* [PATCH 10/13] mm/vma: convert miscellaneous uses of VMA flags in core mm
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Update various uses of legacy flags in vma.c and mmap.c to the new
vma_flags_t type, updating comments alongside them to be consistent.
Also update __install_special_mapping() to rearrange things slightly to
accommodate the changes.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
mm/mmap.c | 39 +++++++++++++++++++++------------------
mm/vma.c | 16 ++++++++++------
2 files changed, 31 insertions(+), 24 deletions(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index e834ec9273e3..a8546c9250a0 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -557,8 +557,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
}
/*
- * Set 'VM_NORESERVE' if we should not account for the
- * memory use of this mapping.
+ * Set VMA_NORESERVE_BIT if we should not account for the memory use
+ * of this mapping.
*/
if (flags & MAP_NORESERVE) {
/* We honor MAP_NORESERVE if allowed to overcommit */
@@ -985,7 +985,7 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon
return NULL;
if (expand_stack_locked(prev, addr))
return NULL;
- if (prev->vm_flags & VM_LOCKED)
+ if (vma_test(prev, VMA_LOCKED_BIT))
populate_vma_page_range(prev, addr, prev->vm_end, NULL);
return prev;
}
@@ -1009,7 +1009,7 @@ struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned lon
start = vma->vm_start;
if (expand_stack_locked(vma, addr))
return NULL;
- if (vma->vm_flags & VM_LOCKED)
+ if (vma_test(vma, VMA_LOCKED_BIT))
populate_vma_page_range(vma, addr, start, NULL);
return vma;
}
@@ -1134,18 +1134,18 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
*/
vma = vma_lookup(mm, start);
- if (!vma || !(vma->vm_flags & VM_SHARED)) {
+ if (!vma || !vma_test(vma, VMA_SHARED_BIT)) {
mmap_read_unlock(mm);
return -EINVAL;
}
- prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
- prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
- prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+ prot |= vma_test(vma, VMA_READ_BIT) ? PROT_READ : 0;
+ prot |= vma_test(vma, VMA_WRITE_BIT) ? PROT_WRITE : 0;
+ prot |= vma_test(vma, VMA_EXEC_BIT) ? PROT_EXEC : 0;
flags &= MAP_NONBLOCK;
flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
- if (vma->vm_flags & VM_LOCKED)
+ if (vma_test(vma, VMA_LOCKED_BIT))
flags |= MAP_LOCKED;
/* Save vm_flags used to calculate prot and flags, and recheck later. */
@@ -1271,7 +1271,7 @@ unsigned long tear_down_vmas(struct mm_struct *mm, struct vma_iterator *vmi,
mmap_assert_write_locked(mm);
vma_iter_set(vmi, vma->vm_end);
do {
- if (vma->vm_flags & VM_ACCOUNT)
+ if (vma_test(vma, VMA_ACCOUNT_BIT))
nr_accounted += vma_pages(vma);
vma_mark_detached(vma);
remove_vma(vma);
@@ -1420,7 +1420,7 @@ static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr)
{
/*
* Forbid splitting special mappings - kernel has expectations over
- * the number of pages in mapping. Together with VM_DONTEXPAND
+ * the number of pages in mapping. Together with VMA_DONTEXPAND_BIT
* the size of vma should stay the same over the special mapping's
* lifetime.
*/
@@ -1692,7 +1692,7 @@ bool mmap_read_lock_maybe_expand(struct mm_struct *mm,
return true;
}
- if (!(new_vma->vm_flags & VM_GROWSDOWN))
+ if (!vma_test(new_vma, VMA_GROWSDOWN_BIT))
return false;
mmap_write_lock(mm);
@@ -1742,7 +1742,7 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
retval = vma_start_write_killable(mpnt);
if (retval < 0)
goto loop_out;
- if (mpnt->vm_flags & VM_DONTCOPY) {
+ if (vma_test(mpnt, VMA_DONTCOPY_BIT)) {
retval = vma_iter_clear_gfp(&vmi, mpnt->vm_start,
mpnt->vm_end, GFP_KERNEL);
if (retval)
@@ -1752,7 +1752,7 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
continue;
}
charge = 0;
- if (mpnt->vm_flags & VM_ACCOUNT) {
+ if (vma_test(mpnt, VMA_ACCOUNT_BIT)) {
unsigned long len = vma_pages(mpnt);
if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
@@ -1770,16 +1770,19 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
retval = dup_userfaultfd(tmp, &uf);
if (retval)
goto fail_nomem_anon_vma_fork;
- if (tmp->vm_flags & VM_WIPEONFORK) {
+
+ if (vma_test(tmp, VMA_WIPEONFORK_BIT)) {
/*
- * VM_WIPEONFORK gets a clean slate in the child.
+ * VMA_WIPEONFORK_BIT gets a clean slate in the child.
* Don't prepare anon_vma until fault since we don't
* copy page for current vma.
*/
tmp->anon_vma = NULL;
} else if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
- vm_flags_clear(tmp, VM_LOCKED_MASK);
+
+ vma_start_write(tmp);
+ vma_clear_flags_mask(tmp, VMA_LOCKED_MASK);
/*
* Copy/update hugetlb private vma information.
*/
@@ -1812,7 +1815,7 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
i_mmap_unlock_write(mapping);
}
- if (!(tmp->vm_flags & VM_WIPEONFORK))
+ if (!vma_test(tmp, VMA_WIPEONFORK_BIT))
retval = copy_page_range(tmp, mpnt);
if (retval) {
diff --git a/mm/vma.c b/mm/vma.c
index b81c05e67a61..ab2ef0f04420 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -3417,23 +3417,27 @@ struct vm_area_struct *__install_special_mapping(
vm_flags_t vm_flags, void *priv,
const struct vm_operations_struct *ops)
{
- int ret;
+ vma_flags_t vma_flags = legacy_to_vma_flags(vm_flags);
struct vm_area_struct *vma;
+ int ret;
vma = vm_area_alloc(mm);
- if (unlikely(vma == NULL))
+ if (unlikely(!vma))
return ERR_PTR(-ENOMEM);
- vma_set_range(vma, addr, addr + len, 0);
- vm_flags |= vma_flags_to_legacy(mm->def_vma_flags) | VM_DONTEXPAND;
+ vma_flags_set_mask(&vma_flags, mm->def_vma_flags);
+ vma_flags_set(&vma_flags, VMA_DONTEXPAND_BIT);
if (pgtable_supports_soft_dirty())
- vm_flags |= VM_SOFTDIRTY;
- vm_flags_init(vma, vm_flags & ~VM_LOCKED_MASK);
+ vma_flags_set(&vma_flags, VMA_SOFTDIRTY_BIT);
+ vma_flags_clear_mask(&vma_flags, VMA_LOCKED_MASK);
+ vma->flags = vma_flags;
vma->vm_page_prot = vma_get_page_prot(vma);
vma->vm_ops = ops;
vma->vm_private_data = priv;
+ vma_set_range(vma, addr, addr + len, 0);
+
ret = insert_vm_struct(mm, vma);
if (ret)
goto out;
--
2.54.0
^ permalink raw reply related
* [PATCH 09/13] mm/vma: update create_init_stack_vma() to use vma_flags_t
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Replace use of the legacy vm_flags_t flags with vma_flags_t values in
create_init_stack_vma().
As part of this change we add VMA_STACK_EARLY and VMA_STACK_INCOMPLETE
vma_flags_t defines, and slightly rework create_init_stack_vma() for
clarity.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
include/linux/mm.h | 4 ++++
mm/vma_exec.c | 18 +++++++++++-------
2 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b55790c75038..6e57d41677de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -440,8 +440,10 @@ enum {
#define VM_STACK INIT_VM_FLAG(STACK)
#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY)
+#define VMA_STACK_EARLY mk_vma_flags(VMA_STACK_EARLY_BIT)
#else
#define VM_STACK_EARLY VM_NONE
+#define VMA_STACK_EARLY EMPTY_VMA_FLAGS
#endif
#ifdef CONFIG_ARCH_HAS_PKEYS
#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT)
@@ -532,6 +534,8 @@ enum {
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
+#define VMA_STACK_INCOMPLETE_SETUP append_vma_flags( \
+ VMA_STACK_EARLY, VMA_RAND_READ_BIT, VMA_SEQ_READ_BIT)
#define TASK_EXEC_BIT ((current->personality & READ_IMPLIES_EXEC) ? \
VMA_EXEC_BIT : VMA_READ_BIT)
diff --git a/mm/vma_exec.c b/mm/vma_exec.c
index b01c4964f2c9..48c783e73cf3 100644
--- a/mm/vma_exec.c
+++ b/mm/vma_exec.c
@@ -112,15 +112,17 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
unsigned long *top_mem_p)
{
- unsigned long flags = VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
+ vma_flags_t flags = VMA_STACK_INCOMPLETE_SETUP;
+ struct vm_area_struct *vma;
int err;
- struct vm_area_struct *vma = vm_area_alloc(mm);
+ /* VMA_STACK_FLAGS and VMA_STACK_INCOMPLETE_SETUP must not overlap. */
+ VM_WARN_ON_ONCE(vma_flags_test_any_mask(&flags, VMA_STACK_FLAGS));
+
+ vma = vm_area_alloc(mm);
if (!vma)
return -ENOMEM;
- vma_set_anonymous(vma);
-
if (mmap_write_lock_killable(mm)) {
err = -EINTR;
goto err_free;
@@ -134,18 +136,20 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
if (err)
goto err_ksm;
+ vma_flags_set_mask(&flags, VMA_STACK_FLAGS);
+ vma_set_anonymous(vma);
+
/*
* Place the stack at the largest stack address the architecture
* supports. Later, we'll move this to an appropriate place. We don't
* use STACK_TOP because that can depend on attributes which aren't
* configured yet.
*/
- VM_WARN_ON_ONCE(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP);
vma->vm_end = STACK_TOP_MAX;
vma->vm_start = vma->vm_end - PAGE_SIZE;
if (pgtable_supports_soft_dirty())
- flags |= VM_SOFTDIRTY;
- vm_flags_init(vma, flags);
+ vma_flags_set(&flags, VMA_SOFTDIRTY_BIT);
+ vma->flags = flags;
vma->vm_page_prot = vma_get_page_prot(vma);
err = insert_vm_struct(mm, vma);
--
2.54.0
^ permalink raw reply related
* [PATCH 08/13] mm: introduce vma_get_page_prot() and use it
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
There's a large number of vm_get_page_prot(vma->vm_flags) invocations. Make
life easier by introducing vma_get_page_prot() parameterised by the VMA.
This also makes converting vm_get_page_prot() to vma_flags_t easier.
Also update the userland VMA tests to reflect the change.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
drivers/gpu/drm/drm_gem.c | 2 +-
drivers/gpu/drm/drm_gem_dma_helper.c | 2 +-
drivers/gpu/drm/drm_gem_shmem_helper.c | 2 +-
drivers/gpu/drm/etnaviv/etnaviv_gem.c | 2 +-
drivers/gpu/drm/exynos/exynos_drm_gem.c | 6 +++---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 12 ++++++------
drivers/gpu/drm/msm/msm_gem.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_gem.c | 2 +-
drivers/gpu/drm/omapdrm/omap_fbdev.c | 2 +-
drivers/gpu/drm/omapdrm/omap_gem.c | 6 +++---
drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 2 +-
drivers/gpu/drm/tegra/gem.c | 2 +-
drivers/gpu/drm/virtio/virtgpu_vram.c | 2 +-
drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 2 +-
drivers/gpu/drm/xe/xe_device.c | 2 +-
drivers/gpu/drm/xe/xe_mmio_gem.c | 2 +-
drivers/gpu/drm/xen/xen_drm_front_gem.c | 2 +-
drivers/video/fbdev/core/fb_io_fops.c | 2 +-
include/linux/mm.h | 10 +++++++++-
mm/vma.c | 2 +-
mm/vma_exec.c | 2 +-
sound/core/memalloc.c | 2 +-
tools/testing/vma/include/dup.h | 4 ++++
23 files changed, 43 insertions(+), 31 deletions(-)
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index e3ed684ddcf2..32a05d889b9a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1252,7 +1252,7 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
}
vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
- vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_writecombine(vma_get_page_prot(vma));
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
}
diff --git a/drivers/gpu/drm/drm_gem_dma_helper.c b/drivers/gpu/drm/drm_gem_dma_helper.c
index 1c00a71ab3c9..7d9612075d31 100644
--- a/drivers/gpu/drm/drm_gem_dma_helper.c
+++ b/drivers/gpu/drm/drm_gem_dma_helper.c
@@ -540,7 +540,7 @@ int drm_gem_dma_mmap(struct drm_gem_dma_object *dma_obj, struct vm_area_struct *
vm_flags_mod(vma, VM_DONTDUMP | VM_DONTEXPAND, VM_PFNMAP);
if (dma_obj->map_noncoherent) {
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
ret = dma_mmap_pages(drm_dev_dma_dev(dma_obj->base.dev),
vma, vma->vm_end - vma->vm_start,
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index c989459eb215..06d019d51d3e 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -764,7 +764,7 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct
return ret;
vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
if (shmem->map_wc)
vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 2e4d6d117ee2..f9c8b7b2bfc7 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -133,7 +133,7 @@ static int etnaviv_gem_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
- vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vm_page_prot = vma_get_page_prot(vma);
if (etnaviv_obj->flags & ETNA_BO_WC) {
vma->vm_page_prot = pgprot_writecombine(vm_page_prot);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 9a6270f3dca6..0208c9259572 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -377,13 +377,13 @@ static int exynos_drm_gem_mmap(struct drm_gem_object *obj, struct vm_area_struct
/* non-cachable as default. */
if (exynos_gem->flags & EXYNOS_BO_CACHABLE)
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
else if (exynos_gem->flags & EXYNOS_BO_WC)
vma->vm_page_prot =
- pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ pgprot_writecombine(vma_get_page_prot(vma));
else
vma->vm_page_prot =
- pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+ pgprot_noncached(vma_get_page_prot(vma));
ret = exynos_drm_gem_mmap_buffer(exynos_gem, vma);
if (ret)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 0644f85c6c8e..9ca90c1bb5b4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -112,7 +112,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
vma = find_vma(mm, addr);
if (vma && __vma_matches(vma, obj->base.filp, addr, args->size))
vma->vm_page_prot =
- pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ pgprot_writecombine(vma_get_page_prot(vma));
else
addr = -ENOMEM;
mmap_write_unlock(mm);
@@ -1024,7 +1024,7 @@ i915_gem_object_mmap(struct drm_i915_gem_object *obj,
fput(anon);
if (obj->ops->mmap_ops) {
- vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_decrypted(vma_get_page_prot(vma));
vma->vm_ops = obj->ops->mmap_ops;
vma->vm_private_data = obj->base.vma_node.driver_private;
return 0;
@@ -1035,7 +1035,7 @@ i915_gem_object_mmap(struct drm_i915_gem_object *obj,
switch (mmo->mmap_type) {
case I915_MMAP_TYPE_WC:
vma->vm_page_prot =
- pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ pgprot_writecombine(vma_get_page_prot(vma));
vma->vm_ops = &vm_ops_cpu;
break;
@@ -1043,19 +1043,19 @@ i915_gem_object_mmap(struct drm_i915_gem_object *obj,
GEM_WARN_ON(1);
fallthrough;
case I915_MMAP_TYPE_WB:
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
vma->vm_ops = &vm_ops_cpu;
break;
case I915_MMAP_TYPE_UC:
vma->vm_page_prot =
- pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+ pgprot_noncached(vma_get_page_prot(vma));
vma->vm_ops = &vm_ops_cpu;
break;
case I915_MMAP_TYPE_GTT:
vma->vm_page_prot =
- pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ pgprot_writecombine(vma_get_page_prot(vma));
vma->vm_ops = &vm_ops_gtt;
break;
}
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index cbf723a5d86f..6a78e242de7c 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1125,7 +1125,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct
struct msm_gem_object *msm_obj = to_msm_bo(obj);
vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
- vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = msm_gem_pgprot(msm_obj, vma_get_page_prot(vma));
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 20dba02d6175..9a6ee2e880c0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -55,7 +55,7 @@ static vm_fault_t nouveau_ttm_fault(struct vm_fault *vmf)
goto error_unlock;
nouveau_bo_del_io_reserve_lru(bo);
- prot = vm_get_page_prot(vma->vm_flags);
+ prot = vma_get_page_prot(vma);
ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
nouveau_bo_add_io_reserve_lru(bo);
if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index ca3fb186bf19..4881777642d2 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -84,7 +84,7 @@ static int omap_fbdev_pan_display(struct fb_var_screeninfo *var, struct fb_info
static int omap_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
{
- vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_writecombine(vma_get_page_prot(vma));
return fb_deferred_io_mmap(info, vma);
}
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 00404fb6c29a..fb0e6f556b31 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -538,9 +538,9 @@ static int omap_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc
vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP | VM_IO | VM_MIXEDMAP);
if (omap_obj->flags & OMAP_BO_WC) {
- vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_writecombine(vma_get_page_prot(vma));
} else if (omap_obj->flags & OMAP_BO_UNCACHED) {
- vma->vm_page_prot = pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_noncached(vma_get_page_prot(vma));
} else {
/*
* We do have some private objects, at least for scanout buffers
@@ -558,7 +558,7 @@ static int omap_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc
vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
vma_set_file(vma, obj->filp);
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
}
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index b188539dca0b..9a1dc9f12072 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -255,7 +255,7 @@ static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj,
*/
vm_flags_mod(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP, VM_PFNMAP);
- vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_writecombine(vma_get_page_prot(vma));
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
if (rk_obj->pages)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 1d8d27a5ea89..f76af733ea79 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -602,7 +602,7 @@ int __tegra_gem_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma)
vma->vm_pgoff = vm_pgoff;
} else {
- pgprot_t prot = vm_get_page_prot(vma->vm_flags);
+ pgprot_t prot = vma_get_page_prot(vma);
vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP);
diff --git a/drivers/gpu/drm/virtio/virtgpu_vram.c b/drivers/gpu/drm/virtio/virtgpu_vram.c
index 4ae3cbc35dd3..544a6abddbc8 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vram.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vram.c
@@ -55,7 +55,7 @@ static int virtio_gpu_vram_mmap(struct drm_gem_object *obj,
vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
vm_flags_set(vma, VM_MIXEDMAP | VM_DONTEXPAND);
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
vma->vm_ops = &virtio_gpu_vram_vm_ops;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 45561bc1c9ef..a9fd4015a0ca 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -481,7 +481,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf)
if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE)
prot = vm_get_page_prot(vma->vm_flags & ~VM_SHARED);
else
- prot = vm_get_page_prot(vma->vm_flags);
+ prot = vma_get_page_prot(vma);
ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault);
if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d224861b6f6f..758acaae85d3 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -281,7 +281,7 @@ static vm_fault_t barrier_fault(struct vm_fault *vmf)
pgprot_t prot;
int idx;
- prot = vm_get_page_prot(vma->vm_flags);
+ prot = vma_get_page_prot(vma);
if (drm_dev_enter(dev, &idx)) {
unsigned long pfn;
diff --git a/drivers/gpu/drm/xe/xe_mmio_gem.c b/drivers/gpu/drm/xe/xe_mmio_gem.c
index 8c803ef233cc..3741ae60f532 100644
--- a/drivers/gpu/drm/xe/xe_mmio_gem.c
+++ b/drivers/gpu/drm/xe/xe_mmio_gem.c
@@ -149,7 +149,7 @@ static int xe_mmio_gem_mmap(struct drm_gem_object *base, struct vm_area_struct *
/* Set vm_pgoff (used as a fake buffer offset by DRM) to 0 */
vma->vm_pgoff = 0;
- vma->vm_page_prot = pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+ vma->vm_page_prot = pgprot_noncached(vma_get_page_prot(vma));
vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
VM_DONTCOPY | VM_NORESERVE);
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index eec4c1da3f9e..dd158443f55f 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -80,7 +80,7 @@ static int xen_drm_front_gem_object_mmap(struct drm_gem_object *gem_obj,
* which is mapped as Normal Inner Write-Back Outer Write-Back
* Inner-Shareable.
