From: "Mike Rapoport (IBM)" <rppt@kernel.org>
Using large pages to map text areas reduces iTLB pressure and improves
performance.
Extend execmem_alloc() with an ability to use PMD_SIZE'ed pages with ROX
permissions as a cache for smaller allocations.
To populate the cache, a writable large page is allocated from vmalloc with
VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
ROX.
Portions of that large page are handed out to execmem_alloc() callers
without any changes to the permissions.
When the memory is freed with execmem_free() it is invalidated again so
that it won't contain stale instructions.
The cache is enabled when an architecture sets EXECMEM_ROX_CACHE flag in
definition of an execmem_range.
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
include/linux/execmem.h | 2 +
mm/execmem.c | 267 ++++++++++++++++++++++++++++++++++++++--
2 files changed, 262 insertions(+), 7 deletions(-)
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 9d22999dbd7d..06f678e6fe55 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -77,12 +77,14 @@ struct execmem_range {
/**
* struct execmem_info - architecture parameters for code allocations
+ * @invalidate: set memory to contain invalid instructions
* @ranges: array of parameter sets defining architecture specific
* parameters for executable memory allocations. The ranges that are not
* explicitly initialized by an architecture use parameters defined for
* @EXECMEM_DEFAULT.
*/
struct execmem_info {
+ void (*invalidate)(void *ptr, size_t size, bool writable);
struct execmem_range ranges[EXECMEM_TYPE_MAX];
};
diff --git a/mm/execmem.c b/mm/execmem.c
index c920d2b5a721..716fba68ab0e 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -1,30 +1,88 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/mm.h>
+#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/execmem.h>
+#include <linux/maple_tree.h>
#include <linux/moduleloader.h>
#include <linux/text-patching.h>
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
static struct execmem_info *execmem_info __ro_after_init;
static struct execmem_info default_execmem_info __ro_after_init;
-static void *__execmem_alloc(struct execmem_range *range, size_t size)
+struct execmem_cache {
+ struct mutex mutex;
+ struct maple_tree busy_areas;
+ struct maple_tree free_areas;
+};
+
+static struct execmem_cache execmem_cache = {
+ .mutex = __MUTEX_INITIALIZER(execmem_cache.mutex),
+ .busy_areas = MTREE_INIT_EXT(busy_areas, MT_FLAGS_LOCK_EXTERN,
+ execmem_cache.mutex),
+ .free_areas = MTREE_INIT_EXT(free_areas, MT_FLAGS_LOCK_EXTERN,
+ execmem_cache.mutex),
+};
+
+static void execmem_cache_clean(struct work_struct *work)
+{
+ struct maple_tree *free_areas = &execmem_cache.free_areas;
+ struct mutex *mutex = &execmem_cache.mutex;
+ MA_STATE(mas, free_areas, 0, ULONG_MAX);
+ void *area;
+
+ mutex_lock(mutex);
+ mas_for_each(&mas, area, ULONG_MAX) {
+ size_t size;
+
+ if (!xa_is_value(area))
+ continue;
+
+ size = xa_to_value(area);
+
+ if (IS_ALIGNED(size, PMD_SIZE) && IS_ALIGNED(mas.index, PMD_SIZE)) {
+ void *ptr = (void *)mas.index;
+
+ mas_erase(&mas);
+ vfree(ptr);
+ }
+ }
+ mutex_unlock(mutex);
+}
+
+static DECLARE_WORK(execmem_cache_clean_work, execmem_cache_clean);
+
+static void execmem_invalidate(void *ptr, size_t size, bool writable)
+{
+ if (execmem_info->invalidate)
+ execmem_info->invalidate(ptr, size, writable);
