }
+ if (pmd_cont(pmd))
+ split_contpmd(pmdp);
+
+ ret = split_pmd(pmdp, pmd, pgtable_alloc_fn, false);
+
+ /*
+ * We have split the pmd directly to ptes so there is no need to
+ * visit each pte to check if they are contpte.
+ */
+ walk->action = ACTION_CONTINUE;
return ret;
}
@@ -880,13 +908,15 @@ static const struct mm_walk_ops split_to_ptes_ops = {
.pte_entry = split_to_ptes_pte_entry,
};
-static int range_split_to_ptes(unsigned long start, unsigned long end, gfp_t gfp)
+static int range_split_to_ptes(unsigned long start, unsigned long end,
+ split_pgtable_alloc_fn *pgtable_alloc_fn)
{
int ret;
arch_enter_lazy_mmu_mode();
ret = walk_kernel_page_table_range_lockless(start, end,
- &split_to_ptes_ops, NULL, &gfp);
+ &split_to_ptes_ops, NULL,
+ pgtable_alloc_fn);
arch_leave_lazy_mmu_mode();
return ret;
@@ -903,6 +933,105 @@ static void __init init_idmap_kpti_bbml2_flag(void)
smp_mb();
}
+static int __init
+collect_to_split_pud_entry(pud_t *pudp, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pud_t pud = pudp_get(pudp);
+
+ if (pud_leaf(pud))
+ split_pgtables_count += 1 + PTRS_PER_PMD;
+
+ return 0;
+}
+
+static int __init
+collect_to_split_pmd_entry(pmd_t *pmdp, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pmd_t pmd = pmdp_get(pmdp);
+
+ if (pmd_leaf(pmd))
+ split_pgtables_count++;
+
+ walk->action = ACTION_CONTINUE;
+
+ return 0;
+}
+
+static void __init linear_map_free_split_pgtables(void)
+{
+ int i;
+
+ if (!split_pgtables_count || !split_pgtables)
+ goto skip_free;
+
+ for (i = split_pgtables_idx; i < split_pgtables_count; i++) {
+ if (split_pgtables[i])
+ pagetable_free(split_pgtables[i]);
+ }
+
+ free_pages((unsigned long)split_pgtables, split_pgtables_order);
+
+skip_free:
+ split_pgtables = NULL;
+ split_pgtables_count = 0;
+ split_pgtables_idx = 0;
+ split_pgtables_order = 0;
+}
+
+static int __init linear_map_prealloc_split_pgtables(void)
+{
+ int ret, i;
+ unsigned long lstart = _PAGE_OFFSET(vabits_actual);
+ unsigned long lend = PAGE_END;
+ unsigned long kstart = (unsigned long)lm_alias(_stext);
+ unsigned long kend = (unsigned long)lm_alias(__init_begin);
+
+ const struct mm_walk_ops collect_to_split_ops = {
+ .pud_entry = collect_to_split_pud_entry,
+ .pmd_entry = collect_to_split_pmd_entry
+ };
+
+ split_pgtables_idx = 0;
+ split_pgtables_count = 0;
+
+ ret = walk_kernel_page_table_range_lockless(lstart, kstart,
+ &collect_to_split_ops,
+ NULL, NULL);
+ if (!ret)
+ ret = walk_kernel_page_table_range_lockless(kend, lend,
+ &collect_to_split_ops,
+ NULL, NULL);
+ if (ret || !split_pgtables_count)
+ goto error;
+
+ ret = -ENOMEM;
+
+ split_pgtables_order =
+ order_base_2(PAGE_ALIGN(split_pgtables_count *
+ sizeof(struct ptdesc *)) >> PAGE_SHIFT);
+
+ split_pgtables = (struct ptdesc **) __get_free_pages(GFP_KERNEL | __GFP_ZERO,
+ split_pgtables_order);
+ if (!split_pgtables)
+ goto error;
+
+ for (i = 0; i < split_pgtables_count; i++) {
+ split_pgtables[i] = pagetable_alloc(GFP_KERNEL, 0);
+ if (!split_pgtables[i])
+ goto error;
+ }
+
+ ret = 0;
+
+error:
+ if (ret)
+ linear_map_free_split_pgtables();
+
+ return ret;
+}
+
static int __init linear_map_split_to_ptes(void *__unused)
{
/*
@@ -928,9 +1057,9 @@ static int __init linear_map_split_to_ptes(void *__unused)
* PTE. The kernel alias remains static throughout runtime so
* can continue to be safely mapped with large mappings.
*/
- ret = range_split_to_ptes(lstart, kstart, GFP_ATOMIC);
+ ret = range_split_to_ptes(lstart, kstart, pgd_pgtable_get_preallocated);
if (!ret)
- ret = range_split_to_ptes(kend, lend, GFP_ATOMIC);
+ ret = range_split_to_ptes(kend, lend, pgd_pgtable_get_preallocated);
if (ret)
panic("Failed to split linear map\n");
flush_tlb_kernel_range(lstart, lend);
@@ -963,10 +1092,16 @@ static int __init linear_map_split_to_ptes(void *__unused)
void __init linear_map_maybe_split_to_ptes(void)
{
- if (linear_map_requires_bbml2 && !system_supports_bbml2_noabort()) {
- init_idmap_kpti_bbml2_flag();
- stop_machine(linear_map_split_to_ptes, NULL, cpu_online_mask);
- }
+ if (!linear_map_requires_bbml2 || system_supports_bbml2_noabort())
+ return;
+
+ if (linear_map_prealloc_split_pgtables())
+ panic("Failed to split linear map\n");
+
+ init_idmap_kpti_bbml2_flag();
+ stop_machine(linear_map_split_to_ptes, NULL, cpu_online_mask);
+
+ linear_map_free_split_pgtables();
}
/*
@@ -1088,6 +1223,7 @@ bool arch_kfence_init_pool(void)
unsigned long end = start + KFENCE_POOL_SIZE;
int ret;
+
/* Exit early if we know the linear map is already pte-mapped. */
if (!split_leaf_mapping_possible())
return true;
@@ -1097,7 +1233,7 @@ bool arch_kfence_init_pool(void)
return true;
mutex_lock(&pgtable_split_lock);
- ret = range_split_to_ptes(start, end, GFP_PGTABLE_KERNEL);
+ ret = range_split_to_ptes(start, end, pgd_pgtable_alloc_init_mm);
mutex_unlock(&pgtable_split_lock);
/*
--
LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7}
Powered by blists - more mailing lists