*/
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
/*
* vm_operations_struct.fault handler will be called if CPU access
diff --git a/drivers/video/fbdev/core/fb_io_fops.c b/drivers/video/fbdev/core/fb_io_fops.c
index 6ab60fcd0050..6d0a8c8e141a 100644
--- a/drivers/video/fbdev/core/fb_io_fops.c
+++ b/drivers/video/fbdev/core/fb_io_fops.c
@@ -161,7 +161,7 @@ int fb_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
len = info->fix.mmio_len;
}
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
vma->vm_page_prot = pgprot_framebuffer(vma->vm_page_prot, vma->vm_start,
vma->vm_end, start);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c8336f68d7bb..b55790c75038 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4575,6 +4575,10 @@ static inline pgprot_t vma_flags_to_page_prot(vma_flags_t vma_flags)
return vm_get_page_prot(vm_flags);
}
+static inline pgprot_t vma_get_page_prot(const struct vm_area_struct *vma)
+{
+ return vma_flags_to_page_prot(vma->flags);
+}
void vma_set_page_prot(struct vm_area_struct *vma);
#else
static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
@@ -4585,9 +4589,13 @@ static inline pgprot_t vma_flags_to_page_prot(vma_flags_t vma_flags)
{
return __pgprot(0);
}
+static inline pgprot_t vma_get_page_prot(const struct vm_area_struct *vma)
+{
+ return __pgprot(0);
+}
static inline void vma_set_page_prot(struct vm_area_struct *vma)
{
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
}
#endif
diff --git a/mm/vma.c b/mm/vma.c
index fcdd2ac3ac68..b81c05e67a61 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -3429,7 +3429,7 @@ struct vm_area_struct *__install_special_mapping(
if (pgtable_supports_soft_dirty())
vm_flags |= VM_SOFTDIRTY;
vm_flags_init(vma, vm_flags & ~VM_LOCKED_MASK);
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
vma->vm_ops = ops;
vma->vm_private_data = priv;
diff --git a/mm/vma_exec.c b/mm/vma_exec.c
index c0f7ba2cfb27..b01c4964f2c9 100644
--- a/mm/vma_exec.c
+++ b/mm/vma_exec.c
@@ -146,7 +146,7 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
if (pgtable_supports_soft_dirty())
flags |= VM_SOFTDIRTY;
vm_flags_init(vma, flags);
- vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+ vma->vm_page_prot = vma_get_page_prot(vma);
err = insert_vm_struct(mm, vma);
if (err)
diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 9320671dfcc8..5bc7e586b430 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -851,7 +851,7 @@ static void snd_dma_noncoherent_free(struct snd_dma_buffer *dmab)
static int snd_dma_noncoherent_mmap(struct snd_dma_buffer *dmab,
struct vm_area_struct *area)
{
- area->vm_page_prot = vm_get_page_prot(area->vm_flags);
+ area->vm_page_prot = vma_get_page_prot(area);
return dma_mmap_pages(dmab->dev.dev, area,
area->vm_end - area->vm_start,
virt_to_page(dmab->area));
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 1ffac38a5377..d86bef8cb37f 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -1577,3 +1577,7 @@ static inline pgoff_t linear_page_index(const struct vm_area_struct *vma,
pgoff += vma_start_pgoff(vma);
return pgoff;
}
+static inline pgprot_t vma_get_page_prot(const struct vm_area_struct *vma)
+{
+ return vma_flags_to_page_prot(vma->flags);
+}
--
2.54.0
^ permalink raw reply related
* [PATCH 07/13] mm/vma: rename vma_get_page_prot to vma_flags_to_page_prot
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Having vma_get_page_prot() refer to VMA flags and vma_set_page_prot() refer
to a VMA is confusing.
Rename vma_get_page_prot() to vma_flags_to_page_prot() to resolve this
confusion.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
include/linux/mm.h | 4 ++--
mm/vma.c | 2 +-
mm/vma.h | 2 +-
tools/testing/vma/include/dup.h | 2 +-
4 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 474b3698f565..c8336f68d7bb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4568,7 +4568,7 @@ static inline bool range_in_vma_desc(const struct vm_area_desc *desc,
#ifdef CONFIG_MMU
pgprot_t vm_get_page_prot(vm_flags_t vm_flags);
-static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags)
+static inline pgprot_t vma_flags_to_page_prot(vma_flags_t vma_flags)
{
const vm_flags_t vm_flags = vma_flags_to_legacy(vma_flags);
@@ -4581,7 +4581,7 @@ static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
{
return __pgprot(0);
}
-static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags)
+static inline pgprot_t vma_flags_to_page_prot(vma_flags_t vma_flags)
{
return __pgprot(0);
}
diff --git a/mm/vma.c b/mm/vma.c
index 395b6619ecc1..fcdd2ac3ac68 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -56,7 +56,7 @@ struct mmap_state {
.pglen = PHYS_PFN(len_), \
.vma_flags = vma_flags_, \
.file = file_, \
- .page_prot = vma_get_page_prot(vma_flags_), \
+ .page_prot = vma_flags_to_page_prot(vma_flags_), \
}
#define VMG_MMAP_STATE(name, map_, vma_) \
diff --git a/mm/vma.h b/mm/vma.h
index 6a8abb8ae937..d6b48d596f44 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -524,7 +524,7 @@ static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma
#ifdef CONFIG_MMU
static inline pgprot_t vma_pgprot_modify(pgprot_t oldprot, vma_flags_t vma_flags)
{
- const pgprot_t prot = vma_get_page_prot(vma_flags);
+ const pgprot_t prot = vma_flags_to_page_prot(vma_flags);
return pgprot_modify(oldprot, prot);
}
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 813044781719..1ffac38a5377 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -1555,7 +1555,7 @@ static inline int get_sysctl_max_map_count(void)
#define pgtable_supports_soft_dirty() IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)
#endif
-static inline pgprot_t vma_get_page_prot(vma_flags_t vma_flags)
+static inline pgprot_t vma_flags_to_page_prot(vma_flags_t vma_flags)
{
const vm_flags_t vm_flags = vma_flags_to_legacy(vma_flags);
--
2.54.0
^ permalink raw reply related
* [PATCH 06/13] mm/vma: convert vm_pgprot_modify() to use vma_flags_t and rename
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Update vm_pgprot_modify() to use the new VMA flags type vma_flags_t, and
rename to vma_pgprot_modify() accordingly.
This is part of the ongoing work to convert vm_flags_t to vma_flags_t, in
order to eliminate the arbitrary limit of the number of bits in a system
word on available VMA flags.
Update VMA userland tests accordingly, updating vma_set_page_prot() to no
longer inline vma_pgprot_modify(), rather we can simply define
vma_pgprot_modify() as a static inline function and the tests will pick it
up from vma.h.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
mm/mmap.c | 8 ++++----
mm/vma.c | 2 +-
mm/vma.h | 6 ++++--
tools/testing/vma/include/dup.h | 12 +++++-------
4 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/mm/mmap.c b/mm/mmap.c
index 477f4a77361a..e834ec9273e3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -80,13 +80,13 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
/* Update vma->vm_page_prot to reflect vma->vm_flags. */
void vma_set_page_prot(struct vm_area_struct *vma)
{
- vm_flags_t vm_flags = vma->vm_flags;
+ vma_flags_t vma_flags = vma->flags;
pgprot_t vm_page_prot;
- vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
+ vm_page_prot = vma_pgprot_modify(vma->vm_page_prot, vma_flags);
if (vma_wants_writenotify(vma, vm_page_prot)) {
- vm_flags &= ~VM_SHARED;
- vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags);
+ vma_flags_clear(&vma_flags, VMA_SHARED_BIT);
+ vm_page_prot = vma_pgprot_modify(vm_page_prot, vma_flags);
}
/* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
diff --git a/mm/vma.c b/mm/vma.c
index fb4341943576..395b6619ecc1 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2179,7 +2179,7 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
/* The open routine did something to the protections that pgprot_modify
* won't preserve? */
if (pgprot_val(vm_page_prot) !=
- pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags)))
+ pgprot_val(vma_pgprot_modify(vm_page_prot, vma->flags)))
return false;
/*
diff --git a/mm/vma.h b/mm/vma.h
index bcf0c2773449..6a8abb8ae937 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -522,9 +522,11 @@ static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma
}
#ifdef CONFIG_MMU
-static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, vm_flags_t vm_flags)
+static inline pgprot_t vma_pgprot_modify(pgprot_t oldprot, vma_flags_t vma_flags)
{
- return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
+ const pgprot_t prot = vma_get_page_prot(vma_flags);
+
+ return pgprot_modify(oldprot, prot);
}
#endif
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 6f5bcd7fbcd8..813044781719 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -1434,20 +1434,18 @@ struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
}
bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
+static inline pgprot_t vma_pgprot_modify(pgprot_t oldprot, vma_flags_t vma_flags);
/* Update vma->vm_page_prot to reflect vma->vm_flags. */
static inline void vma_set_page_prot(struct vm_area_struct *vma)
{
- vm_flags_t vm_flags = vma->vm_flags;
+ vma_flags_t vma_flags = vma->flags;
pgprot_t vm_page_prot;
- /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
- vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags));
-
+ vm_page_prot = vma_pgprot_modify(vma->vm_page_prot, vma_flags);
if (vma_wants_writenotify(vma, vm_page_prot)) {
- vm_flags &= ~VM_SHARED;
- /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
- vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags));
+ vma_flags_clear(&vma_flags, VMA_SHARED_BIT);
+ vm_page_prot = vma_pgprot_modify(vm_page_prot, vma_flags);
}
/* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
--
2.54.0
^ permalink raw reply related
* [PATCH 05/13] mm: prefer mm->def_vma_flags in mm logic
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Currently mm->def_flags (of type vm_flags_t) is union'd with
mm->def_vma_flags (of type vma_flags_t).
As part of the effort to convert vm_flags_t usage to vma_flags_t (in order
to no longer be arbitrarily limited to a system word size for VMA flags),
prefer mm->def_vma_flags to mm->def_flags throughout the mm logic.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
mm/debug.c | 2 +-
mm/mlock.c | 13 +++++++------
mm/mmap.c | 11 ++++++-----
mm/vma.c | 4 ++--
4 files changed, 16 insertions(+), 14 deletions(-)
diff --git a/mm/debug.c b/mm/debug.c
index 497654b36f1a..f0a354a9496a 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -226,7 +226,7 @@ void dump_mm(const struct mm_struct *mm)
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
#endif
atomic_read(&mm->tlb_flush_pending),
- mm->def_flags, &mm->def_flags
+ vma_flags_to_legacy(mm->def_vma_flags), &mm->def_vma_flags
);
}
EXPORT_SYMBOL(dump_mm);
diff --git a/mm/mlock.c b/mm/mlock.c
index 8c227fefa2df..9c87b3ced65f 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -699,26 +699,27 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
/*
* Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
- * and translate into the appropriate modifications to mm->def_flags and/or the
- * flags for all current VMAs.
+ * and translate into the appropriate modifications to mm->def_vma_flags and/or
+ * the flags for all current VMAs.
*
* There are a couple of subtleties with this. If mlockall() is called multiple
* times with different flags, the values do not necessarily stack. If mlockall
* is called once including the MCL_FUTURE flag and then a second time without
- * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_vma_flags.
*/
static int apply_mlockall_flags(int flags)
{
VMA_ITERATOR(vmi, current->mm, 0);
+ struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev = NULL;
vm_flags_t to_add = 0;
- current->mm->def_flags &= ~VM_LOCKED_MASK;
+ vma_flags_clear_mask(&mm->def_vma_flags, VMA_LOCKED_MASK);
if (flags & MCL_FUTURE) {
- current->mm->def_flags |= VM_LOCKED;
+ vma_flags_set(&mm->def_vma_flags, VMA_LOCKED_BIT);
if (flags & MCL_ONFAULT)
- current->mm->def_flags |= VM_LOCKONFAULT;
+ vma_flags_set(&mm->def_vma_flags, VMA_LOCKONFAULT_BIT);
if (!(flags & MCL_CURRENT))
goto out;
diff --git a/mm/mmap.c b/mm/mmap.c
index 3ef603d5ff00..477f4a77361a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -102,15 +102,16 @@ void vma_set_page_prot(struct vm_area_struct *vma)
*/
static int check_brk_limits(unsigned long addr, unsigned long len)
{
+ const struct mm_struct *mm = current->mm;
+ const bool is_def_locked =
+ vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT);
unsigned long mapped_addr;
mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
if (IS_ERR_VALUE(mapped_addr))
return mapped_addr;
- return mlock_future_ok(current->mm,
- current->mm->def_flags & VM_LOCKED, len)
- ? 0 : -EAGAIN;
+ return mlock_future_ok(mm, is_def_locked, len) ? 0 : -EAGAIN;
}
SYSCALL_DEFINE1(brk, unsigned long, brk)
@@ -197,7 +198,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
goto out;
mm->brk = brk;
- if (mm->def_flags & VM_LOCKED)
+ if (vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT))
populate = true;
success:
@@ -1247,7 +1248,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, bool is_exec)
vma = vma_prev(&vmi);
ret = do_brk_flags(&vmi, vma, addr, len, vma_flags);
- populate = ((mm->def_flags & VM_LOCKED) != 0);
+ populate = vma_flags_test(&mm->def_vma_flags, VMA_LOCKED_BIT);
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate && !ret)
diff --git a/mm/vma.c b/mm/vma.c
index 3d1ae3cae45f..fb4341943576 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -3424,7 +3424,8 @@ struct vm_area_struct *__install_special_mapping(
if (unlikely(vma == NULL))
return ERR_PTR(-ENOMEM);
- vm_flags |= mm->def_flags | VM_DONTEXPAND;
+ vma_set_range(vma, addr, addr + len, 0);
+ vm_flags |= vma_flags_to_legacy(mm->def_vma_flags) | VM_DONTEXPAND;
if (pgtable_supports_soft_dirty())
vm_flags |= VM_SOFTDIRTY;
vm_flags_init(vma, vm_flags & ~VM_LOCKED_MASK);
@@ -3432,7 +3433,6 @@ struct vm_area_struct *__install_special_mapping(
vma->vm_ops = ops;
vma->vm_private_data = priv;
- vma_set_range(vma, addr, addr + len, 0);
ret = insert_vm_struct(mm, vma);
if (ret)
--
2.54.0
^ permalink raw reply related
* [PATCH 04/13] mm: update generic_get_unmapped_area[_topdown]() to use vma_flags_t
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
As part of the changes converting VMA flags from a system word size to a
bitmap, extend this change to generic_get_unmapped_area() and
generic_get_unmapped_area_topdown(), which also allows us to convert
stack_guard_placement() as well.