+ else
+ memset(ptr, 0, size);
+}
+
+static void *execmem_vmalloc(struct execmem_range *range, size_t size,
+ pgprot_t pgprot, unsigned long vm_flags)
{
bool kasan = range->flags & EXECMEM_KASAN_SHADOW;
- unsigned long vm_flags = VM_FLUSH_RESET_PERMS;
gfp_t gfp_flags = GFP_KERNEL | __GFP_NOWARN;
+ unsigned int align = range->alignment;
unsigned long start = range->start;
unsigned long end = range->end;
- unsigned int align = range->alignment;
- pgprot_t pgprot = range->pgprot;
void *p;
if (kasan)
vm_flags |= VM_DEFER_KMEMLEAK;
- p = __vmalloc_node_range(size, align, start, end, gfp_flags,
- pgprot, vm_flags, NUMA_NO_NODE,
+ if (vm_flags & VM_ALLOW_HUGE_VMAP)
+ align = PMD_SIZE;
+
+ p = __vmalloc_node_range(size, align, start, end, gfp_flags, pgprot,
+ vm_flags, NUMA_NO_NODE,
__builtin_return_address(0));
if (!p && range->fallback_start) {
start = range->fallback_start;
@@ -44,6 +102,199 @@ static void *__execmem_alloc(struct execmem_range *range, size_t size)
return NULL;
}
+ return p;
+}
+
+static int execmem_cache_add(void *ptr, size_t size)
+{
+ struct maple_tree *free_areas = &execmem_cache.free_areas;
+ struct mutex *mutex = &execmem_cache.mutex;
+ unsigned long addr = (unsigned long)ptr;
+ MA_STATE(mas, free_areas, addr - 1, addr + 1);
+ unsigned long lower, lower_size = 0;
+ unsigned long upper, upper_size = 0;
+ unsigned long area_size;
+ void *area = NULL;
+ int err;
+
+ lower = addr;
+ upper = addr + size - 1;
+
+ mutex_lock(mutex);
+ area = mas_walk(&mas);
+ if (area && xa_is_value(area) && mas.last == addr - 1) {
+ lower = mas.index;
+ lower_size = xa_to_value(area);
+ }
+
+ area = mas_next(&mas, ULONG_MAX);
+ if (area && xa_is_value(area) && mas.index == addr + size) {
+ upper = mas.last;
+ upper_size = xa_to_value(area);
+ }
+
+ mas_set_range(&mas, lower, upper);
+ area_size = lower_size + upper_size + size;
+ err = mas_store_gfp(&mas, xa_mk_value(area_size), GFP_KERNEL);
+ mutex_unlock(mutex);
+ if (err)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void *__execmem_cache_alloc(size_t size)
+{
+ struct maple_tree *free_areas = &execmem_cache.free_areas;
+ struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+ MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
+ MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
+ struct mutex *mutex = &execmem_cache.mutex;
+ unsigned long addr, last, area_size = 0;
+ void *area, *ptr = NULL;
+ int err;
+
+ mutex_lock(mutex);
+ mas_for_each(&mas_free, area, ULONG_MAX) {
+ area_size = xa_to_value(area);
+ if (area_size >= size)
+ break;
+ }
+
+ if (area_size < size)
+ goto out_unlock;
+
+ addr = mas_free.index;
+ last = mas_free.last;
+
+ /* insert allocated size to busy_areas at range [addr, addr + size) */
+ mas_set_range(&mas_busy, addr, addr + size - 1);
+ err = mas_store_gfp(&mas_busy, xa_mk_value(size), GFP_KERNEL);
+ if (err)
+ goto out_unlock;
+
+ mas_erase(&mas_free);
+ if (area_size > size) {
+ /*
+ * re-insert remaining free size to free_areas at range
+ * [addr + size, last]
+ */
+ mas_set_range(&mas_free, addr + size, last);
+ size = area_size - size;
+ err = mas_store_gfp(&mas_free, xa_mk_value(size), GFP_KERNEL);
+ if (err) {
+ mas_erase(&mas_busy);
+ goto out_unlock;
+ }
+ }
+ ptr = (void *)addr;
+
+out_unlock:
+ mutex_unlock(mutex);
+ return ptr;
+}
+
+static int execmem_cache_populate(struct execmem_range *range, size_t size)
+{
