[PATCH v4 1/2] printk: stop including cache.h from printk.h

[PATCH v4 1/2] printk: stop including cache.h from printk.h

[Peter Collingbourne]

An inclusion of cache.h in printk.h was added in 2014 in
commit c28aa1f0a847 ("printk/cache: mark printk_once test variable
__read_mostly") in order to bring in the definition of __read_mostly. The
usage of __read_mostly was later removed in commit 3ec25826ae33 ("printk:
Tie printk_once / printk_deferred_once into .data.once for reset")
which made the inclusion of cache.h unnecessary, so remove it.

We have a small amount of code that depended on the inclusion of cache.h
from printk.h; fix that code to include the appropriate header.

This fixes a circular inclusion on arm64 (linux/printk.h -> linux/cache.h
-> asm/cache.h -> linux/kasan-enabled.h -> linux/static_key.h ->
linux/jump_label.h -> linux/bug.h -> asm/bug.h -> linux/printk.h) that
would otherwise be introduced by the next patch.

Build tested using {allyesconfig,defconfig} x {arm64,x86_64}.

Link: https://linux-review.googlesource.com/id/I8fd51f72c9ef1f2d6afd3b2cbc875aa4792c1fba
Signed-off-by: Peter Collingbourne <pcc@google.com>
---
 arch/arm64/include/asm/mte-kasan.h | 1 +
 arch/arm64/include/asm/percpu.h    | 1 +
 drivers/firmware/smccc/kvm_guest.c | 1 +
 include/linux/printk.h             | 1 -
 4 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h
index a857bcacf0fe..9f79425fc65a 100644
--- a/arch/arm64/include/asm/mte-kasan.h
+++ b/arch/arm64/include/asm/mte-kasan.h
@@ -6,6 +6,7 @@
 #define __ASM_MTE_KASAN_H
 
 #include <asm/compiler.h>
+#include <asm/cputype.h>
 #include <asm/mte-def.h>
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 8f1661603b78..b9ba19dbdb69 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -10,6 +10,7 @@
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/stack_pointer.h>
+#include <asm/sysreg.h>
 
 static inline void set_my_cpu_offset(unsigned long off)
 {
diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c
index 2d3e866decaa..89a68e7eeaa6 100644
--- a/drivers/firmware/smccc/kvm_guest.c
+++ b/drivers/firmware/smccc/kvm_guest.c
@@ -4,6 +4,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/bitmap.h>
+#include <linux/cache.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 1522df223c0f..8e8d74edf121 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -6,7 +6,6 @@
 #include <linux/init.h>
 #include <linux/kern_levels.h>
 #include <linux/linkage.h>
-#include <linux/cache.h>
 #include <linux/ratelimit_types.h>
 #include <linux/once_lite.h>
 
-- 
2.36.0.rc2.479.g8af0fa9b8e-goog

[PATCH v4 2/2] mm: make minimum slab alignment a runtime property

[Peter Collingbourne]

When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum
slab alignment to 16. This happens even if MTE is not supported in
hardware or disabled via kasan=off, which creates an unnecessary
memory overhead in those cases. Eliminate this overhead by making
the minimum slab alignment a runtime property and only aligning to
16 if KASAN is enabled at runtime.

On a DragonBoard 845c (non-MTE hardware) with a kernel built with
CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android
boot I see the following Slab measurements in /proc/meminfo (median
of 3 reboots):

Before: 169020 kB
After:  167304 kB

Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
v4:
- add a dependent patch to fix the build with CONFIG_JUMP_LABEL disabled

v3:
- go back to ARCH_SLAB_MINALIGN
- revert changes to fs/binfmt_flat.c
- update arch_slab_minalign() comment to say that it must be a power of two

v2:
- use max instead of max_t in flat_stack_align()

 arch/arm64/include/asm/cache.h | 17 ++++++++++++-----
 include/linux/slab.h           | 12 ++++++++++++
 mm/slab.c                      |  7 +++----
 mm/slab_common.c               |  3 +--
 mm/slob.c                      |  6 +++---
 5 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index a074459f8f2f..22b22dc1b1b5 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -6,6 +6,7 @@
 #define __ASM_CACHE_H
 