We retain arch_get_unmapped_area() and arch_get_unmapped_area_topdown()
as-is for now, using legacy_to_vma_flags() as necessary to do so.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
arch/powerpc/mm/book3s64/slice.c | 6 ++++--
include/linux/sched/mm.h | 4 ++--
mm/mmap.c | 16 ++++++++--------
3 files changed, 14 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index 28bec5bc7879..82127e31dca6 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -659,7 +659,8 @@ unsigned long arch_get_unmapped_area(struct file *filp,
unsigned int psize;
if (radix_enabled())
- return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
+ return generic_get_unmapped_area(filp, addr, len, pgoff, flags,
+ legacy_to_vma_flags(vm_flags));
if (filp && is_file_hugepages(filp))
psize = file_to_psize(filp);
@@ -679,7 +680,8 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
unsigned int psize;
if (radix_enabled())
- return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags);
+ return generic_get_unmapped_area_topdown(filp, addr0, len,
+ pgoff, flags, legacy_to_vma_flags(vm_flags));
if (filp && is_file_hugepages(filp))
psize = file_to_psize(filp);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index b301ec90740a..c8720d8e2158 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -203,11 +203,11 @@ unsigned long mm_get_unmapped_area_vmaflags(struct file *filp,
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags);
+ unsigned long flags, vma_flags_t vma_flags);
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags);
+ unsigned long flags, vma_flags_t vma_flags);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm,
const struct rlimit *rlim_stack) {}
diff --git a/mm/mmap.c b/mm/mmap.c
index 461ce510e12a..3ef603d5ff00 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -657,9 +657,9 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
* Determine if the allocation needs to ensure that there is no
* existing mapping within it's guard gaps, for use as start_gap.
*/
-static inline unsigned long stack_guard_placement(vm_flags_t vm_flags)
+static inline unsigned long stack_guard_placement(vma_flags_t vma_flags)
{
- if (vm_flags & VM_SHADOW_STACK)
+ if (vma_flags_test_single_mask(&vma_flags, VMA_SHADOW_STACK))
return PAGE_SIZE;
return 0;
@@ -701,7 +701,7 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info)
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags)
+ unsigned long flags, vma_flags_t vma_flags)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma, *prev;
@@ -726,7 +726,7 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr,
info.length = len;
info.low_limit = mm->mmap_base;
info.high_limit = mmap_end;
- info.start_gap = stack_guard_placement(vm_flags);
+ info.start_gap = stack_guard_placement(vma_flags);
if (filp && is_file_hugepages(filp))
info.align_mask = huge_page_mask_align(filp);
return vm_unmapped_area(&info);
@@ -739,7 +739,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long flags, vm_flags_t vm_flags)
{
return generic_get_unmapped_area(filp, addr, len, pgoff, flags,
- vm_flags);
+ legacy_to_vma_flags(vm_flags));
}
#endif
@@ -750,7 +750,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long
generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags)
+ unsigned long flags, vma_flags_t vma_flags)
{
struct vm_area_struct *vma, *prev;
struct mm_struct *mm = current->mm;
@@ -778,7 +778,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
info.length = len;
info.low_limit = PAGE_SIZE;
info.high_limit = arch_get_mmap_base(addr, mm->mmap_base);
- info.start_gap = stack_guard_placement(vm_flags);
+ info.start_gap = stack_guard_placement(vma_flags);
if (filp && is_file_hugepages(filp))
info.align_mask = huge_page_mask_align(filp);
addr = vm_unmapped_area(&info);
@@ -807,7 +807,7 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long flags, vm_flags_t vm_flags)
{
return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags,
- vm_flags);
+ legacy_to_vma_flags(vm_flags));
}
#endif
--
2.54.0
^ permalink raw reply related
* [PATCH 03/13] mm: convert __get_unmapped_area() to use vma_flags_t
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
Update __get_unmapped_area() to be parameterised by vma_flags_t rather than
vm_flags_t as part of the effort to move VMA flags from a system word to a
bitmap.
We cascade the changes up to arch_get_unmapped_area_topdown() and
arch_get_unmapped_area(), where, for now, we use vma_flags_to_legacy() in
order to propagate the VMA flags.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
fs/hugetlbfs/inode.c | 3 ++-
include/linux/huge_mm.h | 10 +++++-----
include/linux/mm.h | 6 ++++--
include/linux/sched/mm.h | 12 ++++++------
mm/huge_memory.c | 21 ++++++++++++---------
mm/mmap.c | 27 ++++++++++++++-------------
6 files changed, 43 insertions(+), 36 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 894d02e73302..fe7d5a5d60bd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -184,7 +184,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
if (addr)
addr0 = ALIGN(addr, huge_page_size(h));
- return mm_get_unmapped_area_vmflags(file, addr0, len, pgoff, flags, 0);
+ return mm_get_unmapped_area_vmaflags(file, addr0, len, pgoff, flags,
+ EMPTY_VMA_FLAGS);
}
/*
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 653b81d08fe7..ae84a714907f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -391,9 +391,9 @@ static inline bool thp_disabled_by_hw(void)
unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags);
-unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
+unsigned long thp_get_unmapped_area_vmaflags(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags,
- vm_flags_t vm_flags);
+ vma_flags_t vma_flags);
enum split_type {
SPLIT_TYPE_UNIFORM,
@@ -615,9 +615,9 @@ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
#define thp_get_unmapped_area NULL
static inline unsigned long
-thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags)
+thp_get_unmapped_area_vmaflags(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags, vma_flags_t vma_flags)
{
return 0;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cc2a87755adb..474b3698f565 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4160,13 +4160,15 @@ unsigned long randomize_page(unsigned long start, unsigned long range);
unsigned long
__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
- unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags);
+ unsigned long pgoff, unsigned long flags,
+ vma_flags_t vma_flags);
static inline unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
- return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
+ return __get_unmapped_area(file, addr, len, pgoff, flags,
+ EMPTY_VMA_FLAGS);
}
unsigned long do_mmap(struct file *file, unsigned long addr,
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 95d0040df584..b301ec90740a 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -193,12 +193,12 @@ unsigned long mm_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
-unsigned long mm_get_unmapped_area_vmflags(struct file *filp,
- unsigned long addr,
- unsigned long len,
- unsigned long pgoff,
- unsigned long flags,
- vm_flags_t vm_flags);
+unsigned long mm_get_unmapped_area_vmaflags(struct file *filp,
+ unsigned long addr,
+ unsigned long len,
+ unsigned long pgoff,
+ unsigned long flags,
+ vma_flags_t vma_flags);
unsigned long
generic_get_unmapped_area(struct file *filp, unsigned long addr,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e94f56487225..d6c5f51ee399 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1196,7 +1196,7 @@ static inline bool is_transparent_hugepage(const struct folio *folio)
static unsigned long __thp_get_unmapped_area(struct file *filp,
unsigned long addr, unsigned long len,
loff_t off, unsigned long flags, unsigned long size,
- vm_flags_t vm_flags)
+ vma_flags_t vma_flags)
{
loff_t off_end = off + len;
loff_t off_align = round_up(off, size);
@@ -1212,8 +1212,9 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
if (len_pad < len || (off + len_pad) < off)
return 0;
- ret = mm_get_unmapped_area_vmflags(filp, addr, len_pad,
- off >> PAGE_SHIFT, flags, vm_flags);
+ ret = mm_get_unmapped_area_vmaflags(filp, addr, len_pad,
+ off >> PAGE_SHIFT, flags,
+ vma_flags);
/*
* The failure might be due to length padding. The caller will retry
@@ -1238,25 +1239,27 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
return ret;
}
-unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
+unsigned long thp_get_unmapped_area_vmaflags(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags,
- vm_flags_t vm_flags)
+ vma_flags_t vma_flags)
{
unsigned long ret;
loff_t off = (loff_t)pgoff << PAGE_SHIFT;
- ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags);
+ ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE,
+ vma_flags);
if (ret)
return ret;
- return mm_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags,
- vm_flags);
+ return mm_get_unmapped_area_vmaflags(filp, addr, len, pgoff, flags,
+ vma_flags);
}
unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff, unsigned long flags)
{
- return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0);
+ return thp_get_unmapped_area_vmaflags(filp, addr, len, pgoff, flags,
+ EMPTY_VMA_FLAGS);
}
EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
diff --git a/mm/mmap.c b/mm/mmap.c
index 547352183214..461ce510e12a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -411,8 +411,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
/* Obtain the address to map to. we verify (or select) it and ensure
* that it represents a valid section of the address space.
*/
- addr = __get_unmapped_area(file, addr, len, pgoff, flags,
- vma_flags_to_legacy(vma_flags));
+ addr = __get_unmapped_area(file, addr, len, pgoff, flags, vma_flags);
if (IS_ERR_VALUE(addr))
return addr;
@@ -812,19 +811,20 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
}
#endif
-unsigned long mm_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags, vm_flags_t vm_flags)
+unsigned long mm_get_unmapped_area_vmaflags(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags, vma_flags_t vma_flags)
{
if (mm_flags_test(MMF_TOPDOWN, current->mm))
return arch_get_unmapped_area_topdown(filp, addr, len, pgoff,
- flags, vm_flags);
- return arch_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
+ flags, vma_flags_to_legacy(vma_flags));
+ return arch_get_unmapped_area(filp, addr, len, pgoff, flags,
+ vma_flags_to_legacy(vma_flags));
}
unsigned long
__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
- unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
+ unsigned long pgoff, unsigned long flags, vma_flags_t vma_flags)
{
unsigned long (*get_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long)
@@ -859,11 +859,11 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
&& !addr /* no hint */
&& IS_ALIGNED(len, PMD_SIZE)) {
/* Ensures that larger anonymous mappings are THP aligned. */
- addr = thp_get_unmapped_area_vmflags(file, addr, len,
- pgoff, flags, vm_flags);
+ addr = thp_get_unmapped_area_vmaflags(file, addr, len,
+ pgoff, flags, vma_flags);
} else {
- addr = mm_get_unmapped_area_vmflags(file, addr, len,
- pgoff, flags, vm_flags);
+ addr = mm_get_unmapped_area_vmaflags(file, addr, len,
+ pgoff, flags, vma_flags);
}
if (IS_ERR_VALUE(addr))
return addr;
@@ -881,7 +881,8 @@ unsigned long
mm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
- return mm_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, 0);
+ return mm_get_unmapped_area_vmaflags(file, addr, len, pgoff, flags,
+ EMPTY_VMA_FLAGS);
}
EXPORT_SYMBOL(mm_get_unmapped_area);
--
2.54.0
^ permalink raw reply related
* [PATCH 02/13] mm/vma: update do_mmap() to use vma_flags_t
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
The core do_mmap() function accepts a vm_flags_t parameter which it then
manipulates before passing to mmap_region() to do the heavy lifting of the
memory mapping.
Update do_mmap() to instead accept a vma_flags_t parameter, and adjust all
the logic within do_mmap() to manipulate this instead.
This is as part of the ongoing effort to convert VMA flags from a system
word size to a bitmap type which allows us to unrestrict the number of VMA
flags, as well as gain control over how VMA flag manipulation occurs.
We do not cascade these changes to all functions which accept vm_flags_t,
but rather use vma_flags_to_legacy() where necessary, specifically
deferring converting calc_vm_prot_bits(), calc_vm_flag_bits() and
__get_unmapped_area() to vma_flags_t.
Also utilise the new vma_flags_can_grow() predicate which correctly handles
the case of architectures without upward growing stacks.
As part of this change, introduce VMA_SHADOW_STACK so we can correctly
handle the case of the shadow stack not being defined.
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
arch/mips/kernel/vdso.c | 4 +--
fs/aio.c | 2 +-
include/linux/memfd.h | 6 ++--
include/linux/mm.h | 6 ++--
ipc/shm.c | 3 +-
mm/memfd.c | 15 ++++-----
mm/mmap.c | 67 ++++++++++++++++++++++++-----------------
mm/nommu.c | 3 +-
mm/util.c | 10 +++---
mm/vma.c | 7 ++---
mm/vma.h | 2 +-
11 files changed, 69 insertions(+), 56 deletions(-)
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index bd1fc17d3975..94873775fc0f 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -91,8 +91,8 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
/* Map delay slot emulation page */
base = do_mmap(NULL, STACK_TOP, PAGE_SIZE, PROT_READ | PROT_EXEC,
- MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, 0, 0, &unused,
- NULL);
+ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED,
+ EMPTY_VMA_FLAGS, 0, &unused, NULL);
if (IS_ERR_VALUE(base)) {
ret = base;
goto out;
diff --git a/fs/aio.c b/fs/aio.c
index f57fa21a2503..3de586da197b 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -604,7 +604,7 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events)
ctx->mmap_base = do_mmap(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_SHARED, 0, 0, &unused, NULL);
+ MAP_SHARED, EMPTY_VMA_FLAGS, 0, &unused, NULL);
mmap_write_unlock(mm);
if (IS_ERR((void *)ctx->mmap_base)) {
ctx->mmap_size = 0;
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index b4fda09dab9f..c159e40e3f34 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -14,9 +14,9 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
* to sealing, or 0 otherwise.
*
* We also update VMA flags if appropriate by manipulating the VMA flags pointed
- * to by vm_flags_ptr.
+ * to by vma_flags_ptr.
*/
-int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr);
+int memfd_check_seals_mmap(struct file *file, vma_flags_t *vma_flags_ptr);
struct file *memfd_alloc_file(const char *name, unsigned int flags);
int memfd_get_seals(struct file *file);
int memfd_add_seals(struct file *file, unsigned int seals);
@@ -30,7 +30,7 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
return ERR_PTR(-EINVAL);
}
static inline int memfd_check_seals_mmap(struct file *file,
- vm_flags_t *vm_flags_ptr)
+ vma_flags_t *vma_flags_ptr)
{
return 0;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cf7df1569052..cc2a87755adb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -463,9 +463,11 @@ enum {
#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS) || \
defined(CONFIG_RISCV_USER_CFI)
#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK)
+#define VMA_SHADOW_STACK mk_vma_flags(VMA_SHADOW_STACK_BIT)
#define VMA_STARTGAP_FLAGS mk_vma_flags(VMA_GROWSDOWN_BIT, VMA_SHADOW_STACK_BIT)
#else
#define VM_SHADOW_STACK VM_NONE
+#define VMA_SHADOW_STACK EMPTY_VMA_FLAGS
#define VMA_STARTGAP_FLAGS mk_vma_flags(VMA_GROWSDOWN_BIT)
#endif
#if defined(CONFIG_PPC64)
@@ -4167,9 +4169,9 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
}
-extern unsigned long do_mmap(struct file *file, unsigned long addr,
+unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot, unsigned long flags,
- vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
+ vma_flags_t vma_flags, unsigned long pgoff, unsigned long *populate,
struct list_head *uf);
extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
unsigned long start, size_t len, struct list_head *uf,
diff --git a/ipc/shm.c b/ipc/shm.c
index b3e8a58e177d..bb1a721a3e74 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1661,7 +1661,8 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
goto invalid;
}
- addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL);
+ addr = do_mmap(file, addr, size, prot, flags, EMPTY_VMA_FLAGS, 0,
+ &populate, NULL);
*raddr = addr;
err = 0;
if (IS_ERR_VALUE(addr))
diff --git a/mm/memfd.c b/mm/memfd.c
index abe13b291ddc..a4c9c1358862 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -369,39 +369,36 @@ static inline bool is_write_sealed(unsigned int seals)
return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
}
-static int check_write_seal(vm_flags_t *vm_flags_ptr)
+static int check_write_seal(vma_flags_t *vma_flags_ptr)
{
- vm_flags_t vm_flags = *vm_flags_ptr;
- vm_flags_t mask = vm_flags & (VM_SHARED | VM_WRITE);
-
/* If a private mapping then writability is irrelevant. */
- if (!(mask & VM_SHARED))
+ if (!vma_flags_test(vma_flags_ptr, VMA_SHARED_BIT))
return 0;
/*
* New PROT_WRITE and MAP_SHARED mmaps are not allowed when
* write seals are active.
*/
- if (mask & VM_WRITE)
+ if (vma_flags_test(vma_flags_ptr, VMA_WRITE_BIT))
return -EPERM;
/*
* This is a read-only mapping, disallow mprotect() from making a
* write-sealed mapping writable in future.
*/
- *vm_flags_ptr &= ~VM_MAYWRITE;
+ vma_flags_clear(vma_flags_ptr, VMA_MAYWRITE_BIT);
return 0;
}
-int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr)
+int memfd_check_seals_mmap(struct file *file, vma_flags_t *vma_flags_ptr)
{
int err = 0;
unsigned int *seals_ptr = memfd_file_seals_ptr(file);
unsigned int seals = seals_ptr ? *seals_ptr : 0;
if (is_write_sealed(seals))
- err = check_write_seal(vm_flags_ptr);
+ err = check_write_seal(vma_flags_ptr);
return err;
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 46174e706bbe..547352183214 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -280,7 +280,7 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode,
* do_mmap() - Perform a userland memory mapping into the current process
* address space of length @len with protection bits @prot, mmap flags @flags
* (from which VMA flags will be inferred), and any additional VMA flags to
- * apply @vm_flags. If this is a file-backed mapping then the file is specified
+ * apply @vma_flags. If this is a file-backed mapping then the file is specified
* in @file and page offset into the file via @pgoff.
*
* This function does not perform security checks on the file and assumes, if
@@ -320,7 +320,8 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode,
* (2) for details.
* @flags: Flags specifying how the mapping should be performed, see mmap (2)
* for details.
- * @vm_flags: VMA flags which should be set by default, or 0 otherwise.
+ * @vma_flags: VMA flags which should be set by default, or EMPTY_VMA_FLAGS
+ * otherwise.
* @pgoff: Page offset into the @file if file-backed, should be 0 otherwise.
* @populate: A pointer to a value which will be set to 0 if no population of
* the range is required, or the number of bytes to populate if it is. Must be
@@ -335,7 +336,7 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode,
*/
unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
- unsigned long flags, vm_flags_t vm_flags,
+ unsigned long flags, vma_flags_t vma_flags,
unsigned long pgoff, unsigned long *populate,
struct list_head *uf)
{
@@ -399,13 +400,19 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
* to. we assume access permissions have been handled by the open
* of the memory object, so we don't do any here.
