[PATCH AUTOSEL 6.1 01/14] asm-generic: make sparse happy with odd-sized put_unaligned_*()

[PATCH AUTOSEL 6.1 01/14] asm-generic: make sparse happy with odd-sized put_unaligned_*()

[Sasha Levin]

From: Dmitry Torokhov <dmitry.torokhov@gmail.com>

[ Upstream commit 1ab33c03145d0f6c345823fc2da935d9a1a9e9fc ]

__put_unaligned_be24() and friends use implicit casts to convert
larger-sized data to bytes, which trips sparse truncation warnings when
the argument is a constant:

    CC [M]  drivers/input/touchscreen/hynitron_cstxxx.o
    CHECK   drivers/input/touchscreen/hynitron_cstxxx.c
  drivers/input/touchscreen/hynitron_cstxxx.c: note: in included file (through arch/x86/include/generated/asm/unaligned.h):
  include/asm-generic/unaligned.h:119:16: warning: cast truncates bits from constant value (aa01a0 becomes a0)
  include/asm-generic/unaligned.h:120:20: warning: cast truncates bits from constant value (aa01 becomes 1)
  include/asm-generic/unaligned.h:119:16: warning: cast truncates bits from constant value (ab00d0 becomes d0)
  include/asm-generic/unaligned.h:120:20: warning: cast truncates bits from constant value (ab00 becomes 0)

To avoid this let's mask off upper bits explicitly, the resulting code
should be exactly the same, but it will keep sparse happy.

Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Closes: https://lore.kernel.org/oe-kbuild-all/202401070147.gqwVulOn-lkp@intel.com/
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/asm-generic/unaligned.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
index 699650f81970..a84c64e5f11e 100644
--- a/include/asm-generic/unaligned.h
+++ b/include/asm-generic/unaligned.h
@@ -104,9 +104,9 @@ static inline u32 get_unaligned_le24(const void *p)
 
 static inline void __put_unaligned_be24(const u32 val, u8 *p)
 {
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be24(const u32 val, void *p)
@@ -116,9 +116,9 @@ static inline void put_unaligned_be24(const u32 val, void *p)
 
 static inline void __put_unaligned_le24(const u32 val, u8 *p)
 {
-	*p++ = val;
-	*p++ = val >> 8;
-	*p++ = val >> 16;
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
 }
 
 static inline void put_unaligned_le24(const u32 val, void *p)
@@ -128,12 +128,12 @@ static inline void put_unaligned_le24(const u32 val, void *p)
 
 static inline void __put_unaligned_be48(const u64 val, u8 *p)
 {
-	*p++ = val >> 40;
-	*p++ = val >> 32;
-	*p++ = val >> 24;
-	*p++ = val >> 16;
-	*p++ = val >> 8;
-	*p++ = val;
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
 }
 
 static inline void put_unaligned_be48(const u64 val, void *p)
-- 
2.43.0

[PATCH AUTOSEL 6.1 04/14] arm64: irq: set the correct node for VMAP stack

[Sasha Levin]

From: Huang Shijie <shijie@os.amperecomputing.com>

[ Upstream commit 75b5e0bf90bffaca4b1f19114065dc59f5cc161f ]

In current code, init_irq_stacks() will call cpu_to_node().
The cpu_to_node() depends on percpu "numa_node" which is initialized in:
     arch_call_rest_init() --> rest_init() -- kernel_init()
	--> kernel_init_freeable() --> smp_prepare_cpus()

But init_irq_stacks() is called in init_IRQ() which is before
arch_call_rest_init().

So in init_irq_stacks(), the cpu_to_node() does not work, it
always return 0. In NUMA, it makes the node 1 cpu accesses the IRQ stack which
is in the node 0.

This patch fixes it by:
  1.) export the early_cpu_to_node(), and use it in the init_irq_stacks().
  2.) change init_irq_stacks() to __init function.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20231124031513.81548-1-shijie@os.amperecomputing.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm64/kernel/irq.c    | 5 +++--
 drivers/base/arch_numa.c   | 2 +-
 include/asm-generic/numa.h | 2 ++
 3 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 38dbd3828f13..d9db544285c4 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/exception.h>
+#include <asm/numa.h>
 #include <asm/vmap_stack.h>
 #include <asm/softirq_stack.h>
 
@@ -50,13 +51,13 @@ static void init_irq_scs(void)
 }
 
 #ifdef CONFIG_VMAP_STACK
-static void init_irq_stacks(void)
+static void __init init_irq_stacks(void)
 {
 	int cpu;
 	unsigned long *p;
 
 	for_each_possible_cpu(cpu) {
-		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu));
 		per_cpu(irq_stack_ptr, cpu) = p;
 	}
 }
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index eaa31e567d1e..5b59d133b6af 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
-static int __init early_cpu_to_node(int cpu)
+int __init early_cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }
diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h
index 1a3ad6d29833..c32e0cf23c90 100644
--- a/include/asm-generic/numa.h
+++ b/include/asm-generic/numa.h
@@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end);
 void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+int __init early_cpu_to_node(int cpu);
 void numa_store_cpu_info(unsigned int cpu);
 void numa_add_cpu(unsigned int cpu);
 void numa_remove_cpu(unsigned int cpu);
@@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { }
 static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arch_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+static inline int early_cpu_to_node(int cpu) { return 0; }
 
 #endif	/* CONFIG_NUMA */
 
-- 
2.43.0