+ unsigned long vm_flags = VM_FLUSH_RESET_PERMS | VM_ALLOW_HUGE_VMAP;
+ unsigned long start, end;
+ struct vm_struct *vm;
+ size_t alloc_size;
+ int err = -ENOMEM;
+ void *p;
+
+ alloc_size = round_up(size, PMD_SIZE);
+ p = execmem_vmalloc(range, alloc_size, PAGE_KERNEL, vm_flags);
+ if (!p)
+ return err;
+
+ vm = find_vm_area(p);
+ if (!vm)
+ goto err_free_mem;
+
+ /* fill memory with invalid instructions */
+ execmem_invalidate(p, alloc_size, /* writable = */ true);
+
+ start = (unsigned long)p;
+ end = start + alloc_size;
+
+ vunmap_range_noflush(start, end);
+ flush_tlb_kernel_range(start, end);
+
+ /* FIXME: handle direct map alias */
+
+ err = vmap_pages_range_noflush(start, end, range->pgprot, vm->pages,
+ PMD_SHIFT);
+ if (err)
+ goto err_free_mem;
+
+ err = execmem_cache_add(p, alloc_size);
+ if (err)
+ goto err_free_mem;
+
+ return 0;
+
+err_free_mem:
+ vfree(p);
+ return err;
+}
+
+static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
+{
+ void *p;
+ int err;
+
+ p = __execmem_cache_alloc(size);
+ if (p)
+ return p;
+
+ err = execmem_cache_populate(range, size);
+ if (err)
+ return NULL;
+
+ return __execmem_cache_alloc(size);
+}
+
+static bool execmem_cache_free(void *ptr)
+{
+ struct maple_tree *busy_areas = &execmem_cache.busy_areas;
+ struct mutex *mutex = &execmem_cache.mutex;
+ unsigned long addr = (unsigned long)ptr;
+ MA_STATE(mas, busy_areas, addr, addr);
+ size_t size;
+ void *area;
+
+ mutex_lock(mutex);
+ area = mas_walk(&mas);
+ if (!area) {
+ mutex_unlock(mutex);
+ return false;
+ }
+ size = xa_to_value(area);
+ mas_erase(&mas);
+ mutex_unlock(mutex);
+
+ execmem_invalidate(ptr, size, /* writable = */ false);
+
+ execmem_cache_add(ptr, size);
+
+ schedule_work(&execmem_cache_clean_work);
+
+ return true;
+}
+
+static void *__execmem_alloc(struct execmem_range *range, size_t size)
+{
+ bool use_cache = range->flags & EXECMEM_ROX_CACHE;
+ unsigned long vm_flags = VM_FLUSH_RESET_PERMS;
+ pgprot_t pgprot = range->pgprot;
+ void *p;
+
+ if (use_cache)
+ p = execmem_cache_alloc(range, size);
+ else
+ p = execmem_vmalloc(range, size, pgprot, vm_flags);
+
return kasan_reset_tag(p);
}
@@ -61,7 +312,9 @@ void execmem_free(void *ptr)
* supported by vmalloc.
*/
WARN_ON(in_interrupt());
- vfree(ptr);
+
+ if (!execmem_cache_free(ptr))
+ vfree(ptr);
}
void *execmem_update_copy(void *dst, const void *src, size_t size)
--
2.43.0On Thu, Apr 11, 2024 at 07:05:25PM +0300, Mike Rapoport wrote:
> To populate the cache, a writable large page is allocated from vmalloc with
> VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
> ROX.
> +static void execmem_invalidate(void *ptr, size_t size, bool writable)
> +{
> + if (execmem_info->invalidate)
> + execmem_info->invalidate(ptr, size, writable);
> + else
> + memset(ptr, 0, size);
> +}
+static void execmem_invalidate(void *ptr, size_t size, bool writeable)
+{
+ /* fill memory with INT3 instructions */
+ if (writeable)
+ memset(ptr, 0xcc, size);
+ else
+ text_poke_set(ptr, 0xcc, size);
+}
Thing is, 0xcc (aka INT3_INSN_OPCODE) is not an invalid instruction.
It raises #BP not #UD.
On Mon, Apr 15, 2024 at 12:47:50PM +0200, Peter Zijlstra wrote:
> On Thu, Apr 11, 2024 at 07:05:25PM +0300, Mike Rapoport wrote:
>
> > To populate the cache, a writable large page is allocated from vmalloc with
> > VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
> > ROX.