*/
- vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) |
- mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+ vma_flags_set_mask(&vma_flags,
+ legacy_to_vma_flags(calc_vm_prot_bits(prot, pkey)));
+ vma_flags_set_mask(&vma_flags,
+ legacy_to_vma_flags(calc_vm_flag_bits(file, flags)));
+ vma_flags_set_mask(&vma_flags, mm->def_vma_flags);
+ vma_flags_set(&vma_flags, VMA_MAYREAD_BIT, VMA_MAYWRITE_BIT,
+ VMA_MAYEXEC_BIT);
/* Obtain the address to map to. we verify (or select) it and ensure
* that it represents a valid section of the address space.
*/
- addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags);
+ addr = __get_unmapped_area(file, addr, len, pgoff, flags,
+ vma_flags_to_legacy(vma_flags));
if (IS_ERR_VALUE(addr))
return addr;
@@ -418,7 +425,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
if (!can_do_mlock())
return -EPERM;
- if (!mlock_future_ok(mm, vm_flags & VM_LOCKED, len))
+ if (!mlock_future_ok(mm, vma_flags_test(&vma_flags, VMA_LOCKED_BIT), len))
return -EAGAIN;
if (file) {
@@ -461,22 +468,23 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
return -EACCES;
- vm_flags |= VM_SHARED | VM_MAYSHARE;
+ vma_flags_set(&vma_flags, VMA_SHARED_BIT, VMA_MAYSHARE_BIT);
if (!(file->f_mode & FMODE_WRITE))
- vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
+ vma_flags_clear(&vma_flags, VMA_MAYWRITE_BIT,
+ VMA_SHARED_BIT);
fallthrough;
case MAP_PRIVATE:
if (!(file->f_mode & FMODE_READ))
return -EACCES;
if (path_noexec(&file->f_path)) {
- if (vm_flags & VM_EXEC)
+ if (vma_flags_test(&vma_flags, VMA_EXEC_BIT))
return -EPERM;
- vm_flags &= ~VM_MAYEXEC;
+ vma_flags_clear(&vma_flags, VMA_MAYEXEC_BIT);
}
if (!can_mmap_file(file))
return -ENODEV;
- if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+ if (vma_flags_can_grow(&vma_flags))
return -EINVAL;
break;
@@ -488,23 +496,27 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
* Check to see if we are violating any seals and update VMA
* flags if necessary to avoid future seal violations.
*/
- err = memfd_check_seals_mmap(file, &vm_flags);
+ err = memfd_check_seals_mmap(file, &vma_flags);
if (err)
return (unsigned long)err;
} else {
switch (flags & MAP_TYPE) {
case MAP_SHARED:
- if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+ if (vma_flags_can_grow(&vma_flags))
return -EINVAL;
/*
* Ignore pgoff.
*/
pgoff = 0;
- vm_flags |= VM_SHARED | VM_MAYSHARE;
+ vma_flags_set(&vma_flags, VMA_SHARED_BIT, VMA_MAYSHARE_BIT);
break;
- case MAP_DROPPABLE:
- if (VM_DROPPABLE == VM_NONE)
+ case MAP_DROPPABLE: {
+ vma_flags_t droppable = VMA_DROPPABLE;
+
+ if (vma_flags_empty(&droppable))
return -EOPNOTSUPP;
+ vma_flags_set_mask(&vma_flags, droppable);
+
/*
* A locked or stack area makes no sense to be droppable.
*
@@ -515,23 +527,24 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
*/
if (flags & (MAP_LOCKED | MAP_HUGETLB))
return -EINVAL;
- if (vm_flags & (VM_GROWSDOWN | VM_GROWSUP))
+ if (vma_flags_can_grow(&vma_flags))
return -EINVAL;
- vm_flags |= VM_DROPPABLE;
-
/*
* If the pages can be dropped, then it doesn't make
* sense to reserve them.
*/
- vm_flags |= VM_NORESERVE;
+ vma_flags_set(&vma_flags, VMA_NORESERVE_BIT);
/*
* Likewise, they're volatile enough that they
* shouldn't survive forks or coredumps.
*/
- vm_flags |= VM_WIPEONFORK | VM_DONTDUMP;
+ vma_flags_set(&vma_flags, VMA_WIPEONFORK_BIT,
+ VMA_DONTDUMP_BIT);
+
fallthrough;
+ }
case MAP_PRIVATE:
/*
* Set pgoff according to addr for anon_vma.
@@ -550,16 +563,16 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
if (flags & MAP_NORESERVE) {
/* We honor MAP_NORESERVE if allowed to overcommit */
if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
- vm_flags |= VM_NORESERVE;
+ vma_flags_set(&vma_flags, VMA_NORESERVE_BIT);
/* hugetlb applies strict overcommit unless MAP_NORESERVE */
if (file && is_file_hugepages(file))
- vm_flags |= VM_NORESERVE;
+ vma_flags_set(&vma_flags, VMA_NORESERVE_BIT);
}
- addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
+ addr = mmap_region(file, addr, len, vma_flags, pgoff, uf);
if (!IS_ERR_VALUE(addr) &&
- ((vm_flags & VM_LOCKED) ||
+ (vma_flags_test(&vma_flags, VMA_LOCKED_BIT) ||
(flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
*populate = len;
return addr;
@@ -1191,7 +1204,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
}
ret = do_mmap(vma->vm_file, start, size,
- prot, flags, 0, pgoff, &populate, NULL);
+ prot, flags, EMPTY_VMA_FLAGS, pgoff, &populate, NULL);
out:
mmap_write_unlock(mm);
fput(file);
diff --git a/mm/nommu.c b/mm/nommu.c
index 4fef6fbbd6e9..47dc8bdd18e7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1014,11 +1014,12 @@ unsigned long do_mmap(struct file *file,
unsigned long len,
unsigned long prot,
unsigned long flags,
- vm_flags_t vm_flags,
+ vma_flags_t vma_flags,
unsigned long pgoff,
unsigned long *populate,
struct list_head *uf)
{
+ vm_flags_t vm_flags = vma_flags_to_legacy(vma_flags);
struct vm_area_struct *vma;
struct vm_region *region;
struct rb_node *rb;
diff --git a/mm/util.c b/mm/util.c
index 61e6d32b2c16..befb16c6ea0e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -578,8 +578,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
if (!ret) {
if (mmap_write_lock_killable(mm))
return -EINTR;
- ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate,
- &uf);
+ ret = do_mmap(file, addr, len, prot, flag, EMPTY_VMA_FLAGS, pgoff,
+ &populate, &uf);
mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
@@ -627,20 +627,20 @@ EXPORT_SYMBOL(vm_mmap);
unsigned long vm_mmap_shadow_stack(unsigned long addr, unsigned long len,
unsigned long flags)
{
+ vma_flags_t vma_flags = VMA_SHADOW_STACK;
struct mm_struct *mm = current->mm;
unsigned long ret, unused;
- vm_flags_t vm_flags = VM_SHADOW_STACK;
flags |= MAP_ANONYMOUS | MAP_PRIVATE;
if (addr)
flags |= MAP_FIXED_NOREPLACE;
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
- vm_flags |= VM_NOHUGEPAGE;
+ vma_flags_set(&vma_flags, VMA_NOHUGEPAGE_BIT);
mmap_write_lock(mm);
ret = do_mmap(NULL, addr, len, PROT_READ | PROT_WRITE, flags,
- vm_flags, 0, &unused, NULL);
+ vma_flags, 0, &unused, NULL);
mmap_write_unlock(mm);
return ret;
diff --git a/mm/vma.c b/mm/vma.c
index 7201199fc668..3d1ae3cae45f 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2881,7 +2881,7 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
* file to be mapped, otherwise NULL.
* @addr: The page-aligned address at which to perform the mapping.
* @len: The page-aligned, non-zero, length of the mapping.
- * @vm_flags: The VMA flags which should be applied to the mapping.
+ * @vma_flags: The VMA flags which should be applied to the mapping.
* @pgoff: If @file is specified, the page offset into the file, if not then
* the virtual page offset in memory of the anonymous mapping.
* @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap
@@ -2891,12 +2891,11 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
* been performed.
*/
unsigned long mmap_region(struct file *file, unsigned long addr,
- unsigned long len, vm_flags_t vm_flags,
+ unsigned long len, vma_flags_t vma_flags,
unsigned long pgoff, struct list_head *uf)
{
unsigned long ret;
bool writable_file_mapping = false;
- const vma_flags_t vma_flags = legacy_to_vma_flags(vm_flags);
mmap_assert_write_locked(current->mm);
@@ -2905,7 +2904,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
return -EACCES;
/* Allow architectures to sanity-check the vm_flags. */
- if (!arch_validate_flags(vm_flags))
+ if (!arch_validate_flags(vma_flags_to_legacy(vma_flags)))
return -EINVAL;
/* Map writable and ensure this isn't a sealed memfd. */
diff --git a/mm/vma.h b/mm/vma.h
index f4f885615a92..bcf0c2773449 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -498,7 +498,7 @@ int mm_take_all_locks(struct mm_struct *mm);
void mm_drop_all_locks(struct mm_struct *mm);
unsigned long mmap_region(struct file *file, unsigned long addr,
- unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+ unsigned long len, vma_flags_t vma_flags, unsigned long pgoff,
struct list_head *uf);
int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
--
2.54.0
^ permalink raw reply related
* [PATCH 01/13] mm: introduce vma_flags_can_grow() and vma_can_grow()
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
In-Reply-To: <cover.1782760670.git.ljs@kernel.org>
These test whether the VMA has stack sematics, i.e. is able to grow upwards
or downwards depending on the architecture.
In order to account for arches which do not support upward-growing stacks,
introduce VMA_GROWSUP whose definition depends on the architecture
supporting it, and use vma_flags_test_single_mask() in vma_flags_can_grow()
to account for this.
Update the VMA userland tests to reflect the changes
No functional change intended.
Signed-off-by: Lorenzo Stoakes <ljs@kernel.org>
---
include/linux/mm.h | 21 ++++++++++++++++++---
tools/testing/vma/include/dup.h | 4 ++++
2 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 868b2334bff3..cf7df1569052 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -472,6 +472,7 @@ enum {
#define VM_SAO INIT_VM_FLAG(SAO)
#elif defined(CONFIG_PARISC)
#define VM_GROWSUP INIT_VM_FLAG(GROWSUP)
+#define VMA_GROWSUP mk_vma_flags(VMA_GROWSUP_BIT)
#elif defined(CONFIG_SPARC64)
#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI)
#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR)
@@ -483,6 +484,7 @@ enum {
#endif
#ifndef VM_GROWSUP
#define VM_GROWSUP VM_NONE
+#define VMA_GROWSUP EMPTY_VMA_FLAGS
#endif
#ifdef CONFIG_ARM64_MTE
#define VM_MTE INIT_VM_FLAG(MTE)
@@ -1563,11 +1565,24 @@ static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
vma->vm_end >= vma->vm_mm->start_stack;
}
-static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma)
+static inline bool vma_flags_can_grow(const vma_flags_t *flags)
{
- int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
+ if (vma_flags_test_single_mask(flags, VMA_GROWSUP))
+ return true;
+ if (vma_flags_test(flags, VMA_GROWSDOWN_BIT))
+ return true;
+
+ return false;
+}
- if (!maybe_stack)
+static inline bool vma_can_grow(const struct vm_area_struct *vma)
+{
+ return vma_flags_can_grow(&vma->flags);
+}
+
+static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma)
+{
+ if (!vma_can_grow(vma))
return false;
if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 5d7d0afd7765..6f5bcd7fbcd8 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -245,8 +245,10 @@ enum {
#define VM_STACK INIT_VM_FLAG(STACK)
#ifdef CONFIG_STACK_GROWS_UP
#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY)
+#define VMA_STACK_EARLY mk_vma_flags(VMA_STACK_EARLY_BIT)
#else
#define VM_STACK_EARLY VM_NONE
+#define VMA_STACK_EARLY EMPTY_VMA_FLAGS
#endif
#ifdef CONFIG_ARCH_HAS_PKEYS
#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT)
@@ -315,6 +317,8 @@ enum {
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
+#define VMA_STACK_INCOMPLETE_SETUP append_vma_flags( \
+ VMA_STACK_EARLY, VMA_RAND_READ_BIT, VMA_SEQ_READ_BIT)
#define TASK_EXEC_BIT ((current->personality & READ_IMPLIES_EXEC) ? \
VM_EXEC_BIT : VM_READ_BIT)
--
2.54.0
^ permalink raw reply related
* [PATCH 00/13] convert more vm_flags_t users to vma_flags_t
From: Lorenzo Stoakes @ 2026-06-29 19:25 UTC (permalink / raw)
To: Andrew Morton
Cc: Thomas Bogendoerfer, Madhavan Srinivasan, Michael Ellerman,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Lucas Stach, Inki Dae, Seung-Woo Kim,
Kyungmin Park, Krzysztof Kozlowski, Peter Griffin, Jani Nikula,
Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin, Rob Clark,
Dmitry Baryshkov, Lyude Paul, Danilo Krummrich, Tomi Valkeinen,
Sandy Huang, Heiko Stübner, Andy Yan, Thierry Reding,
Mikko Perttunen, Jonathan Hunter, Gerd Hoffmann, Dmitry Osipenko,
Zack Rusin, Matthew Brost, Thomas Hellstrom,
Oleksandr Andrushchenko, Helge Deller, Benjamin LaHaise,
Alexander Viro, Christian Brauner, Muchun Song, Oscar Salvador,
David Hildenbrand, Zi Yan, Baolin Wang, Liam R . Howlett,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Hugh Dickins, Vlastimil Babka, Mike Rapoport, Suren Baghdasaryan,
Michal Hocko, Jann Horn, Pedro Falcato, Kees Cook,
Jaroslav Kysela, Takashi Iwai, linux-mips, linux-kernel,
linuxppc-dev, dri-devel, etnaviv, linux-arm-kernel,
linux-samsung-soc, intel-gfx, linux-arm-msm, freedreno, nouveau,
linux-rockchip, linux-tegra, virtualization, intel-xe, xen-devel,
linux-fbdev, linux-aio, linux-fsdevel, linux-mm, linux-sound
This series makes further progress in converting usage of the deprecated
vm_flags_t type to its replacement, vma_flags_t.
It focuses on mm, though updates some users of mm APIs also.
It updates:
* The core do_mmap() code path for VMA mapping.
* Unmapped area logic.
* The usage of mm->def_vma_flags.
* VMA page protection bit logic.
* General usage of VMA flags in core mm code, mlock, mprotect, mremap.
REVIEWER/MERGER NOTE: This is dependent on [0], which must be merged before
this.
[0]:https://lore.kernel.org/linux-mm/cover.1782735110.git.ljs@kernel.org/
Lorenzo Stoakes (13):
mm: introduce vma_flags_can_grow() and vma_can_grow()
mm/vma: update do_mmap() to use vma_flags_t
mm: convert __get_unmapped_area() to use vma_flags_t
mm: update generic_get_unmapped_area[_topdown]() to use vma_flags_t
mm: prefer mm->def_vma_flags in mm logic
mm/vma: convert vm_pgprot_modify() to use vma_flags_t and rename
mm/vma: rename vma_get_page_prot to vma_flags_to_page_prot
mm: introduce vma_get_page_prot() and use it
mm/vma: update create_init_stack_vma() to use vma_flags_t
mm/vma: convert miscellaneous uses of VMA flags in core mm
mm/mlock: convert mlock code to use vma_flags_t
mm/mprotect: convert mprotect code to use vma_flags_t
mm/mremap: convert mremap code to use vma_flags_t
arch/mips/kernel/vdso.c | 4 +-
arch/powerpc/mm/book3s64/slice.c | 6 +-
drivers/gpu/drm/drm_gem.c | 2 +-
drivers/gpu/drm/drm_gem_dma_helper.c | 2 +-
drivers/gpu/drm/drm_gem_shmem_helper.c | 2 +-
drivers/gpu/drm/etnaviv/etnaviv_gem.c | 2 +-
drivers/gpu/drm/exynos/exynos_drm_gem.c | 6 +-
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 12 +-
drivers/gpu/drm/msm/msm_gem.c | 2 +-
drivers/gpu/drm/nouveau/nouveau_gem.c | 2 +-
drivers/gpu/drm/omapdrm/omap_fbdev.c | 2 +-
drivers/gpu/drm/omapdrm/omap_gem.c | 6 +-
drivers/gpu/drm/rockchip/rockchip_drm_gem.c | 2 +-
drivers/gpu/drm/tegra/gem.c | 2 +-
drivers/gpu/drm/virtio/virtgpu_vram.c | 2 +-
drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 2 +-
drivers/gpu/drm/xe/xe_device.c | 2 +-
drivers/gpu/drm/xe/xe_mmio_gem.c | 2 +-
drivers/gpu/drm/xen/xen_drm_front_gem.c | 2 +-
drivers/video/fbdev/core/fb_io_fops.c | 2 +-
fs/aio.c | 2 +-
fs/hugetlbfs/inode.c | 3 +-
include/linux/huge_mm.h | 10 +-
include/linux/memfd.h | 6 +-
include/linux/mm.h | 51 ++++--
include/linux/sched/mm.h | 16 +-
ipc/shm.c | 3 +-
mm/debug.c | 2 +-
mm/huge_memory.c | 21 +--
mm/memfd.c | 15 +-
mm/mlock.c | 97 ++++++------
mm/mmap.c | 164 +++++++++++---------
mm/mprotect.c | 16 +-
mm/mremap.c | 38 ++---
mm/nommu.c | 3 +-
mm/util.c | 10 +-
mm/vma.c | 27 ++--
mm/vma.h | 8 +-
mm/vma_exec.c | 20 ++-
sound/core/memalloc.c | 2 +-
tools/testing/vma/include/dup.h | 22 ++-
41 files changed, 339 insertions(+), 261 deletions(-)
--
2.54.0
^ permalink raw reply
* Re: [RFC 1/3] powerpc/perf: Register PMU from device tree and expose events
From: Krzysztof Kozlowski @ 2026-06-29 18:47 UTC (permalink / raw)
To: Shivani Nittor, maddy, linuxppc-dev; +Cc: linux-kernel, atrajeev, tshah
In-Reply-To: <20260629061101.43119-2-shivani@linux.ibm.com>
On 29/06/2026 08:10, Shivani Nittor wrote:
> Introduce a DTS-based PMU driver that discovers PMU information
> from the device tree and registers a PowerPC PMU instance at
> runtime.