 #include <asm/cputype.h>
+#include <asm/mte-def.h>
 
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
@@ -49,16 +50,22 @@
  */
 #define ARCH_DMA_MINALIGN	(128)
 
+#ifndef __ASSEMBLY__
+
+#include <linux/bitops.h>
+#include <linux/kasan-enabled.h>
+
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
 #elif defined(CONFIG_KASAN_HW_TAGS)
-#define ARCH_SLAB_MINALIGN	MTE_GRANULE_SIZE
+static inline size_t arch_slab_minalign(void)
+{
+	return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE :
+					 __alignof__(unsigned long long);
+}
+#define arch_slab_minalign() arch_slab_minalign()
 #endif
 
-#ifndef __ASSEMBLY__
-
-#include <linux/bitops.h>
-
 #define ICACHEF_ALIASING	0
 #define ICACHEF_VPIPT		1
 extern unsigned long __icache_flags;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 373b3ef99f4e..2c7190db4cc0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -209,6 +209,18 @@ void kmem_dump_obj(void *object);
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
 
+/*
+ * Arches can define this function if they want to decide the minimum slab
+ * alignment at runtime. The value returned by the function must be a power
+ * of two and >= ARCH_SLAB_MINALIGN.
+ */
+#ifndef arch_slab_minalign
+static inline size_t arch_slab_minalign(void)
+{
+	return ARCH_SLAB_MINALIGN;
+}
+#endif
+
 /*
  * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
  * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
diff --git a/mm/slab.c b/mm/slab.c
index 0edb474edef1..97b756976c8b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3009,10 +3009,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
-	if (ARCH_SLAB_MINALIGN &&
-	    ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
-		pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n",
-		       objp, (int)ARCH_SLAB_MINALIGN);
+	if ((unsigned long)objp & (arch_slab_minalign() - 1)) {
+		pr_err("0x%px: not aligned to arch_slab_minalign()=%d\n", objp,
+		       (int)arch_slab_minalign());
 	}
 	return objp;
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2b3206a2c3b5..33cc49810a54 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -154,8 +154,7 @@ static unsigned int calculate_alignment(slab_flags_t flags,
 		align = max(align, ralign);
 	}
 
-	if (align < ARCH_SLAB_MINALIGN)
-		align = ARCH_SLAB_MINALIGN;
+	align = max_t(size_t, align, arch_slab_minalign());
 
 	return ALIGN(align, sizeof(void *));
 }
diff --git a/mm/slob.c b/mm/slob.c
index 40ea6e2d4ccd..3bd2669bd690 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -478,7 +478,7 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign());
 	void *ret;
 
 	gfp &= gfp_allowed_mask;
@@ -555,7 +555,7 @@ void kfree(const void *block)
 
 	sp = virt_to_folio(block);
 	if (folio_test_slab(sp)) {
-		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign());
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
 	} else {
@@ -584,7 +584,7 @@ size_t __ksize(const void *block)
 	if (unlikely(!folio_test_slab(folio)))
 		return folio_size(folio);
 
-	align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	align = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign());
 	m = (unsigned int *)(block - align);
 	return SLOB_UNITS(*m) * SLOB_UNIT;
 }
-- 
2.36.0.rc2.479.g8af0fa9b8e-goog

Re: [PATCH v4 1/2] printk: stop including cache.h from printk.h

[kernel test robot]

Hi Peter,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on vbabka-slab/for-next]
[also build test ERROR on arm64/for-next/core linus/master v5.18-rc4 next-20220426]
[cannot apply to dennis-percpu/for-next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/intel-lab-lkp/linux/commits/Peter-Collingbourne/printk-stop-including-cache-h-from-printk-h/20220427-043357
base:   git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git for-next
config: arm-randconfig-r025-20220425 (https://download.01.org/0day-ci/archive/20220427/202204271135.P05x34Pe-lkp@intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project 1cddcfdc3c683b393df1a5c9063252eb60e52818)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install arm cross compiling tool for clang build
        # apt-get install binutils-arm-linux-gnueabi
        # https://github.com/intel-lab-lkp/linux/commit/edcb0f592304f7849a39586f9e3fe0d8f6e6c6b9
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Peter-Collingbourne/printk-stop-including-cache-h-from-printk-h/20220427-043357
        git checkout edcb0f592304f7849a39586f9e3fe0d8f6e6c6b9
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=arm SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   In file included from kernel/bpf/bpf_lru_list.c:8:
>> kernel/bpf/bpf_lru_list.h:36:21: error: expected ';' at end of declaration list
           raw_spinlock_t lock ____cacheline_aligned_in_smp;
                              ^
                              ;
   1 error generated.