>
> > +static void execmem_invalidate(void *ptr, size_t size, bool writable)
> > +{
> > + if (execmem_info->invalidate)
> > + execmem_info->invalidate(ptr, size, writable);
> > + else
> > + memset(ptr, 0, size);
> > +}
>
> +static void execmem_invalidate(void *ptr, size_t size, bool writeable)
> +{
> + /* fill memory with INT3 instructions */
> + if (writeable)
> + memset(ptr, 0xcc, size);
> + else
> + text_poke_set(ptr, 0xcc, size);
> +}
>
> Thing is, 0xcc (aka INT3_INSN_OPCODE) is not an invalid instruction.
> It raises #BP not #UD.
Do you mean that _invalidate is a poor name choice or that it's necessary
to use an instruction that raises #UD?
--
Sincerely yours,
Mike.
On Mon, Apr 15, 2024 at 08:00:26PM +0300, Mike Rapoport wrote:
> On Mon, Apr 15, 2024 at 12:47:50PM +0200, Peter Zijlstra wrote:
> > On Thu, Apr 11, 2024 at 07:05:25PM +0300, Mike Rapoport wrote:
> >
> > > To populate the cache, a writable large page is allocated from vmalloc with
> > > VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
> > > ROX.
> >
> > > +static void execmem_invalidate(void *ptr, size_t size, bool writable)
> > > +{
> > > + if (execmem_info->invalidate)
> > > + execmem_info->invalidate(ptr, size, writable);
> > > + else
> > > + memset(ptr, 0, size);
> > > +}
> >
> > +static void execmem_invalidate(void *ptr, size_t size, bool writeable)
> > +{
> > + /* fill memory with INT3 instructions */
> > + if (writeable)
> > + memset(ptr, 0xcc, size);
> > + else
> > + text_poke_set(ptr, 0xcc, size);
> > +}
> >
> > Thing is, 0xcc (aka INT3_INSN_OPCODE) is not an invalid instruction.
> > It raises #BP not #UD.
>
> Do you mean that _invalidate is a poor name choice or that it's necessary
> to use an instruction that raises #UD?
Poor naming, mostly. #BP handler will still scream bloody murder if the
site is otherwise unclaimed.
It just isn't an invalid instruction.
On Tue, Apr 16, 2024 at 09:52:34AM +0200, Peter Zijlstra wrote:
> On Mon, Apr 15, 2024 at 08:00:26PM +0300, Mike Rapoport wrote:
> > On Mon, Apr 15, 2024 at 12:47:50PM +0200, Peter Zijlstra wrote:
> > > On Thu, Apr 11, 2024 at 07:05:25PM +0300, Mike Rapoport wrote:
> > >
> > > > To populate the cache, a writable large page is allocated from vmalloc with
> > > > VM_ALLOW_HUGE_VMAP, filled with invalid instructions and then remapped as
> > > > ROX.
> > >
> > > > +static void execmem_invalidate(void *ptr, size_t size, bool writable)
> > > > +{
> > > > + if (execmem_info->invalidate)
> > > > + execmem_info->invalidate(ptr, size, writable);
> > > > + else
> > > > + memset(ptr, 0, size);
> > > > +}
> > >
> > > +static void execmem_invalidate(void *ptr, size_t size, bool writeable)
> > > +{
> > > + /* fill memory with INT3 instructions */
> > > + if (writeable)
> > > + memset(ptr, 0xcc, size);
> > > + else
> > > + text_poke_set(ptr, 0xcc, size);
> > > +}
> > >
> > > Thing is, 0xcc (aka INT3_INSN_OPCODE) is not an invalid instruction.
> > > It raises #BP not #UD.
> >
> > Do you mean that _invalidate is a poor name choice or that it's necessary
> > to use an instruction that raises #UD?
>
> Poor naming, mostly. #BP handler will still scream bloody murder if the
> site is otherwise unclaimed.
>
> It just isn't an invalid instruction.
Well, execmem_fill_with_insns_screaming_bloody_murder seems too long, how
about execmem_fill_trapping_insns?
--
Sincerely yours,
Mike.
© 2016 - 2026 Red Hat, Inc.