>
> The driver parses basic PMU properties such as the number of
> counters and MMCR register definitions, creates sysfs event
> entries from the device tree event descriptions, and registers
> the PMU with the perf subsystem.
>
> To support dynamic PMU registration, add PMU unregistration
> support and create a platform device for PMU nodes described
> in the device tree.
>
> This forms the foundation for moving PMU descriptions out of
> architecture-specific kernel code and into device tree data.
>
> The driver implements the following functionality:
>
> Device Tree Parsing:
> - Reads PMU properties including counter count (nr_pmc), PMU name,
> version, and platform information
> - Parses MMCR (Monitor Mode Control Register) definitions from the
> sprs/mmcr node hierarchy, storing the MMCR register SPRNs
> - Extracts event definitions from the events node, supporting both
> 32-bit and 64-bit event codes
>
> Dynamic Event Registration:
> - Creates sysfs event entries dynamically from device tree event
> descriptions
> - Generates event attributes with format "event=0x<code>" for each
> discovered event
> - Exposes events under /sys/devices/<pmu-name>/events/
>
> PMU Registration:
> - Registers a power_pmu instance with the perf subsystem using the
> device tree-provided PMU name
> - Adds PMU unregistration support to enable proper cleanup
> - Creates platform device for "ibm,power-pmu" compatible nodes
>
> Sysfs Interface:
> - Provides format attributes (event, pmcsel) under
> /sys/devices/<pmu-name>/format/
> - Exposes device tree debug information (nr_pmc) under
> /sys/devices/<pmu-name>/dt/
Where did you document the ABI?
...
> +static struct power_pmu dts_pmu = {
> + .name = "cpu_dts",
> + .n_counter = MAX_PMU_COUNTERS,
> + .attr_groups = pmu_dts_attr_groups,
> +};
> +
> +/* Device Tree match */
That's obvious. Can of_device_id be something else than DT match?
> +static const struct of_device_id pmu_dts_of_match[] = {
> + { .compatible = "ibm,power-pmu" },
Where is ABI documented?
> + { }
> +};
> +MODULE_DEVICE_TABLE(of, pmu_dts_of_match);
> +
> +/* Probe function */
> +static int pmu_dts_probe(struct platform_device *pdev)
> +{
> + struct device_node *np = pdev->dev.of_node, *child, *events_np;
> + struct device_node *sprs_np, *mmcr_np, *mmcr_child;
> + struct pmu_dts_event *evt;
> + u64 code;
> + u32 code32, sprn;
> + u32 code64[2];
> + u32 code128[4];
> + int cells;
> + const char *str;
> +
> + pr_info("PMU DTS probe node = %s\n", np->full_name);
This does not look like useful printk message. Drivers should be silent
on success:
https://elixir.bootlin.com/linux/v6.15-rc7/source/Documentation/process/coding-style.rst#L913
https://elixir.bootlin.com/linux/v6.15-rc7/source/Documentation/process/debugging/driver_development_debugging_guide.rst#L79
> +
> + if (!of_property_present(np, "nr_pmc")) {
> +
> + for_each_child_of_node(np, child) {
> + pr_info("child node = %s\n", child->full_name);
Why are you sending debugging code?
> +
> + if (of_property_present(child, "nr_pmc")) {
> + np = child;
> + break;
> + }
> + }
> + }
> +
> + if (of_property_read_u32(np, "nr_pmc", &pmu_dts_nr_pmc)) {
> + pr_err("pmu_dts: nr_pmc not found in %s\n", np->full_name);
Why isn't this using dev interface?
> + return -EINVAL;
> + }
> +
> + if (!of_property_read_string(np, "pmu-name", &str))
> + pr_info("PMU Name: %s\n", str);
> +
> + if (!of_property_read_string(np, "pmu-version", &str))
> + pr_info("PMU Version: %s\n", str);
> +
> + if (!of_property_read_string(np, "platform", &str))
No, you cannot just add bunch of undocumented ABI and call it a day.
> + pr_info("Platform: %s\n", str);
> +
> + sprs_np = of_get_child_by_name(np, "sprs");
> + if (!sprs_np) {
> + pr_err("pmu_dts: no sprs node\n");
> + return -EINVAL;
> + }
> +
> + mmcr_np = of_get_child_by_name(sprs_np, "mmcr");
> + if (!mmcr_np) {
> + pr_err("pmu_dts: no mmcr node\n");
> + return -EINVAL;
> + }
> +
> + mmcr_count = 0;
> + for_each_child_of_node(mmcr_np, mmcr_child) {
> +
> + if (of_property_read_u32(mmcr_child, "sprn", &sprn))
> + continue;
> +
> + mmcr_regs_sprs[mmcr_count++] = sprn;
> + pr_info("pmu_dts: MMCR[%d] = %u (%s)\n", mmcr_count - 1,
> + sprn, mmcr_child->name);
> +
> + if (mmcr_count >= MAX_MMCR)
> + break;
Where is cleanup?
> + }
> +
> + if (!mmcr_count) {
> + pr_err("pmu_dts: no MMCR SPRs found\n");
> + return -EINVAL;
> + }
> +
> + /* Parse events */
> + events_np = of_get_child_by_name(np, "events");
> + if (!events_np) {
> + pr_err("pmu_dts: no events node found\n");
> + return -EINVAL;
> + }
> +
> + dts_event_count = 0;
> + for_each_child_of_node(events_np, child) {
> + if (!of_device_is_available(child))
Why are you open-coding available variant of loop?
> + continue;
> +
> + cells = of_property_count_u32_elems(child, "event_code");
> + if (cells == 1) {
> + if (of_property_read_u32(child, "event_code", &code32))
> + continue;
> +
> + code = code32;
> +
> + } else if (cells == 2) {
> + if (of_property_read_u32_array(child, "event_code", code64, 2))
> + continue;
> + code = ((u64)code64[0] << 32) | code64[1];
> +
> + } else if (cells == 4) {
> + if (of_property_read_u32_array(child, "event_code", code128, 4))
> + continue;
> + code = ((u64)code128[1] << 32) | code128[3];
> +
> + } else {
> + pr_warn("pmu_dts: invalid event_code for %s\n", child->name);
> + continue;
> + }
> +
> + evt = kzalloc(sizeof(*evt), GFP_KERNEL);
> + if (!evt)
> + continue;
> +
> + snprintf(evt->name, sizeof(evt->name), "%s", child->name);
> + snprintf(evt->config, sizeof(evt->config), "event=0x%llx", code);
> +
> + sysfs_attr_init(&evt->attr.attr);
> + evt->attr.attr.name = evt->name;
> + evt->attr.attr.mode = 0444;
> + evt->attr.show = pmu_dts_event_show;
> + dts_events[dts_event_count] = evt;
> + pmu_dts_events_attrs[dts_event_count] = &evt->attr.attr;
> + dts_event_count++;
> +
> + if (dts_event_count >= MAX_DTS_EVENTS)
> + break;
And node cleanup?
> + }
> + pmu_dts_events_attrs[dts_event_count] = NULL;
> +
> + /* Register PMU */
No.
> + pr_info("pmu_dts: registering PMU\n");
No.
> + return register_power_pmu(&dts_pmu);
> +}
> +
> +/* Platform driver */
This is ridicilous comment.
> +static struct platform_driver pmu_dts_driver = {
> + .probe = pmu_dts_probe,
> + .driver = {
> + .name = "pmu_dts",
> + .of_match_table = pmu_dts_of_match,
> + },
> +};
> +
> +static int __init pmu_dts_init(void)
> +{
> + pr_info("pmu_dts: init\n");
NAK, init functions do not print anything. RFC does not mean you can
send debugging code with poor quality and...
> + return platform_driver_register(&pmu_dts_driver);
> +}
> +
> +static void __exit pmu_dts_exit(void)
> +{
> + pr_info("pmu_dts: exit\n");
> + platform_driver_unregister(&pmu_dts_driver);
> + unregister_power_pmu(&dts_pmu);
> +}
> +module_init(pmu_dts_init);
> +module_exit(pmu_dts_exit);
> +
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Shivani Nittor");
> +MODULE_DESCRIPTION("PMU DTS driver");
> diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h
> index a70ac471a5a5..11154ee31f8e 100644
> --- a/arch/powerpc/perf/internal.h
> +++ b/arch/powerpc/perf/internal.h
> @@ -2,6 +2,7 @@
> //
> // Copyright 2019 Madhavan Srinivasan, IBM Corporation.
>
> +void unregister_power_pmu(struct power_pmu *pmu);
> int __init init_ppc970_pmu(void);
> int __init init_power5_pmu(void);
> int __init init_power5p_pmu(void);
> diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
> index 2b3547fdba4a..e11d1bbbc27b 100644
> --- a/arch/powerpc/perf/isa207-common.c
> +++ b/arch/powerpc/perf/isa207-common.c
> @@ -7,6 +7,7 @@
> * Copyright 2016 Madhavan Srinivasan, IBM Corporation.
> */
> #include "isa207-common.h"
> +#include <asm/dts_pmu.h>
>
> PMU_FORMAT_ATTR(event, "config:0-49");
> PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
> diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
> index 1946dbdc9fa1..35be67eef2c6 100644
> --- a/arch/powerpc/platforms/powernv/opal.c
> +++ b/arch/powerpc/platforms/powernv/opal.c
> @@ -947,6 +947,18 @@ static void __init opal_imc_init_dev(void)
>
> of_node_put(np);
> }
> +#define PMU_DTB "ibm,power-pmu"
> +
> +static void __init opal_pmus_init_dev(void)
> +{
> + struct device_node *np;
> +
> + np = of_find_compatible_node(NULL, NULL, PMU_DTB);
> + if (np)
> + of_platform_device_create(np, NULL, NULL);
> +
> + of_node_put(np);
> +}
>
> static int kopald(void *unused)
> {
> @@ -1032,6 +1044,9 @@ static int __init opal_init(void)
> /* Detect In-Memory Collection counters and create devices*/
> opal_imc_init_dev();
>
> + /*Detect PMU node and create device*/
.... with completely broken indentation style.
> + opal_pmus_init_dev();
> +
> /* Create leds platform devices */
> leds = of_find_node_by_path("/ibm,opal/leds");
> if (leds) {
Best regards,
Krzysztof
^ permalink raw reply
* [PATCH V2] powerpc/syscall: Fix seccomp errno handling with GENERIC_ENTRY
From: Mukesh Kumar Chaurasiya (IBM) @ 2026-06-29 18:29 UTC (permalink / raw)
To: maddy, mpe, npiggin, chleroy, mkchauras, sshegde, ryan.roberts,
ruanjinjie, mkchauras, linuxppc-dev, linux-kernel
Cc: Michal Suchánek
After enabling GENERIC_ENTRY on PowerPC, seccomp filters using
SCMP_ACT_ERRNO without an explicit errnoRet value return ENOSYS
(Function not implemented) instead of the expected EPERM (Operation
not permitted).
The issue occurs in system_call_exception() when syscall_enter_from_user_mode()
returns -1 to indicate the syscall should be skipped (e.g., blocked by seccomp).
The current code treats this -1 as a syscall number and compares it against
NR_syscalls. Since -1 is greater than NR_syscalls,
the code incorrectly returns -ENOSYS, overwriting the errno that seccomp
already set via syscall_set_return_value().
The generic entry code in syscall_trace_enter() calls __secure_computing(),
which sets the appropriate errno in regs->gpr[3] and returns -1 to signal
that the syscall should be skipped. However, the PowerPC syscall handler
was not checking for this -1 return value before validating the syscall
number.
Fix this by explicitly checking if syscall_enter_from_user_mode() returns
-1 and returning the value already set in regs->gpr[3] (the errno from
seccomp) before performing the syscall number validation.
Also Move the syscall_enter_from_user_mode() call and the seccomp/ptrace
skip check to after the NR_syscalls bounds check.
When syscall -1 was passed, the r0 == -1L check would trigger before
the NR_syscalls check, causing syscall_get_error() to return 0 instead
of -ENOSYS. This resulted in a silent success (ret=0, errno=0) instead
of the expected ENOSYS error.
By moving syscall_enter_from_user_mode() after the bounds check, an
initial syscall number of -1 is correctly rejected with -ENOSYS first.
The seccomp/ptrace skip path still works correctly for valid syscall
numbers that get overridden to -1 by seccomp or ptrace.
This aligns PowerPC's behavior with other architectures using GENERIC_ENTRY
and restores correct seccomp errno handling.
Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature")
Reported-by: Michal Suchánek <msuchanek@suse.de>
Closes: https://lore.kernel.org/all/ajpp-_XnbF3UTM_E@kunlun.suse.cz/
Signed-off-by: Mukesh Kumar Chaurasiya (IBM) <mkchauras@gmail.com>
---
v1 -> v2:
- Fix issues in the previous fix (Michal)
v1: https://lore.kernel.org/all/20260624171520.772408-1-mkchauras@gmail.com
arch/powerpc/kernel/syscall.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index a9da2af6efa8..36d73933a311 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -20,7 +20,6 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
syscall_fn f;
add_random_kstack_offset();
- r0 = syscall_enter_from_user_mode(regs, r0);
if (unlikely(r0 >= NR_syscalls)) {
if (unlikely(trap_is_unsupported_scv(regs))) {
@@ -31,6 +30,12 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
return -ENOSYS;
}
+ r0 = syscall_enter_from_user_mode(regs, r0);
+
+ /* Seccomp or ptrace may have set return value, skip syscall */
+ if (unlikely(r0 == -1L))
+ return syscall_get_error(current, regs);
+
/* May be faster to do array_index_nospec? */
barrier_nospec();
--
2.54.0
^ permalink raw reply related
* Re: [PATCH] powerpc/syscall: Fix seccomp errno handling with GENERIC_ENTRY
From: Mukesh Kumar Chaurasiya @ 2026-06-29 17:14 UTC (permalink / raw)
To: Michal Suchánek
Cc: maddy, mpe, npiggin, chleroy, sshegde, mkchauras, kees,
mark.rutland, ryan.roberts, linuxppc-dev, linux-kernel
In-Reply-To: <akKmSblIh_xNcHHp@kunlun.suse.cz>
On Mon, Jun 29, 2026 at 07:07:21PM +0200, Michal Suchánek wrote:
> On Mon, Jun 29, 2026 at 10:32:47PM +0530, Mukesh Kumar Chaurasiya wrote:
> > On Mon, Jun 29, 2026 at 03:31:36PM +0200, Michal Suchánek wrote:
> > > Hello,
> > >
> > > there is yet another bug identified.
> > >
> > > When the initial syscall number is -1 the new condition bypasses setting
> > > the ENOSYS below in if (unlikely(r0 >= NR_syscalls)) and returns 0.
> > >
> > > perl -MPOSIX -e '$!=0; my $r = syscall(-1, 0); print "ret=$r errno=".($!+0)." ($!)\n"'
> > >
> > > Normally the result is
> > >
> > > ret=-1 errno=38 (Function not implemented)
> > >
> > > but with this patch the result is
> > >
> > > ret=0 errno=0 ()
> > >
> > > fixup below.
> > >
> > > On Wed, Jun 24, 2026 at 10:45:20PM +0530, Mukesh Kumar Chaurasiya (IBM) wrote:
> > > > After enabling GENERIC_ENTRY on PowerPC, seccomp filters using
> > > > SCMP_ACT_ERRNO without an explicit errnoRet value return ENOSYS
> > > > (Function not implemented) instead of the expected EPERM (Operation
> > > > not permitted).
> > > >
> > > > The issue occurs in system_call_exception() when syscall_enter_from_user_mode()
> > > > returns -1 to indicate the syscall should be skipped (e.g., blocked by seccomp).
> > > > The current code treats this -1 as a syscall number and compares it against
> > > > NR_syscalls. Since -1 (when cast to unsigned long) is greater than NR_syscalls,
> > > > the code incorrectly returns -ENOSYS, overwriting the errno that seccomp
> > > > already set via syscall_set_return_value().
> > > >
> > > > The generic entry code in syscall_trace_enter() calls __secure_computing(),
> > > > which sets the appropriate errno in regs->gpr[3] and returns -1 to signal
> > > > that the syscall should be skipped. However, the PowerPC syscall handler
> > > > was not checking for this -1 return value before validating the syscall
> > > > number.
> > > >
> > > > Fix this by explicitly checking if syscall_enter_from_user_mode() returns
> > > > -1 and returning the value already set in regs->gpr[3] (the errno from
> > > > seccomp) before performing the syscall number validation.
> > > >
> > > > This aligns PowerPC's behavior with other architectures using GENERIC_ENTRY
> > > > and restores correct seccomp errno handling.
