[PATCH mm-hotfixes v5 1/2] Introduce cpu_icache_is_aliasing() across all architectures

[PATCH mm-hotfixes v5 1/2] Introduce cpu_icache_is_aliasing() across all architectures

[Zi Yan]

In commit eacd0e950dc2 ("ARC: [mm] Lazy D-cache flush (non aliasing
VIPT)"), arc adds the need to flush dcache to make icache see the code
page change. This also requires special handling for
clear_user_(high)page(). Introduce cpu_icache_is_aliasing() to make
MM code query special clear_user_(high)page() easier. This will be used
by the following commit.

Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 arch/arc/Kconfig                 | 1 +
 arch/arc/include/asm/cachetype.h | 8 ++++++++
 include/linux/cacheinfo.h        | 6 ++++++
 3 files changed, 15 insertions(+)
 create mode 100644 arch/arc/include/asm/cachetype.h

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5b2488142041..e96935373796 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -6,6 +6,7 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_CPU_CACHE_ALIASING
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DMA_PREP_COHERENT
diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h
new file mode 100644
index 000000000000..acd3b6cb4bf5
--- /dev/null
+++ b/arch/arc/include/asm/cachetype.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ARC_CACHETYPE_H
+#define __ASM_ARC_CACHETYPE_H
+
+#define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	true
+
+#endif
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 108060612bb8..7ad736538649 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level)
 
 #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING
 #define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
 #else
 #include <asm/cachetype.h>
+
+#ifndef cpu_icache_is_aliasing
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
+#endif
+
 #endif
 
 #endif /* _LINUX_CACHEINFO_H */
-- 
2.45.2

[PATCH mm-hotfixes v5 2/2] mm: use clear_user_(high)page() for arch with special user folio handling

[Zi Yan]

Some architectures have special handling after clearing user folios:
architectures, which set cpu_dcache_is_aliasing() to true, require
flushing dcache; arc, which sets cpu_icache_is_aliasing() to true, changes
folio->flags to make icache coherent to dcache. So __GFP_ZERO using only
clear_page() is not enough to zero user folios and clear_user_(high)page()
must be used. Otherwise, user data will be corrupted.

Fix it by always clearing user folios with clear_user_(high)page() when
cpu_dcache_is_aliasing() is true or cpu_icache_is_aliasing() is true.
Rename alloc_zeroed() to user_alloc_needs_zeroing() and invert the logic
to clarify its intend.

Fixes: 5708d96da20b ("mm: avoid zeroing user movable page twice with init_on_alloc=1")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Closes: https://lore.kernel.org/linux-mm/CAMuHMdV1hRp_NtR5YnJo=HsfgKQeH91J537Gh4gKk3PFZhSkbA@mail.gmail.com/
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/highmem.h |  8 +++++++-
 include/linux/mm.h      | 18 ++++++++++++++++++
 mm/huge_memory.c        |  9 +++++----
 mm/internal.h           |  6 ------
 mm/memory.c             | 10 +++++-----
 5 files changed, 35 insertions(+), 16 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 6e452bd8e7e3..5c6bea81a90e 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -224,7 +224,13 @@ static inline
 struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
 				   unsigned long vaddr)
 {
-	return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr);
+	struct folio *folio;
+
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
+	if (folio && user_alloc_needs_zeroing())
+		clear_user_highpage(&folio->page, vaddr);
+
+	return folio;
 }
 #endif
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c39c4945946c..6c853b0c4f91 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -31,6 +31,7 @@
 #include <linux/kasan.h>
 #include <linux/memremap.h>
 #include <linux/slab.h>
+#include <linux/cacheinfo.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -4175,6 +4176,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla
 }
 #endif
 
+/*
+ * user_alloc_needs_zeroing checks if a user folio from page allocator needs to
+ * be zeroed or not.
+ */
+static inline bool user_alloc_needs_zeroing(void)
+{
+	/*
+	 * for user folios, arch with cache aliasing requires cache flush and
+	 * arc changes folio->flags to make icache coherent with dcache, so
+	 * always return false to make caller use
+	 * clear_user_page()/clear_user_highpage().
+	 */
+	return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() ||
+	       !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+				   &init_on_alloc);
+}
+
 int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
 int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
 int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ee335d96fc39..9bb351caa619 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1176,11 +1176,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
 	folio_throttle_swaprate(folio, gfp);
 
        /*
-	* When a folio is not zeroed during allocation (__GFP_ZERO not used),
-	* folio_zero_user() is used to make sure that the page corresponding
-	* to the faulting address will be hot in the cache after zeroing.
+	* When a folio is not zeroed during allocation (__GFP_ZERO not used)
+	* or user folios require special handling, folio_zero_user() is used to
+	* make sure that the page corresponding to the faulting address will be
+	* hot in the cache after zeroing.
 	*/
-	if (!alloc_zeroed())
+	if (user_alloc_needs_zeroing())
 		folio_zero_user(folio, addr);
 	/*
 	 * The memory barrier inside __folio_mark_uptodate makes sure that
diff --git a/mm/internal.h b/mm/internal.h
index cb8d8e8e3ffa..3bd08bafad04 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1285,12 +1285,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
 void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 	       pmd_t *pmd, bool write);
 
-static inline bool alloc_zeroed(void)
-{
-	return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
-			&init_on_alloc);
-}
-
 /*
  * Parses a string with mem suffixes into its order. Useful to parse kernel
  * parameters.
diff --git a/mm/memory.c b/mm/memory.c
index 75c2dfd04f72..da8b2e8ab796 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4733,12 +4733,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
 			folio_throttle_swaprate(folio, gfp);
 			/*
 			 * When a folio is not zeroed during allocation
-			 * (__GFP_ZERO not used), folio_zero_user() is used
-			 * to make sure that the page corresponding to the
-			 * faulting address will be hot in the cache after
-			 * zeroing.
+			 * (__GFP_ZERO not used) or user folios require special
+			 * handling, folio_zero_user() is used to make sure
+			 * that the page corresponding to the faulting address
+			 * will be hot in the cache after zeroing.
 			 */
-			if (!alloc_zeroed())
+			if (user_alloc_needs_zeroing())
 				folio_zero_user(folio, vmf->address);
 			return folio;
 		}
-- 
2.45.2