vim +36 kernel/bpf/bpf_lru_list.h

3a08c2fd763450a Martin KaFai Lau 2016-11-11  29  
3a08c2fd763450a Martin KaFai Lau 2016-11-11  30  struct bpf_lru_list {
3a08c2fd763450a Martin KaFai Lau 2016-11-11  31  	struct list_head lists[NR_BPF_LRU_LIST_T];
3a08c2fd763450a Martin KaFai Lau 2016-11-11  32  	unsigned int counts[NR_BPF_LRU_LIST_COUNT];
0ac16296ffc638f Qiujun Huang     2020-04-03  33  	/* The next inactive list rotation starts from here */
3a08c2fd763450a Martin KaFai Lau 2016-11-11  34  	struct list_head *next_inactive_rotation;
3a08c2fd763450a Martin KaFai Lau 2016-11-11  35  
3a08c2fd763450a Martin KaFai Lau 2016-11-11 @36  	raw_spinlock_t lock ____cacheline_aligned_in_smp;
3a08c2fd763450a Martin KaFai Lau 2016-11-11  37  };
3a08c2fd763450a Martin KaFai Lau 2016-11-11  38  

-- 
0-DAY CI Kernel Test Service
https://01.org/lkp

Re: [PATCH v4 1/2] printk: stop including cache.h from printk.h

[kernel test robot]

Hi Peter,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on vbabka-slab/for-next]
[also build test ERROR on arm64/for-next/core linus/master v5.18-rc4 next-20220427]
[cannot apply to dennis-percpu/for-next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/intel-lab-lkp/linux/commits/Peter-Collingbourne/printk-stop-including-cache-h-from-printk-h/20220427-043357
base:   git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git for-next
config: csky-randconfig-r031-20220425 (https://download.01.org/0day-ci/archive/20220427/202204271721.kgeFN450-lkp@intel.com/config)
compiler: csky-linux-gcc (GCC) 11.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/edcb0f592304f7849a39586f9e3fe0d8f6e6c6b9
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Peter-Collingbourne/printk-stop-including-cache-h-from-printk-h/20220427-043357
        git checkout edcb0f592304f7849a39586f9e3fe0d8f6e6c6b9
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.3.0 make.cross W=1 O=build_dir ARCH=csky prepare

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   In file included from include/linux/compiler_types.h:73,
                    from <command-line>:
>> arch/csky/include/asm/processor.h:19:13: error: 'SMP_CACHE_BYTES' undeclared here (not in a function); did you mean 'L1_CACHE_BYTES'?
      19 | } __aligned(SMP_CACHE_BYTES);
         |             ^~~~~~~~~~~~~~~
   include/linux/compiler_attributes.h:33:68: note: in definition of macro '__aligned'
      33 | #define __aligned(x)                    __attribute__((__aligned__(x)))
         |                                                                    ^
   make[2]: *** [scripts/Makefile.build:120: arch/csky/kernel/asm-offsets.s] Error 1
   make[2]: Target '__build' not remade because of errors.
   make[1]: *** [Makefile:1194: prepare0] Error 2
   make[1]: Target 'prepare' not remade because of errors.
   make: *** [Makefile:219: __sub-make] Error 2
   make: Target 'prepare' not remade because of errors.


vim +19 arch/csky/include/asm/processor.h

e9564df753fd547 Guo Ren 2018-09-05  16  
e9564df753fd547 Guo Ren 2018-09-05  17  struct cpuinfo_csky {
e9564df753fd547 Guo Ren 2018-09-05  18  	unsigned long asid_cache;
e9564df753fd547 Guo Ren 2018-09-05 @19  } __aligned(SMP_CACHE_BYTES);
e9564df753fd547 Guo Ren 2018-09-05  20  

-- 
0-DAY CI Kernel Test Service
https://01.org/lkp