> > > >
> > > > Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature")
> > > > Reported-by: Michal Suchánek <msuchanek@suse.de>
> > > > Signed-off-by: Mukesh Kumar Chaurasiya (IBM) <mkchauras@gmail.com>
> > > > ---
> > > > arch/powerpc/kernel/syscall.c | 4 ++++
> > > > 1 file changed, 4 insertions(+)
> > > >
> > > > diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> > > > index a9da2af6efa8..5b58c8d396c8 100644
> > > > --- a/arch/powerpc/kernel/syscall.c
> > > > +++ b/arch/powerpc/kernel/syscall.c
> > > > @@ -22,6 +22,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> > > unsigned long r0_initial = r0;
> > > > add_random_kstack_offset();
> > > > r0 = syscall_enter_from_user_mode(regs, r0);
> > > >
> > > > + /* Seccomp or ptrace may have set return value, skip syscall */
> > > > + if (unlikely(r0 == -1L)
> > > && (r0_initial != -1L))
> > > > + return regs->gpr[3];
> > > > +
> > > > if (unlikely(r0 >= NR_syscalls)) {
> > > > if (unlikely(trap_is_unsupported_scv(regs))) {
> > > > /* Unsupported scv vector */
> > >
> > > Thanks
> > >
> > > Michal
> >
> > What do you think about this diff?
> > This seems much cleaner.
> >
> > diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> > index a9da2af6efa8..a6c89052e8c5 100644
> > --- a/arch/powerpc/kernel/syscall.c
> > +++ b/arch/powerpc/kernel/syscall.c
> > @@ -20,8 +20,6 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> > syscall_fn f;
> >
> > add_random_kstack_offset();
> > - r0 = syscall_enter_from_user_mode(regs, r0);
> > -
> > if (unlikely(r0 >= NR_syscalls)) {
> > if (unlikely(trap_is_unsupported_scv(regs))) {
> > /* Unsupported scv vector */
> > @@ -30,6 +28,11 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> > }
> > return -ENOSYS;
> > }
> > + r0 = syscall_enter_from_user_mode(regs, r0);
> > +
> > + /* Seccomp or ptrace may have set return value, skip syscall */
> > + if (unlikely(r0 == -1L))
> > + return syscall_get_error(current, regs);
> >
>
> This will skip the check for NR_syscalls for whatever is returned from
> syscall_enter_from_user_mode other than -1. To me it is not clear if
> invalid syscall can be generated by one of the modifications done in
> syscall_enter_from_user_mode.
>
> Thanks
>
> Michal
The possible return values for syscall_enter_from_user_mode are either
`gpr[0]` or -1. If we have an invalid syscall it'll be handled by the
`r0 >= NR_syscalls` check. I think functionally there should be no
issues.
Regards,
Mukesh
^ permalink raw reply
* Re: [PATCH] powerpc/syscall: Fix seccomp errno handling with GENERIC_ENTRY
From: Michal Suchánek @ 2026-06-29 17:07 UTC (permalink / raw)
To: Mukesh Kumar Chaurasiya
Cc: maddy, mpe, npiggin, chleroy, sshegde, mkchauras, kees,
mark.rutland, ryan.roberts, linuxppc-dev, linux-kernel
In-Reply-To: <akKkdd7i6oZ2o5A5@li-1a3e774c-28e4-11b2-a85c-acc9f2883e29.ibm.com>
On Mon, Jun 29, 2026 at 10:32:47PM +0530, Mukesh Kumar Chaurasiya wrote:
> On Mon, Jun 29, 2026 at 03:31:36PM +0200, Michal Suchánek wrote:
> > Hello,
> >
> > there is yet another bug identified.
> >
> > When the initial syscall number is -1 the new condition bypasses setting
> > the ENOSYS below in if (unlikely(r0 >= NR_syscalls)) and returns 0.
> >
> > perl -MPOSIX -e '$!=0; my $r = syscall(-1, 0); print "ret=$r errno=".($!+0)." ($!)\n"'
> >
> > Normally the result is
> >
> > ret=-1 errno=38 (Function not implemented)
> >
> > but with this patch the result is
> >
> > ret=0 errno=0 ()
> >
> > fixup below.
> >
> > On Wed, Jun 24, 2026 at 10:45:20PM +0530, Mukesh Kumar Chaurasiya (IBM) wrote:
> > > After enabling GENERIC_ENTRY on PowerPC, seccomp filters using
> > > SCMP_ACT_ERRNO without an explicit errnoRet value return ENOSYS
> > > (Function not implemented) instead of the expected EPERM (Operation
> > > not permitted).
> > >
> > > The issue occurs in system_call_exception() when syscall_enter_from_user_mode()
> > > returns -1 to indicate the syscall should be skipped (e.g., blocked by seccomp).
> > > The current code treats this -1 as a syscall number and compares it against
> > > NR_syscalls. Since -1 (when cast to unsigned long) is greater than NR_syscalls,
> > > the code incorrectly returns -ENOSYS, overwriting the errno that seccomp
> > > already set via syscall_set_return_value().
> > >
> > > The generic entry code in syscall_trace_enter() calls __secure_computing(),
> > > which sets the appropriate errno in regs->gpr[3] and returns -1 to signal
> > > that the syscall should be skipped. However, the PowerPC syscall handler
> > > was not checking for this -1 return value before validating the syscall
> > > number.
> > >
> > > Fix this by explicitly checking if syscall_enter_from_user_mode() returns
> > > -1 and returning the value already set in regs->gpr[3] (the errno from
> > > seccomp) before performing the syscall number validation.
> > >
> > > This aligns PowerPC's behavior with other architectures using GENERIC_ENTRY
> > > and restores correct seccomp errno handling.
> > >
> > > Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature")
> > > Reported-by: Michal Suchánek <msuchanek@suse.de>
> > > Signed-off-by: Mukesh Kumar Chaurasiya (IBM) <mkchauras@gmail.com>
> > > ---
> > > arch/powerpc/kernel/syscall.c | 4 ++++
> > > 1 file changed, 4 insertions(+)
> > >
> > > diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> > > index a9da2af6efa8..5b58c8d396c8 100644
> > > --- a/arch/powerpc/kernel/syscall.c
> > > +++ b/arch/powerpc/kernel/syscall.c
> > > @@ -22,6 +22,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> > unsigned long r0_initial = r0;
> > > add_random_kstack_offset();
> > > r0 = syscall_enter_from_user_mode(regs, r0);
> > >
> > > + /* Seccomp or ptrace may have set return value, skip syscall */
> > > + if (unlikely(r0 == -1L)
> > && (r0_initial != -1L))
> > > + return regs->gpr[3];
> > > +
> > > if (unlikely(r0 >= NR_syscalls)) {
> > > if (unlikely(trap_is_unsupported_scv(regs))) {
> > > /* Unsupported scv vector */
> >
> > Thanks
> >
> > Michal
>
> What do you think about this diff?
> This seems much cleaner.
>
> diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> index a9da2af6efa8..a6c89052e8c5 100644
> --- a/arch/powerpc/kernel/syscall.c
> +++ b/arch/powerpc/kernel/syscall.c
> @@ -20,8 +20,6 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> syscall_fn f;
>
> add_random_kstack_offset();
> - r0 = syscall_enter_from_user_mode(regs, r0);
> -
> if (unlikely(r0 >= NR_syscalls)) {
> if (unlikely(trap_is_unsupported_scv(regs))) {
> /* Unsupported scv vector */
> @@ -30,6 +28,11 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> }
> return -ENOSYS;
> }
> + r0 = syscall_enter_from_user_mode(regs, r0);
> +
> + /* Seccomp or ptrace may have set return value, skip syscall */
> + if (unlikely(r0 == -1L))
> + return syscall_get_error(current, regs);
>
This will skip the check for NR_syscalls for whatever is returned from
syscall_enter_from_user_mode other than -1. To me it is not clear if
invalid syscall can be generated by one of the modifications done in
syscall_enter_from_user_mode.
Thanks
Michal
^ permalink raw reply
* Re: [PATCH] powerpc/syscall: Fix seccomp errno handling with GENERIC_ENTRY
From: Mukesh Kumar Chaurasiya @ 2026-06-29 17:02 UTC (permalink / raw)
To: Michal Suchánek
Cc: maddy, mpe, npiggin, chleroy, sshegde, mkchauras, kees,
mark.rutland, ryan.roberts, linuxppc-dev, linux-kernel
In-Reply-To: <akJzuEJRLniHk4Fi@kunlun.suse.cz>
On Mon, Jun 29, 2026 at 03:31:36PM +0200, Michal Suchánek wrote:
> Hello,
>
> there is yet another bug identified.
>
> When the initial syscall number is -1 the new condition bypasses setting
> the ENOSYS below in if (unlikely(r0 >= NR_syscalls)) and returns 0.
>
> perl -MPOSIX -e '$!=0; my $r = syscall(-1, 0); print "ret=$r errno=".($!+0)." ($!)\n"'
>
> Normally the result is
>
> ret=-1 errno=38 (Function not implemented)
>
> but with this patch the result is
>
> ret=0 errno=0 ()
>
> fixup below.
>
> On Wed, Jun 24, 2026 at 10:45:20PM +0530, Mukesh Kumar Chaurasiya (IBM) wrote:
> > After enabling GENERIC_ENTRY on PowerPC, seccomp filters using
> > SCMP_ACT_ERRNO without an explicit errnoRet value return ENOSYS
> > (Function not implemented) instead of the expected EPERM (Operation
> > not permitted).
> >
> > The issue occurs in system_call_exception() when syscall_enter_from_user_mode()
> > returns -1 to indicate the syscall should be skipped (e.g., blocked by seccomp).
> > The current code treats this -1 as a syscall number and compares it against
> > NR_syscalls. Since -1 (when cast to unsigned long) is greater than NR_syscalls,
> > the code incorrectly returns -ENOSYS, overwriting the errno that seccomp
> > already set via syscall_set_return_value().
> >
> > The generic entry code in syscall_trace_enter() calls __secure_computing(),
> > which sets the appropriate errno in regs->gpr[3] and returns -1 to signal
> > that the syscall should be skipped. However, the PowerPC syscall handler
> > was not checking for this -1 return value before validating the syscall
> > number.
> >
> > Fix this by explicitly checking if syscall_enter_from_user_mode() returns
> > -1 and returning the value already set in regs->gpr[3] (the errno from
> > seccomp) before performing the syscall number validation.
> >
> > This aligns PowerPC's behavior with other architectures using GENERIC_ENTRY
> > and restores correct seccomp errno handling.
> >
> > Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature")
> > Reported-by: Michal Suchánek <msuchanek@suse.de>
> > Signed-off-by: Mukesh Kumar Chaurasiya (IBM) <mkchauras@gmail.com>
> > ---
> > arch/powerpc/kernel/syscall.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> > index a9da2af6efa8..5b58c8d396c8 100644
> > --- a/arch/powerpc/kernel/syscall.c
> > +++ b/arch/powerpc/kernel/syscall.c
> > @@ -22,6 +22,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
> unsigned long r0_initial = r0;
> > add_random_kstack_offset();
> > r0 = syscall_enter_from_user_mode(regs, r0);
> >
> > + /* Seccomp or ptrace may have set return value, skip syscall */
> > + if (unlikely(r0 == -1L)
> && (r0_initial != -1L))
> > + return regs->gpr[3];
> > +
> > if (unlikely(r0 >= NR_syscalls)) {
> > if (unlikely(trap_is_unsupported_scv(regs))) {
> > /* Unsupported scv vector */
>
> Thanks
>
> Michal
What do you think about this diff?
This seems much cleaner.
diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
index a9da2af6efa8..a6c89052e8c5 100644
--- a/arch/powerpc/kernel/syscall.c
+++ b/arch/powerpc/kernel/syscall.c
@@ -20,8 +20,6 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
syscall_fn f;
add_random_kstack_offset();
- r0 = syscall_enter_from_user_mode(regs, r0);
-
if (unlikely(r0 >= NR_syscalls)) {
if (unlikely(trap_is_unsupported_scv(regs))) {
/* Unsupported scv vector */
@@ -30,6 +28,11 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
}
return -ENOSYS;
}
+ r0 = syscall_enter_from_user_mode(regs, r0);
+
+ /* Seccomp or ptrace may have set return value, skip syscall */
+ if (unlikely(r0 == -1L))
+ return syscall_get_error(current, regs);
/* May be faster to do array_index_nospec? */
barrier_nospec();
Regards,
Mukesh
^ permalink raw reply related
* [PATCH v2 6/8] powerpc64/kasan: Remove unreachable invalid range check in kasan_init_phys_region()
From: Sang-Heon Jeon @ 2026-06-29 16:37 UTC (permalink / raw)
To: rppt, Madhavan Srinivasan, Michael Ellerman
Cc: linux-mm, Sang-Heon Jeon, Christophe Leroy (CS GROUP),
linux-kernel, linuxppc-dev, Nicholas Piggin
In-Reply-To: <20260629163736.1606688-1-ekffu200098@gmail.com>
kasan_init() maps each memblock region with for_each_mem_range() and passes
it to kasan_init_phys_region(), which does nothing when start >= end.
for_each_mem_range() never returns an invalid range, so start < end always.
Therefore the start >= end check is unreachable, so remove it.
No functional change.
Signed-off-by: Sang-Heon Jeon <ekffu200098@gmail.com>
---
arch/powerpc/mm/kasan/init_book3e_64.c | 3 ---
arch/powerpc/mm/kasan/init_book3s_64.c | 3 ---
2 files changed, 6 deletions(-)
diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c
index 0d3a73d6d4b0..0ed372fb8b09 100644
--- a/arch/powerpc/mm/kasan/init_book3e_64.c
+++ b/arch/powerpc/mm/kasan/init_book3e_64.c
@@ -68,9 +68,6 @@ static void __init kasan_init_phys_region(void *start, void *end)
unsigned long k_start, k_end, k_cur;
void *va;
- if (start >= end)
- return;
-
k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c
index dcafa641804c..ccfbfb894637 100644
--- a/arch/powerpc/mm/kasan/init_book3s_64.c
+++ b/arch/powerpc/mm/kasan/init_book3s_64.c
@@ -24,9 +24,6 @@ static void __init kasan_init_phys_region(void *start, void *end)
unsigned long k_start, k_end, k_cur;
void *va;
- if (start >= end)
- return;
-
k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
--
2.43.0
^ permalink raw reply related
* [PATCH v2 0/8] treewide: remove unnecessary invalid range checks in memblock iteration loops
From: Sang-Heon Jeon @ 2026-06-29 16:37 UTC (permalink / raw)
To: rppt, Albert Ou, Andrew Morton, Andrey Ryabinin, Catalin Marinas,
Huacai Chen, Madhavan Srinivasan, Michael Ellerman, Muchun Song,
Oscar Salvador, Palmer Dabbelt, Paul Walmsley, Russell King,
Will Deacon
Cc: linux-mm, Sang-Heon Jeon, Alexander Potapenko, Alexandre Ghiti,
Andrey Konovalov, Christophe Leroy (CS GROUP), David Hildenbrand,
Dmitry Vyukov, kasan-dev, linux-arm-kernel, linux-kernel,
linuxppc-dev, linux-riscv, loongarch, Nicholas Piggin,
Vincenzo Frascino, WANG Xuerui
The memblock API guarantees that for_each_mem_range() and
for_each_mem_pfn_range() never return an invalid range, meaning start is
always less than end.
Several memblock callers still have unnecessary invalid range checks in
their loop bodies, so remove them.
Patches 1-6 cover for_each_mem_range() callers. memblock never stores a
zero-size region, so the range it returns always has start < end. Some
callers apply __va() or __phys_to_virt() before comparing, but these keep
start < end too, so the check is unreachable.
Patches 7-8 cover for_each_mem_pfn_range() callers. __next_mem_pfn_range()
skips any region that contains no whole page, so it only ever returns
start_pfn < end_pfn and the check is unnecessary.
For reference, commit 36ca7f4be809 ("arm64: mm: Remove bogus stop
condition from map_mem() loop") did a similar cleanup in arm64 map_mem().
All these checks are in different trees, so I split the change into one
patch per arch/subsystem. The patches are independent and can be applied
separately.
---
Changes from v1 [1]
- Add review-by, tested-by tags from v1
- Add missing simliar patches(5,6) to patch series
- Change base to rppt/for-next
[1] https://lore.kernel.org/all/20260621145919.1453-1-ekffu200098@gmail.com/
---
Sang-Heon Jeon (8):
arm64: mm: remove unreachable invalid range check in
kasan_init_shadow()
LoongArch: remove unreachable invalid range check in kasan_init()
riscv: remove unreachable invalid range check in
create_linear_mapping_page_table()
riscv: remove unreachable invalid range check in kasan_init()
ARM: remove unreachable invalid range check in kasan_init()
powerpc64/kasan: Remove unreachable invalid range check in
kasan_init_phys_region()
mm: remove unnecessary empty range check in
early_calculate_totalpages()
mm/hugetlb: remove unnecessary empty range check in
hugetlb_bootmem_set_nodes()
arch/arm/mm/kasan_init.c | 6 ------
arch/arm64/mm/kasan_init.c | 3 ---
arch/loongarch/mm/kasan_init.c | 3 ---
arch/powerpc/mm/kasan/init_book3e_64.c | 3 ---
arch/powerpc/mm/kasan/init_book3s_64.c | 3 ---
arch/riscv/mm/init.c | 2 --
arch/riscv/mm/kasan_init.c | 3 ---
mm/hugetlb.c | 3 +--
mm/mm_init.c | 3 +--
9 files changed, 2 insertions(+), 27 deletions(-)
--
2.43.0
^ permalink raw reply
* Re: [PATCH v2 00/19] driver core: count references of the platform device's fwnode, not OF node
From: Andy Shevchenko @ 2026-06-29 16:23 UTC (permalink / raw)
To: Bartosz Golaszewski
Cc: Lee Jones, Mark Brown, Thierry Reding, Sebastian Hesselbarth,
Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Srinivas Kandagatla, Greg Kroah-Hartman, Vinod Koul,
Rafael J. Wysocki, Danilo Krummrich, Rob Herring, Saravana Kannan,
Madhavan Srinivasan, Michael Ellerman, Nicholas Piggin,
Christophe Leroy (CS GROUP), Andi Shyti, Joerg Roedel,
Will Deacon, Robin Murphy, Doug Berger, Florian Fainelli,
Broadcom internal kernel review list, Ulf Hansson, Frank Li,
Sascha Hauer, Pengutronix Kernel Team, Fabio Estevam,
Matthew Brost, Thomas Hellström, Rodrigo Vivi, David Airlie,
Simona Vetter, Peter Chen, Paul Cercueil, Bin Liu, Philipp Zabel,
Maximilian Luz, Hans de Goede, Ilpo Järvinen,
Krzysztof Kozlowski, Benjamin Herrenschmidt, brgl, linux-kernel,
netdev, linux-arm-msm, linux-sound, driver-core, devicetree,
linuxppc-dev, linux-i2c, iommu, linux-pm, imx, linux-arm-kernel,
intel-xe, dri-devel, linux-usb, linux-mips, platform-driver-x86,
stable, Wolfram Sang
In-Reply-To: <20260629-pdev-fwnode-ref-v2-0-8abe2513f96e@oss.qualcomm.com>
On Mon, Jun 29, 2026 at 11:12:23AM +0200, Bartosz Golaszewski wrote:
> Platform device core provides helper interfaces for dealing with
> dynamically created platform devices. Most users should use
> platform_device_register_full() which encapsulates most of the
> operations but some modules will want to use the split approach of
> calling platform_device_alloc() + platform_device_add() separately for
> various reasons.
>
> With many platform devices now using dynamic software nodes as their
> primary firmware nodes and with the platform device interface being
> extended to also better cover the use-cases of secondary software nodes,
> I believe it makes sense to switch to counting the references of all
> kinds of firmware nodes.
>
> To that end, I identified all users of platform_device_alloc() that also
> assign dev.of_node or dev.fwnode manually. I noticed five cases where
> the references are not increased as they should (patches 1-5 fix these
> users) and provided three new functions in platform_device.h that now
> become the preferred interfaces for assigning firmware nodes to dynamic
> platform devices (in line with platform_device_add_data(),
> platform_device_add_resources(), etc.). The bulk of the patches in this
> series are small driver conversions to port all users to going through
> the new functions that now encapsulate the refcount logic. With that
> done, the final patch seamlessly switches to counting the references of
> all firmware node types.
>
> This effort is prerequisite of removing platform_device_release_full()
> and unifying the release path for dynamic platform devices using
> unmanaged software nodes.
>
> Merging strategy: The entire series should go through the driver core
> tree, possibly with an immutable branch provided to solve any potential
> conflicts though these are rather unlikely.
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
for patches 2-4 assuming they will be accompanied with patch 19 at the same
time.
--
With Best Regards,
Andy Shevchenko
^ permalink raw reply
* Re: [PATCH v2 19/19] driver core: platform: count references to all kinds of firmware nodes
From: Andy Shevchenko @ 2026-06-29 16:21 UTC (permalink / raw)
To: Bartosz Golaszewski
Cc: Lee Jones, Mark Brown, Thierry Reding, Sebastian Hesselbarth,
Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Srinivas Kandagatla, Greg Kroah-Hartman, Vinod Koul,
Rafael J. Wysocki, Danilo Krummrich, Rob Herring, Saravana Kannan,
Madhavan Srinivasan, Michael Ellerman, Nicholas Piggin,
Christophe Leroy (CS GROUP), Andi Shyti, Joerg Roedel,
Will Deacon, Robin Murphy, Doug Berger, Florian Fainelli,
Broadcom internal kernel review list, Ulf Hansson, Frank Li,
Sascha Hauer, Pengutronix Kernel Team, Fabio Estevam,
Matthew Brost, Thomas Hellström, Rodrigo Vivi, David Airlie,
Simona Vetter, Peter Chen, Paul Cercueil, Bin Liu, Philipp Zabel,
Maximilian Luz, Hans de Goede, Ilpo Järvinen,
Krzysztof Kozlowski, Benjamin Herrenschmidt, brgl, linux-kernel,
netdev, linux-arm-msm, linux-sound, driver-core, devicetree,
linuxppc-dev, linux-i2c, iommu, linux-pm, imx, linux-arm-kernel,
intel-xe, dri-devel, linux-usb, linux-mips, platform-driver-x86
In-Reply-To: <20260629-pdev-fwnode-ref-v2-19-8abe2513f96e@oss.qualcomm.com>
On Mon, Jun 29, 2026 at 11:12:42AM +0200, Bartosz Golaszewski wrote:
> When using platform_device_register_full(), we currently only increase
> the reference count of the OF node associated with a platform device. We
> symmetrically decrease it in platform_device_release(). With all users in
> tree now converted to using provided platform device helpers for
> assigning OF and firmware nodes, we can now switch to counting references
> of all kinds of firmware nodes.
Yep, that's the expected result, thanks!
...
> void platform_device_set_fwnode(struct platform_device *pdev,
> struct fwnode_handle *fwnode)
> {
> - if (is_of_node(fwnode))
> - platform_device_set_of_node(pdev, to_of_node(fwnode));
> - else
> - pdev->dev.fwnode = fwnode;
> + fwnode_handle_put(pdev->dev.fwnode);
> + pdev->dev.fwnode = fwnode_handle_get(fwnode);
> + pdev->dev.of_node = to_of_node(fwnode);
device_set_node(&pdev->dev, fwnode_handle_get(fwnode));
> }
...
> pdev->dev.parent = pdevinfo->parent;
> - pdev->dev.fwnode = pdevinfo->fwnode;
> - pdev->dev.of_node = of_node_get(to_of_node(pdev->dev.fwnode));
> + pdev->dev.fwnode = fwnode_handle_get(pdevinfo->fwnode);
> + pdev->dev.of_node = to_of_node(pdev->dev.fwnode);
See above.
...
With them being addressed,
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
--
With Best Regards,
Andy Shevchenko
^ permalink raw reply
* Re: [PATCH v2 08/19] iommu/fsl: use platform_device_set_of_node()
From: Frank Li @ 2026-06-29 14:08 UTC (permalink / raw)
To: Bartosz Golaszewski
Cc: Lee Jones, Mark Brown, Thierry Reding, Sebastian Hesselbarth,
Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Srinivas Kandagatla, Greg Kroah-Hartman, Vinod Koul,
Rafael J. Wysocki, Danilo Krummrich, Rob Herring, Saravana Kannan,
Madhavan Srinivasan, Michael Ellerman, Nicholas Piggin,
Christophe Leroy (CS GROUP), Andi Shyti, Andy Shevchenko,
Joerg Roedel, Will Deacon, Robin Murphy, Doug Berger,
Florian Fainelli, Broadcom internal kernel review list,
Ulf Hansson, Frank Li, Sascha Hauer, Pengutronix Kernel Team,
Fabio Estevam, Matthew Brost, Thomas Hellström, Rodrigo Vivi,
David Airlie, Simona Vetter, Peter Chen, Paul Cercueil, Bin Liu,
Philipp Zabel, Maximilian Luz, Hans de Goede, Ilpo Järvinen,
Krzysztof Kozlowski, Benjamin Herrenschmidt, brgl, linux-kernel,
netdev, linux-arm-msm, linux-sound, driver-core, devicetree,
linuxppc-dev, linux-i2c, iommu, linux-pm, imx, linux-arm-kernel,
intel-xe, dri-devel, linux-usb, linux-mips, platform-driver-x86
In-Reply-To: <20260629-pdev-fwnode-ref-v2-8-8abe2513f96e@oss.qualcomm.com>
On Mon, Jun 29, 2026 at 11:12:31AM +0200, Bartosz Golaszewski wrote:
> [You don't often get email from bartosz.golaszewski@oss.qualcomm.com. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
>
> Ahead of reworking the reference counting logic for platform devices,
> encapsulate the assignment of the OF node for dynamically allocated
> platform devices with the provided helper.
>
> Acked-by: Robin Murphy <robin.murphy@arm.com>
> Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
> ---
> drivers/iommu/fsl_pamu.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
> index 25aa477a95a95cb4fa4e132727cde0a936750ee2..012839fa0d8a27cafc6a441373f4f6da794388c1 100644
> --- a/drivers/iommu/fsl_pamu.c
> +++ b/drivers/iommu/fsl_pamu.c
> @@ -973,7 +973,8 @@ static __init int fsl_pamu_init(void)
> ret = -ENOMEM;
> goto error_device_alloc;
> }
> - pdev->dev.of_node = of_node_get(np);
> +
> + platform_device_set_of_node(pdev, np);
>
> ret = pamu_domain_init();
> if (ret)
> @@ -985,12 +986,10 @@ static __init int fsl_pamu_init(void)
> goto error_device_add;
> }
>
> + of_node_put(np);
there are other place miss of_node_put() at error pass.
Can you use auto cleanup
struct device_node *np __free(device_node) = of_find_compatible_node().
Frank
> return 0;
>
> error_device_add:
> - of_node_put(pdev->dev.of_node);
> - pdev->dev.of_node = NULL;
> -
> platform_device_put(pdev);
>
> error_device_alloc:
>
> --
> 2.47.3
>
>
^ permalink raw reply
* Re: [PATCH] powerpc/syscall: Fix seccomp errno handling with GENERIC_ENTRY
From: Michal Suchánek @ 2026-06-29 13:31 UTC (permalink / raw)
To: Mukesh Kumar Chaurasiya (IBM)
Cc: maddy, mpe, npiggin, chleroy, sshegde, mkchauras, kees,
mark.rutland, ryan.roberts, linuxppc-dev, linux-kernel
In-Reply-To: <20260624171520.772408-1-mkchauras@gmail.com>
Hello,
there is yet another bug identified.
When the initial syscall number is -1 the new condition bypasses setting
the ENOSYS below in if (unlikely(r0 >= NR_syscalls)) and returns 0.
perl -MPOSIX -e '$!=0; my $r = syscall(-1, 0); print "ret=$r errno=".($!+0)." ($!)\n"'
Normally the result is
ret=-1 errno=38 (Function not implemented)
but with this patch the result is
ret=0 errno=0 ()
fixup below.
On Wed, Jun 24, 2026 at 10:45:20PM +0530, Mukesh Kumar Chaurasiya (IBM) wrote:
> After enabling GENERIC_ENTRY on PowerPC, seccomp filters using
> SCMP_ACT_ERRNO without an explicit errnoRet value return ENOSYS
> (Function not implemented) instead of the expected EPERM (Operation
> not permitted).
>
> The issue occurs in system_call_exception() when syscall_enter_from_user_mode()
> returns -1 to indicate the syscall should be skipped (e.g., blocked by seccomp).
> The current code treats this -1 as a syscall number and compares it against
> NR_syscalls. Since -1 (when cast to unsigned long) is greater than NR_syscalls,
> the code incorrectly returns -ENOSYS, overwriting the errno that seccomp
> already set via syscall_set_return_value().
>
> The generic entry code in syscall_trace_enter() calls __secure_computing(),
> which sets the appropriate errno in regs->gpr[3] and returns -1 to signal
> that the syscall should be skipped. However, the PowerPC syscall handler
> was not checking for this -1 return value before validating the syscall
> number.
>
> Fix this by explicitly checking if syscall_enter_from_user_mode() returns
> -1 and returning the value already set in regs->gpr[3] (the errno from
> seccomp) before performing the syscall number validation.
>
> This aligns PowerPC's behavior with other architectures using GENERIC_ENTRY
> and restores correct seccomp errno handling.
>
> Fixes: bee25f97ad24 ("powerpc: Enable GENERIC_ENTRY feature")
> Reported-by: Michal Suchánek <msuchanek@suse.de>
> Signed-off-by: Mukesh Kumar Chaurasiya (IBM) <mkchauras@gmail.com>
> ---
> arch/powerpc/kernel/syscall.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/arch/powerpc/kernel/syscall.c b/arch/powerpc/kernel/syscall.c
> index a9da2af6efa8..5b58c8d396c8 100644
> --- a/arch/powerpc/kernel/syscall.c
> +++ b/arch/powerpc/kernel/syscall.c
> @@ -22,6 +22,10 @@ notrace long system_call_exception(struct pt_regs *regs, unsigned long r0)
unsigned long r0_initial = r0;
> add_random_kstack_offset();
> r0 = syscall_enter_from_user_mode(regs, r0);
>
> + /* Seccomp or ptrace may have set return value, skip syscall */
> + if (unlikely(r0 == -1L)
&& (r0_initial != -1L))
> + return regs->gpr[3];
> +
> if (unlikely(r0 >= NR_syscalls)) {
> if (unlikely(trap_is_unsupported_scv(regs))) {
> /* Unsupported scv vector */
Thanks
Michal
^ permalink raw reply
* [PATCH v16 18/18] arm64: vdso: Expose sigreturn address on vdso to the kernel
From: Jinjie Ruan @ 2026-06-29 13:06 UTC (permalink / raw)
To: oleg, richard.henderson, mattst88, linmag7, linux,
catalin.marinas, will, kees, guoren, chenhuacai, kernel, geert,
tsbogend, James.Bottomley, deller, maddy, mpe, npiggin, chleroy,
pjw, palmer, aou, alex, hca, gor, agordeev, borntraeger, svens,
ysato, dalias, glaubitz, richard, anton.ivanov, johannes, luto,
tglx, mingo, bp, dave.hansen, hpa, chris, jcmvbkbc, peterz, wad,
ruanjinjie, thuth, mark.rutland, ada.coupriediaz, kevin.brodsky,
linusw, yeoreum.yun, song, james.morse, anshuman.khandual,
broonie, liqiang01, pengcan, ryan.roberts, yangtiezhu, sshegde,
mchauras, austin.kim, jchrist, arnd, thomas.weissschuh,
sohil.mehta, andrew.cooper3, jgross, kas, x86, linux-alpha,
linux-kernel, linux-arm-kernel, linux-mm, linux-csky, loongarch,
linux-m68k, linux-mips, linux-parisc, linuxppc-dev, linux-riscv,
linux-s390, linux-sh, linux-um
In-Reply-To: <20260629130616.642022-1-ruanjinjie@huawei.com>
Syscall User Dispatch (SUD) requires the signal trampoline code to not be
intercepted. This is necessary to support returning with a locked selector
while avoiding infinite recursion back into the signal handler.
Implement arch_syscall_is_vdso_sigreturn() for arm64 to support this
exclusion mechanism. For native 64-bit tasks, it checks whether the current
PC matches the 'svc #0' instruction inside the vDSO sigreturn trampoline.
SYM_CODE_START(__kernel_rt_sigreturn)
mov x8, #__NR_rt_sigreturn
svc #0
SYM_CODE_END(__kernel_rt_sigreturn)
For COMPAT tasks, it verifies if the instruction falls within
the architecture's 'sigpage' range, allowing the kernel to safely bypass
dispatching syscalls originating from these areas back to userspace.
Suggested-by: Kevin Brodsky <kevin.brodsky@arm.com>
Suggested-by: kemal <kmal@cock.li>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
---
arch/arm64/include/asm/elf.h | 1 +
arch/arm64/kernel/vdso.c | 16 ++++++++++++++++
2 files changed, 17 insertions(+)
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index d2779d604c7b..f43d4dea916a 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -185,6 +185,7 @@ do { \
struct linux_binprm;
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
+extern bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs);
/* 1GB of VA */
#ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 592dd8668de4..5a0314a3c26e 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -343,3 +343,19 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
return ret;
}
+
+bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
+{
+ unsigned long sigtramp;
+
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ unsigned long sigpage = (unsigned long)current->mm->context.sigpage;
+
+ return regs->pc >= sigpage && regs->pc < (sigpage + PAGE_SIZE);
+ }
+#endif
+ sigtramp = (unsigned long)VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
+
+ return regs->pc == (sigtramp + 8);
+}
--
2.34.1
^ permalink raw reply related
* [PATCH v16 17/18] arm64: Inline el0_svc_common()
From: Jinjie Ruan @ 2026-06-29 13:06 UTC (permalink / raw)
To: oleg, richard.henderson, mattst88, linmag7, linux,
catalin.marinas, will, kees, guoren, chenhuacai, kernel, geert,
tsbogend, James.Bottomley, deller, maddy, mpe, npiggin, chleroy,
pjw, palmer, aou, alex, hca, gor, agordeev, borntraeger, svens,
ysato, dalias, glaubitz, richard, anton.ivanov, johannes, luto,
tglx, mingo, bp, dave.hansen, hpa, chris, jcmvbkbc, peterz, wad,
ruanjinjie, thuth, mark.rutland, ada.coupriediaz, kevin.brodsky,
linusw, yeoreum.yun, song, james.morse, anshuman.khandual,
broonie, liqiang01, pengcan, ryan.roberts, yangtiezhu, sshegde,
mchauras, austin.kim, jchrist, arnd, thomas.weissschuh,
sohil.mehta, andrew.cooper3, jgross, kas, x86, linux-alpha,
linux-kernel, linux-arm-kernel, linux-mm, linux-csky, loongarch,
linux-m68k, linux-mips, linux-parisc, linuxppc-dev, linux-riscv,
linux-s390, linux-sh, linux-um
In-Reply-To: <20260629130616.642022-1-ruanjinjie@huawei.com>
After converting arm64 to Generic Entry framework, the compiler no longer
inlines el0_svc_common() into its caller do_el0_svc(). This introduces
a small but measurable overhead in the critical system call path.
Manually forcing el0_svc_common() to be inlined restores the
performance. Benchmarking with perf bench syscall basic on a
Kunpeng 920 platform (based on v6.19-rc1) shows a ~1% performance
uplift.
Inlining this function reduces function prologue/epilogue overhead
and allows for better compiler optimization in the hot system call
dispatch path.
| Metric | W/O this patch | With this patch | Change |
| ---------- | -------------- | --------------- | --------- |
| Total time | 2.195 [sec] | 2.171 [sec] | ↓1.1% |
| usecs/op | 0.219575 | 0.217192 | ↓1.1% |
| ops/sec | 4,554,260 | 4,604,225 | ↑1.1% |
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Reviewed-by: Yeoreum Yun <yeoreum.yun@arm.com>
Reviewed-by: Kevin Brodsky <kevin.brodsky@arm.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
---
arch/arm64/kernel/syscall.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 41a3b70a9374..e0a98fac3b85 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -55,8 +55,8 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
syscall_set_return_value(current, regs, 0, ret);
}
-static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
- const syscall_fn_t syscall_table[])
+static __always_inline void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
+ const syscall_fn_t syscall_table[])
{
unsigned long flags = read_thread_flags();
unsigned long work;
--
2.34.1
^ permalink raw reply related
* [PATCH v16 16/18] arm64: entry: Convert to generic entry
From: Jinjie Ruan @ 2026-06-29 13:06 UTC (permalink / raw)
To: oleg, richard.henderson, mattst88, linmag7, linux,
catalin.marinas, will, kees, guoren, chenhuacai, kernel, geert,
tsbogend, James.Bottomley, deller, maddy, mpe, npiggin, chleroy,
pjw, palmer, aou, alex, hca, gor, agordeev, borntraeger, svens,
ysato, dalias, glaubitz, richard, anton.ivanov, johannes, luto,
tglx, mingo, bp, dave.hansen, hpa, chris, jcmvbkbc, peterz, wad,
ruanjinjie, thuth, mark.rutland, ada.coupriediaz, kevin.brodsky,
linusw, yeoreum.yun, song, james.morse, anshuman.khandual,
broonie, liqiang01, pengcan, ryan.roberts, yangtiezhu, sshegde,
mchauras, austin.kim, jchrist, arnd, thomas.weissschuh,
sohil.mehta, andrew.cooper3, jgross, kas, x86, linux-alpha,
linux-kernel, linux-arm-kernel, linux-mm, linux-csky, loongarch,
linux-m68k, linux-mips, linux-parisc, linuxppc-dev, linux-riscv,
linux-s390, linux-sh, linux-um
In-Reply-To: <20260629130616.642022-1-ruanjinjie@huawei.com>
Implement the generic entry framework for arm64 to handle system call
entry and exit. This follows the migration of x86, RISC-V, and LoongArch,
consolidating architecture-specific syscall tracing and auditing into
the common kernel entry infrastructure, making it easier to enable
advanced features on arm64, such as "Syscall User Dispatch" and "rseq time
slice extension" optimization.
[Background]
Arm64 has already adopted generic IRQ entry. Completing the conversion
to the generic syscall entry framework reduces architectural divergence,
simplifies maintenance, and allows arm64 to automatically benefit from
improvements in the common entry code.
[Changes]
1. Kconfig and Infrastructure:
- Select GENERIC_ENTRY and remove GENERIC_IRQ_ENTRY (now implied).
- Migrate struct thread_info to use the syscall_work field instead
of TIF flags for syscall-related tasks.
2. Thread Info and Flags:
- Remove definitions for TIF_SYSCALL_TRACE, TIF_SYSCALL_AUDIT,
TIF_SYSCALL_TRACEPOINT, TIF_SECCOMP, and TIF_SYSCALL_EMU.
- Replace _TIF_SYSCALL_WORK and _TIF_SYSCALL_EXIT_WORK with the
generic SYSCALL_WORK bitmask.
- Map single-step state to SYSCALL_EXIT_TRAP in debug-monitors.c.
3. Architecture-Specific Hooks (asm/entry-common.h):
- Implement arch_ptrace_report_syscall_entry() and _exit() by
porting the existing arm64 logic to the generic interface.
4. Cleanup and Refactoring:
- Remove redundant arm64-specific syscall tracing functions from
ptrace.c, including syscall_trace_enter(), syscall_exit_work(),
and related audit/step helpers.
- Update el0_svc_common() in syscall.c to use the generic
syscall_work checks and entry/exit call sites.
[Why this matters]
- Unified Interface: Aligns arm64 with the modern kernel entry standard.
- Improved Maintainability: Bug fixes in kernel/entry/common.c now
apply to arm64 automatically.
- Feature Readiness: Simplifies the implementation of future
cross-architecture syscall features.
[Compatibility]
This conversion maintains full ABI compatibility with existing
userspace. The ptrace register-saving behavior, seccomp filtering, and
syscall tracing semantics remain identical to the previous implementation.
Additionally, since arm64 now does not select HAVE_GENERIC_TIF_BITS, there
is no functional change regarding rseq management, as those generic entry
pathways remain a no-op for this architecture."
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Tested-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Reviewed-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Yeoreum Yun <yeoreum.yun@arm.com>
Reviewed-by: Kevin Brodsky <kevin.brodsky@arm.com>
Suggested-by: Kevin Brodsky <kevin.brodsky@arm.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
---
arch/arm64/Kconfig | 2 +-
arch/arm64/include/asm/entry-common.h | 76 ++++++++++++++
arch/arm64/include/asm/syscall.h | 13 ---
arch/arm64/include/asm/thread_info.h | 19 +---
arch/arm64/kernel/debug-monitors.c | 8 ++
arch/arm64/kernel/ptrace.c | 142 --------------------------
arch/arm64/kernel/signal.c | 2 +-
arch/arm64/kernel/syscall.c | 7 +-
8 files changed, 92 insertions(+), 177 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b3afe0688919..aea686dce3d5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -128,9 +128,9 @@ config ARM64
select GENERIC_CPU_DEVICES
select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
+ select GENERIC_ENTRY
select GENERIC_IDLE_POLL_SETUP
select GENERIC_IOREMAP
- select GENERIC_IRQ_ENTRY
select GENERIC_IRQ_IPI
select GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD
select GENERIC_IRQ_PROBE
diff --git a/arch/arm64/include/asm/entry-common.h b/arch/arm64/include/asm/entry-common.h
index cab8cd78f693..d8bf4bf342e8 100644
--- a/arch/arm64/include/asm/entry-common.h
+++ b/arch/arm64/include/asm/entry-common.h
@@ -3,14 +3,21 @@
#ifndef _ASM_ARM64_ENTRY_COMMON_H
#define _ASM_ARM64_ENTRY_COMMON_H
+#include <linux/ptrace.h>
#include <linux/thread_info.h>
+#include <asm/compat.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
#include <asm/fpsimd.h>
#include <asm/mte.h>
#include <asm/stacktrace.h>
+enum ptrace_syscall_dir {
+ PTRACE_SYSCALL_ENTER = 0,
+ PTRACE_SYSCALL_EXIT,
+};
+
#define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_MTE_ASYNC_FAULT | _TIF_FOREIGN_FPSTATE)
static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
@@ -54,4 +61,73 @@ static inline bool arch_irqentry_exit_need_resched(void)
#define arch_irqentry_exit_need_resched arch_irqentry_exit_need_resched
+static __always_inline unsigned long ptrace_save_reg(struct pt_regs *regs,
+ enum ptrace_syscall_dir dir,
+ int *regno)
+{
+ unsigned long saved_reg;
+
+ /*
+ * We have some ABI weirdness here in the way that we handle syscall
+ * exit stops because we indicate whether or not the stop has been
+ * signalled from syscall entry or syscall exit by clobbering a general
+ * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+ * and restoring its old value after the stop. This means that:
+ *
+ * - Any writes by the tracer to this register during the stop are
+ * ignored/discarded.
+ *
+ * - The actual value of the register is not available during the stop,
+ * so the tracer cannot save it and restore it later.
+ *
+ * - Syscall stops behave differently to seccomp and pseudo-step traps
+ * (the latter do not nobble any registers).
+ */
+ *regno = (is_compat_task() ? 12 : 7);
+ saved_reg = regs->regs[*regno];
+ regs->regs[*regno] = dir;
+
+ return saved_reg;
+}
+
+static __always_inline int arch_ptrace_report_syscall_entry(struct pt_regs *regs)
+{
+ unsigned long saved_reg;
+ int regno, ret;
+
+ saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, ®no);
+ ret = ptrace_report_syscall_entry(regs);
+ if (ret)
+ forget_syscall(regs);
+ regs->regs[regno] = saved_reg;
+
+ return ret;
+}
+
+#define arch_ptrace_report_syscall_entry arch_ptrace_report_syscall_entry
+
+static __always_inline void arch_ptrace_report_syscall_exit(struct pt_regs *regs,
+ int step)
+{
+ unsigned long saved_reg;
+ int regno;
+
+ saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, ®no);
+ if (!step) {
+ ptrace_report_syscall_exit(regs, 0);
+ regs->regs[regno] = saved_reg;
+ } else {
+ regs->regs[regno] = saved_reg;
+
+ /*
+ * Signal a pseudo-step exception since we are stepping but
+ * tracer modifications to the registers may have rewound the
+ * state machine.
+ */
+ ptrace_report_syscall_exit(regs, 1);
+ }
+}
+
+#define arch_ptrace_report_syscall_exit arch_ptrace_report_syscall_exit
+
#endif /* _ASM_ARM64_ENTRY_COMMON_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index b982398f8765..84b1c36233d4 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -121,17 +121,4 @@ static inline int syscall_get_arch(struct task_struct *task)
return AUDIT_ARCH_AARCH64;
}
-int syscall_trace_enter(struct pt_regs *regs, unsigned long flags);
-void syscall_exit_work(struct pt_regs *regs, unsigned long flags);
-
-static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
-{
- unsigned long flags = read_thread_flags();
-
- rseq_syscall(regs);
-
- if (unlikely(flags & _TIF_SYSCALL_EXIT_WORK) || flags & _TIF_SINGLESTEP)
- syscall_exit_work(regs, flags);
-}
-
#endif /* __ASM_SYSCALL_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 56a2c9426a32..3f621ba0f961 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -46,6 +46,7 @@ struct thread_info {
u64 mpam_partid_pmg;
#endif
u32 cpu;
+ unsigned long syscall_work; /* SYSCALL_WORK_ flags */
};
#define thread_saved_pc(tsk) \
@@ -68,11 +69,6 @@ void arch_setup_new_exec(void);
#define TIF_UPROBE 5 /* uprobe breakpoint or singlestep */
#define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */
#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */
-#define TIF_SYSCALL_TRACE 8 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */
-#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */
-#define TIF_SECCOMP 11 /* syscall secure computing */
-#define TIF_SYSCALL_EMU 12 /* syscall emulation active */
#define TIF_PATCH_PENDING 13 /* pending live patching update */
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_FREEZE 19
@@ -94,27 +90,14 @@ void arch_setup_new_exec(void);
#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE)
-#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
-#define _TIF_SECCOMP (1 << TIF_SECCOMP)
-#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
#define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING)
#define _TIF_UPROBE (1 << TIF_UPROBE)
-#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)
#define _TIF_32BIT (1 << TIF_32BIT)
#define _TIF_SVE (1 << TIF_SVE)
#define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT)
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_TSC_SIGSEGV (1 << TIF_TSC_SIGSEGV)
-#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
- _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
- _TIF_SYSCALL_EMU)
-
-#define _TIF_SYSCALL_EXIT_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
- _TIF_SYSCALL_TRACEPOINT)
-
#ifdef CONFIG_SHADOW_CALL_STACK
#define INIT_SCS \
.scs_base = init_shadow_call_stack, \
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 29307642f4c9..c53683839155 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -385,11 +385,19 @@ void user_enable_single_step(struct task_struct *task)
if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
set_regs_spsr_ss(task_pt_regs(task));
+
+ /*
+ * Ensure that the generic entry code triggers a trap once stepping
+ * out of a system call prior to executing any user instruction,
+ * as the generic entry code does not natively check for TIF_SINGLESTEP.
+ */
+ set_task_syscall_work(task, SYSCALL_EXIT_TRAP);
}
NOKPROBE_SYMBOL(user_enable_single_step);
void user_disable_single_step(struct task_struct *task)
{
clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
+ clear_task_syscall_work(task, SYSCALL_EXIT_TRAP);
}
NOKPROBE_SYMBOL(user_disable_single_step);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 650db9b47373..61a668682947 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -8,7 +8,6 @@
* Copyright (C) 2012 ARM Ltd.
*/
-#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
@@ -18,7 +17,6 @@
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
-#include <linux/seccomp.h>
#include <linux/security.h>
#include <linux/init.h>
#include <linux/signal.h>
@@ -37,13 +35,9 @@
#include <asm/mte.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
-#include <asm/syscall.h>
#include <asm/traps.h>
#include <asm/system_misc.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
struct pt_regs_offset {
const char *name;
int offset;
@@ -2338,142 +2332,6 @@ long arch_ptrace(struct task_struct *child, long request,
return ptrace_request(child, request, addr, data);
}
-enum ptrace_syscall_dir {
- PTRACE_SYSCALL_ENTER = 0,
- PTRACE_SYSCALL_EXIT,
-};
-
-static __always_inline unsigned long ptrace_save_reg(struct pt_regs *regs,
- enum ptrace_syscall_dir dir,
- int *regno)
-{
- unsigned long saved_reg;
-
- /*
- * We have some ABI weirdness here in the way that we handle syscall
- * exit stops because we indicate whether or not the stop has been
- * signalled from syscall entry or syscall exit by clobbering a general
- * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
- * and restoring its old value after the stop. This means that:
- *
- * - Any writes by the tracer to this register during the stop are
- * ignored/discarded.
- *
- * - The actual value of the register is not available during the stop,
- * so the tracer cannot save it and restore it later.
- *
- * - Syscall stops behave differently to seccomp and pseudo-step traps
- * (the latter do not nobble any registers).
- */
- *regno = (is_compat_task() ? 12 : 7);
- saved_reg = regs->regs[*regno];
- regs->regs[*regno] = dir;
-
- return saved_reg;
-}
-
-static int report_syscall_entry(struct pt_regs *regs)
-{
- unsigned long saved_reg;
- int regno, ret;
-
- saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_ENTER, ®no);
- ret = ptrace_report_syscall_entry(regs);
- if (ret)
- forget_syscall(regs);
- regs->regs[regno] = saved_reg;
-
- return ret;
-}
-
-static void report_syscall_exit(struct pt_regs *regs)
-{
- unsigned long saved_reg;
- int regno;
-
- saved_reg = ptrace_save_reg(regs, PTRACE_SYSCALL_EXIT, ®no);
- if (!test_thread_flag(TIF_SINGLESTEP)) {
- ptrace_report_syscall_exit(regs, 0);
- regs->regs[regno] = saved_reg;
- } else {
- regs->regs[regno] = saved_reg;
-
- /*
- * Signal a pseudo-step exception since we are stepping but
- * tracer modifications to the registers may have rewound the
- * state machine.
- */
- ptrace_report_syscall_exit(regs, 1);
- }
-}
-
-static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
-{
- if (unlikely(audit_context())) {
- unsigned long args[6];
-
- syscall_get_arguments(current, regs, args);
- audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
- }
-}
-
-int syscall_trace_enter(struct pt_regs *regs, unsigned long flags)
-{
- long syscall;
- int ret;
-
- if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
- ret = report_syscall_entry(regs);
- if (ret || (flags & _TIF_SYSCALL_EMU))
- return NO_SYSCALL;
- }
-
- /* Do the secure computing after ptrace; failures should be fast. */
- if (flags & _TIF_SECCOMP) {
- if (!__secure_computing())
- return NO_SYSCALL;
- }
-
- /* Either of the above might have changed the syscall number */
- syscall = syscall_get_nr(current, regs);
-
- if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) {
- trace_sys_enter(regs, syscall);
-
- /*
- * Probes or BPF hooks in the tracepoint may have changed the
- * system call number as well.
- */
- syscall = syscall_get_nr(current, regs);
- }
-
- syscall_enter_audit(regs, syscall);
-
- return syscall;
-}
-
-static inline bool report_single_step(unsigned long flags)
-{
- if (flags & _TIF_SYSCALL_EMU)
- return false;
-
- return flags & _TIF_SINGLESTEP;
-}
-
-void syscall_exit_work(struct pt_regs *regs, unsigned long flags)
-{
- bool step;
-
- audit_syscall_exit(regs);
-
- if (flags & _TIF_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
- step = report_single_step(flags);
- if (step || flags & _TIF_SYSCALL_TRACE)
- report_syscall_exit(regs);
-}
-
/*
* SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a.
* We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 38e6fa204c17..093eebb9d764 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -8,8 +8,8 @@
#include <linux/cache.h>
#include <linux/compat.h>
+#include <linux/entry-common.h>
#include <linux/errno.h>
-#include <linux/irq-entry-common.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/freezer.h>
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 275cde8ab6f4..41a3b70a9374 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -2,6 +2,7 @@
#include <linux/compiler.h>
#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
#include <linux/errno.h>
#include <linux/nospec.h>
#include <linux/ptrace.h>
@@ -58,6 +59,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
const syscall_fn_t syscall_table[])
{
unsigned long flags = read_thread_flags();
+ unsigned long work;
regs->orig_x0 = regs->regs[0];
regs->syscallno = scno;
@@ -90,7 +92,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
return;
}
- if (unlikely(flags & _TIF_SYSCALL_WORK)) {
+ work = READ_ONCE(current_thread_info()->syscall_work);
+ if (unlikely(work & SYSCALL_WORK_ENTER)) {
/*
* The de-facto standard way to skip a system call using ptrace
* is to set the system call to -1 (NO_SYSCALL) and set x0 to a
@@ -108,7 +111,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
*/
if (scno == NO_SYSCALL)
syscall_set_return_value(current, regs, -ENOSYS, 0);
- scno = syscall_trace_enter(regs, read_thread_flags());
+ scno = syscall_trace_enter(regs, work);
if (scno == NO_SYSCALL)
goto trace_exit;
}
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox