From: Dmitry Torokhov <[email protected]>
[ 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 <[email protected]>
Suggested-by: Linus Torvalds <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Signed-off-by: Dmitry Torokhov <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
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
From: Kunwu Chan <[email protected]>
[ Upstream commit f46c8a75263f97bda13c739ba1c90aced0d3b071 ]
kasprintf() returns a pointer to dynamically allocated memory
which can be NULL upon failure. Ensure the allocation was successful
by checking the pointer validity.
Suggested-by: Christophe Leroy <[email protected]>
Suggested-by: Michael Ellerman <[email protected]>
Signed-off-by: Kunwu Chan <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/mm/init-common.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
index 119ef491f797..d3a7726ecf51 100644
--- a/arch/powerpc/mm/init-common.c
+++ b/arch/powerpc/mm/init-common.c
@@ -126,7 +126,7 @@ void pgtable_cache_add(unsigned int shift)
* as to leave enough 0 bits in the address to contain it. */
unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
HUGEPD_SHIFT_MASK + 1);
- struct kmem_cache *new;
+ struct kmem_cache *new = NULL;
/* It would be nice if this was a BUILD_BUG_ON(), but at the
* moment, gcc doesn't seem to recognize is_power_of_2 as a
@@ -139,7 +139,8 @@ void pgtable_cache_add(unsigned int shift)
align = max_t(unsigned long, align, minalign);
name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
- new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
+ if (name)
+ new = kmem_cache_create(name, table_size, align, 0, ctor(shift));
if (!new)
panic("Could not allocate pgtable cache for order %d", shift);
--
2.43.0
From: Dmitry Antipov <[email protected]>
[ Upstream commit 1bfc466b13cf6652ba227c282c27a30ffede69a5 ]
When compiling with gcc version 14.0.0 20231220 (experimental)
and W=1, I've noticed the following warning:
kernel/watch_queue.c: In function 'watch_queue_set_size':
kernel/watch_queue.c:273:32: warning: 'kcalloc' sizes specified with 'sizeof'
in the earlier argument and not in the later argument [-Wcalloc-transposed-args]
273 | pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
| ^~~~~~
Since 'n' and 'size' arguments of 'kcalloc()' are multiplied to
calculate the final size, their actual order doesn't affect the
result and so this is not a bug. But it's still worth to fix it.
Signed-off-by: Dmitry Antipov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Christian Brauner <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/watch_queue.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 442bb92212f2..9bdcfdef0509 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -271,7 +271,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
goto error;
ret = -ENOMEM;
- pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto error;
--
2.43.0
From: Huang Shijie <[email protected]>
[ 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 <[email protected]>
Signed-off-by: Huang Shijie <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
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
From: Michael Ellerman <[email protected]>
[ Upstream commit f8d3555355653848082c351fa90775214fb8a4fa ]
With CONFIG_GENERIC_BUG=n the build fails with:
arch/powerpc/kernel/traps.c:1442:5: error: no previous prototype for ‘is_valid_bugaddr’ [-Werror=missing-prototypes]
1442 | int is_valid_bugaddr(unsigned long addr)
| ^~~~~~~~~~~~~~~~
The prototype is only defined, and the function is only needed, when
CONFIG_GENERIC_BUG=y, so move the implementation under that.
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/kernel/traps.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 3956f32682c6..362b712386f6 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1439,10 +1439,12 @@ static int emulate_instruction(struct pt_regs *regs)
return -EINVAL;
}
+#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long addr)
{
return is_kernel_addr(addr);
}
+#endif
#ifdef CONFIG_MATH_EMULATION
static int emulate_math(struct pt_regs *regs)
--
2.43.0
From: Michael Ellerman <[email protected]>
[ Upstream commit ede66cd22441820cbd399936bf84fdc4294bc7fa ]
With CONFIG_NUMA=n the build fails with:
arch/powerpc/mm/book3s64/pgtable.c:275:15: error: no previous prototype for ‘create_section_mapping’ [-Werror=missing-prototypes]
275 | int __meminit create_section_mapping(unsigned long start, unsigned long end,
| ^~~~~~~~~~~~~~~~~~~~~~
That happens because the prototype for create_section_mapping() is in
asm/mmzone.h, but asm/mmzone.h is only included by linux/mmzone.h
when CONFIG_NUMA=y.
In fact the prototype is only needed by arch/powerpc/mm code, so move
the prototype into arch/powerpc/mm/mmu_decl.h, which also fixes the
build error.
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/include/asm/mmzone.h | 5 -----
arch/powerpc/mm/mmu_decl.h | 5 +++++
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 3764d3585d30..da827d2d0866 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -43,10 +43,5 @@ u64 memory_hotplug_max(void);
#define memory_hotplug_max() memblock_end_of_DRAM()
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_MEMORY_HOTPLUG
-extern int create_section_mapping(unsigned long start, unsigned long end,
- int nid, pgprot_t prot);
-#endif
-
#endif /* __KERNEL__ */
#endif /* _ASM_MMZONE_H_ */
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index bd9784f77f2e..71250605b784 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -179,3 +179,8 @@ static inline bool debug_pagealloc_enabled_or_kfence(void)
{
return IS_ENABLED(CONFIG_KFENCE) || debug_pagealloc_enabled();
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int create_section_mapping(unsigned long start, unsigned long end,
+ int nid, pgprot_t prot);
+#endif
--
2.43.0
From: Jun'ichi Nomura <[email protected]>
[ Upstream commit 78a509fba9c9b1fcb77f95b7c6be30da3d24823a ]
When there are two racing NMIs on x86, the first NMI invokes NMI handler and
the 2nd NMI is latched until IRET is executed.
If panic on NMI and panic kexec are enabled, the first NMI triggers
panic and starts booting the next kernel via kexec. Note that the 2nd
NMI is still latched. During the early boot of the next kernel, once
an IRET is executed as a result of a page fault, then the 2nd NMI is
unlatched and invokes the NMI handler.
However, NMI handler is not set up at the early stage of boot, which
results in a boot failure.
Avoid such problems by setting up a NOP handler for early NMIs.
[ mingo: Refined the changelog. ]
Signed-off-by: Jun'ichi Nomura <[email protected]>
Signed-off-by: Derek Barbosa <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Paul E. McKenney <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/boot/compressed/ident_map_64.c | 5 +++++
arch/x86/boot/compressed/idt_64.c | 1 +
arch/x86/boot/compressed/idt_handlers_64.S | 1 +
arch/x86/boot/compressed/misc.h | 1 +
4 files changed, 8 insertions(+)
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index b4155273df89..d34222816c9f 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -393,3 +393,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
*/
kernel_add_identity_map(address, end);
}
+
+void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code)
+{
+ /* Empty handler to ignore NMI during early boot */
+}
diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c
index 3cdf94b41456..d100284bbef4 100644
--- a/arch/x86/boot/compressed/idt_64.c
+++ b/arch/x86/boot/compressed/idt_64.c
@@ -61,6 +61,7 @@ void load_stage2_idt(void)
boot_idt_desc.address = (unsigned long)boot_idt;
set_idt_entry(X86_TRAP_PF, boot_page_fault);
+ set_idt_entry(X86_TRAP_NMI, boot_nmi_trap);
#ifdef CONFIG_AMD_MEM_ENCRYPT
/*
diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S
index 22890e199f5b..4d03c8562f63 100644
--- a/arch/x86/boot/compressed/idt_handlers_64.S
+++ b/arch/x86/boot/compressed/idt_handlers_64.S
@@ -70,6 +70,7 @@ SYM_FUNC_END(\name)
.code64
EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1
+EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0
#ifdef CONFIG_AMD_MEM_ENCRYPT
EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 20118fb7c53b..a49d9219c06e 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -190,6 +190,7 @@ static inline void cleanup_exception_handling(void) { }
/* IDT Entry Points */
void boot_page_fault(void);
+void boot_nmi_trap(void);
void boot_stage1_vc(void);
void boot_stage2_vc(void);
--
2.43.0
From: "Borislav Petkov (AMD)" <[email protected]>
[ Upstream commit 04c3024560d3a14acd18d0a51a1d0a89d29b7eb5 ]
AMD does not have the requirement for a synchronization barrier when
acccessing a certain group of MSRs. Do not incur that unnecessary
penalty there.
There will be a CPUID bit which explicitly states that a MFENCE is not
needed. Once that bit is added to the APM, this will be extended with
it.
While at it, move to processor.h to avoid include hell. Untangling that
file properly is a matter for another day.
Some notes on the performance aspect of why this is relevant, courtesy
of Kishon VijayAbraham <[email protected]>:
On a AMD Zen4 system with 96 cores, a modified ipi-bench[1] on a VM
shows x2AVIC IPI rate is 3% to 4% lower than AVIC IPI rate. The
ipi-bench is modified so that the IPIs are sent between two vCPUs in the
same CCX. This also requires to pin the vCPU to a physical core to
prevent any latencies. This simulates the use case of pinning vCPUs to
the thread of a single CCX to avoid interrupt IPI latency.
In order to avoid run-to-run variance (for both x2AVIC and AVIC), the
below configurations are done:
1) Disable Power States in BIOS (to prevent the system from going to
lower power state)
2) Run the system at fixed frequency 2500MHz (to prevent the system
from increasing the frequency when the load is more)
With the above configuration:
*) Performance measured using ipi-bench for AVIC:
Average Latency: 1124.98ns [Time to send IPI from one vCPU to another vCPU]
Cumulative throughput: 42.6759M/s [Total number of IPIs sent in a second from
48 vCPUs simultaneously]
*) Performance measured using ipi-bench for x2AVIC:
Average Latency: 1172.42ns [Time to send IPI from one vCPU to another vCPU]
Cumulative throughput: 40.9432M/s [Total number of IPIs sent in a second from
48 vCPUs simultaneously]
From above, x2AVIC latency is ~4% more than AVIC. However, the expectation is
x2AVIC performance to be better or equivalent to AVIC. Upon analyzing
the perf captures, it is observed significant time is spent in
weak_wrmsr_fence() invoked by x2apic_send_IPI().
With the fix to skip weak_wrmsr_fence()
*) Performance measured using ipi-bench for x2AVIC:
Average Latency: 1117.44ns [Time to send IPI from one vCPU to another vCPU]
Cumulative throughput: 42.9608M/s [Total number of IPIs sent in a second from
48 vCPUs simultaneously]
Comparing the performance of x2AVIC with and without the fix, it can be seen
the performance improves by ~4%.
Performance captured using an unmodified ipi-bench using the 'mesh-ipi' option
with and without weak_wrmsr_fence() on a Zen4 system also showed significant
performance improvement without weak_wrmsr_fence(). The 'mesh-ipi' option ignores
CCX or CCD and just picks random vCPU.
Average throughput (10 iterations) with weak_wrmsr_fence(),
Cumulative throughput: 4933374 IPI/s
Average throughput (10 iterations) without weak_wrmsr_fence(),
Cumulative throughput: 6355156 IPI/s
[1] https://github.com/bytedance/kvm-utils/tree/master/microbenchmark/ipi-bench
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/include/asm/barrier.h | 18 ------------------
arch/x86/include/asm/cpufeatures.h | 2 +-
arch/x86/include/asm/processor.h | 18 ++++++++++++++++++
arch/x86/kernel/cpu/amd.c | 3 +++
arch/x86/kernel/cpu/common.c | 7 +++++++
arch/x86/kernel/cpu/hygon.c | 3 +++
6 files changed, 32 insertions(+), 19 deletions(-)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 35389b2af88e..0216f63a366b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -81,22 +81,4 @@ do { \
#include <asm-generic/barrier.h>
-/*
- * Make previous memory operations globally visible before
- * a WRMSR.
- *
- * MFENCE makes writes visible, but only affects load/store
- * instructions. WRMSR is unfortunately not a load/store
- * instruction and is unaffected by MFENCE. The LFENCE ensures
- * that the WRMSR is not reordered.
- *
- * Most WRMSRs are full serializing instructions themselves and
- * do not require this barrier. This is only required for the
- * IA32_TSC_DEADLINE and X2APIC MSRs.
- */
-static inline void weak_wrmsr_fence(void)
-{
- asm volatile("mfence; lfence" : : : "memory");
-}
-
#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b122708792c4..e7549e460884 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -307,10 +307,10 @@
#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
-
#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */
#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */
#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 94ea13adb724..1371511f1e7c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -869,4 +869,22 @@ bool arch_is_platform_page(u64 paddr);
extern bool gds_ucode_mitigated(void);
+/*
+ * Make previous memory operations globally visible before
+ * a WRMSR.
+ *
+ * MFENCE makes writes visible, but only affects load/store
+ * instructions. WRMSR is unfortunately not a load/store
+ * instruction and is unaffected by MFENCE. The LFENCE ensures
+ * that the WRMSR is not reordered.
+ *
+ * Most WRMSRs are full serializing instructions themselves and
+ * do not require this barrier. This is only required for the
+ * IA32_TSC_DEADLINE and X2APIC MSRs.
+ */
+static inline void weak_wrmsr_fence(void)
+{
+ alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE));
+}
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c1d09c8844d6..ef47cfc913f6 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1133,6 +1133,9 @@ static void init_amd(struct cpuinfo_x86 *c)
if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
cpu_has_amd_erratum(c, amd_erratum_1485))
msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+
+ /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 454cdf341862..e7937a69ed92 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1837,6 +1837,13 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
#endif
+
+ /*
+ * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and
+ * Hygon will clear it in ->c_init() below.
+ */
+ set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
/*
* Vendor-specific initialization. In this section we
* canonicalize the feature flags, meaning if there are
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 9e8380bd4fb9..8a80d5343f3a 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -347,6 +347,9 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
check_null_seg_clears_base(c);
+
+ /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
+ clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
}
static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
--
2.43.0
From: Miklos Szeredi <[email protected]>
[ Upstream commit 98d2b43081972abeb5bb5a087bc3e3197531c46e ]
If a mount is released then its mnt_id can immediately be reused. This is
bad news for user interfaces that want to uniquely identify a mount.
Implementing a unique mount ID is trivial (use a 64bit counter).
Unfortunately userspace assumes 32bit size and would overflow after the
counter reaches 2^32.
Introduce a new 64bit ID alongside the old one. Initialize the counter to
2^32, this guarantees that the old and new IDs are never mixed up.
Signed-off-by: Miklos Szeredi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Ian Kent <[email protected]>
Signed-off-by: Christian Brauner <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/mount.h | 3 ++-
fs/namespace.c | 4 ++++
fs/stat.c | 9 +++++++--
include/uapi/linux/stat.h | 1 +
4 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/fs/mount.h b/fs/mount.h
index 130c07c2f8d2..a14f762b3f29 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -72,7 +72,8 @@ struct mount {
struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
__u32 mnt_fsnotify_mask;
#endif
- int mnt_id; /* mount identifier */
+ int mnt_id; /* mount identifier, reused */
+ u64 mnt_id_unique; /* mount ID unique until reboot */
int mnt_group_id; /* peer group identifier */
int mnt_expiry_mark; /* true if marked for expiry */
struct hlist_head mnt_pins;
diff --git a/fs/namespace.c b/fs/namespace.c
index e04a9e9e3f14..12c8e2eeda91 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -68,6 +68,9 @@ static u64 event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
+/* Don't allow confusion with old 32bit mount ID */
+static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
+
static struct hlist_head *mount_hashtable __read_mostly;
static struct hlist_head *mountpoint_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly;
@@ -130,6 +133,7 @@ static int mnt_alloc_id(struct mount *mnt)
if (res < 0)
return res;
mnt->mnt_id = res;
+ mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
return 0;
}
diff --git a/fs/stat.c b/fs/stat.c
index ef50573c72a2..a003e891a682 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -232,8 +232,13 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
error = vfs_getattr(&path, stat, request_mask, flags);
- stat->mnt_id = real_mount(path.mnt)->mnt_id;
- stat->result_mask |= STATX_MNT_ID;
+ if (request_mask & STATX_MNT_ID_UNIQUE) {
+ stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
+ stat->result_mask |= STATX_MNT_ID_UNIQUE;
+ } else {
+ stat->mnt_id = real_mount(path.mnt)->mnt_id;
+ stat->result_mask |= STATX_MNT_ID;
+ }
if (path.mnt->mnt_root == path.dentry)
stat->attributes |= STATX_ATTR_MOUNT_ROOT;
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 7cab2c65d3d7..2f2ee82d5517 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -154,6 +154,7 @@ struct statx {
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
--
2.43.0
From: Mark Rutland <[email protected]>
[ Upstream commit ca6f537e459e2da4b331fe8928d1a0b0f9301f42 ]
The SW_INCR event is somewhat unusual, and depends on the specific HW
counter that it is programmed into. When programmed into PMEVCNTR<n>,
SW_INCR will count any writes to PMSWINC_EL0 with bit n set, ignoring
writes to SW_INCR with bit n clear.
Event rotation means that there's no fixed relationship between
perf_events and HW counters, so this isn't all that useful.
Further, we program PMUSERENR.{SW,EN}=={0,0}, which causes EL0 writes to
PMSWINC_EL0 to be trapped and handled as UNDEFINED, resulting in a
SIGILL to userspace.
Given that, it's not a good idea to expose SW_INCR in sysfs. Hide it as
we did for CHAIN back in commit:
4ba2578fa7b55701 ("arm64: perf: don't expose CHAIN event in sysfs")
Signed-off-by: Mark Rutland <[email protected]>
Cc: Will Deacon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/arm64/kernel/perf_event.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 7b0643fe2f13..214b1805e536 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -168,7 +168,11 @@ armv8pmu_events_sysfs_show(struct device *dev,
PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config)
static struct attribute *armv8_pmuv3_event_attrs[] = {
- ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
+ /*
+ * Don't expose the sw_incr event in /sys. It's not usable as writes to
+ * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation
+ * means we don't have a fixed event<->counter relationship regardless.
+ */
ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL),
ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL),
ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),
--
2.43.0
From: Michael Ellerman <[email protected]>
[ Upstream commit d8c3f243d4db24675b653f0568bb65dae34e6455 ]
With NUMA=n and FA_DUMP=y or PRESERVE_FA_DUMP=y the build fails with:
arch/powerpc/kernel/fadump.c:1739:22: error: no previous prototype for ‘arch_reserved_kernel_pages’ [-Werror=missing-prototypes]
1739 | unsigned long __init arch_reserved_kernel_pages(void)
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
The prototype for arch_reserved_kernel_pages() is in include/linux/mm.h,
but it's guarded by __HAVE_ARCH_RESERVED_KERNEL_PAGES. The powerpc
headers define __HAVE_ARCH_RESERVED_KERNEL_PAGES in asm/mmzone.h, which
is not included into the generic headers when NUMA=n.
Move the definition of __HAVE_ARCH_RESERVED_KERNEL_PAGES into asm/mmu.h
which is included regardless of NUMA=n.
Additionally the ifdef around __HAVE_ARCH_RESERVED_KERNEL_PAGES needs to
also check for CONFIG_PRESERVE_FA_DUMP.
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/include/asm/mmu.h | 4 ++++
arch/powerpc/include/asm/mmzone.h | 3 ---
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 94b981152667..07fabb054aea 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -417,5 +417,9 @@ extern void *abatron_pteptrs[2];
#include <asm/nohash/mmu.h>
#endif
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
+#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MMU_H_ */
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 4c6c6dbd182f..3764d3585d30 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -42,9 +42,6 @@ u64 memory_hotplug_max(void);
#else
#define memory_hotplug_max() memblock_end_of_DRAM()
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_FA_DUMP
-#define __HAVE_ARCH_RESERVED_KERNEL_PAGES
-#endif
#ifdef CONFIG_MEMORY_HOTPLUG
extern int create_section_mapping(unsigned long start, unsigned long end,
--
2.43.0
From: Stephen Rothwell <[email protected]>
[ Upstream commit 0d555b57ee660d8a871781c0eebf006e855e918d ]
The linux-next build of powerpc64 allnoconfig fails with:
arch/powerpc/mm/book3s64/pgtable.c:557:5: error: no previous prototype for 'pmd_move_must_withdraw'
557 | int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
| ^~~~~~~~~~~~~~~~~~~~~~
Caused by commit:
c6345dfa6e3e ("Makefile.extrawarn: turn on missing-prototypes globally")
Fix it by moving the function definition under
CONFIG_TRANSPARENT_HUGEPAGE like the prototype. The function is only
called when CONFIG_TRANSPARENT_HUGEPAGE=y.
Signed-off-by: Stephen Rothwell <[email protected]>
[mpe: Flesh out change log from linux-next patch]
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/mm/book3s64/pgtable.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index f6151a589298..87aa76c73799 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -463,6 +463,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* For hash translation mode, we use the deposited table to store hash slot
* information and they are stored at PTRS_PER_PMD offset from related pmd
@@ -484,6 +485,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
return true;
}
+#endif
/*
* Does the CPU support tlbie?
--
2.43.0
From: Naveen N Rao <[email protected]>
[ Upstream commit 8f9abaa6d7de0a70fc68acaedce290c1f96e2e59 ]
Some of the fp/vmx code in sstep.c assume a certain maximum size for the
instructions being emulated. The size of those operations however is
determined separately in analyse_instr().
Add a check to validate the assumption on the maximum size of the
operations, so as to prevent any unintended kernel stack corruption.
Signed-off-by: Naveen N Rao <[email protected]>
Reviewed-by: Gustavo A. R. Silva <[email protected]>
Build-tested-by: Gustavo A. R. Silva <[email protected]>
Signed-off-by: Michael Ellerman <[email protected]>
Link: https://msgid.link/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/powerpc/lib/sstep.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 398b5694aeb7..ec30af8eadb7 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -586,6 +586,8 @@ static int do_fp_load(struct instruction_op *op, unsigned long ea,
} u;
nb = GETSIZE(op->type);
+ if (nb > sizeof(u))
+ return -EINVAL;
if (!address_ok(regs, ea, nb))
return -EFAULT;
rn = op->reg;
@@ -636,6 +638,8 @@ static int do_fp_store(struct instruction_op *op, unsigned long ea,
} u;
nb = GETSIZE(op->type);
+ if (nb > sizeof(u))
+ return -EINVAL;
if (!address_ok(regs, ea, nb))
return -EFAULT;
rn = op->reg;
@@ -680,6 +684,9 @@ static nokprobe_inline int do_vec_load(int rn, unsigned long ea,
u8 b[sizeof(__vector128)];
} u = {};
+ if (size > sizeof(u))
+ return -EINVAL;
+
if (!address_ok(regs, ea & ~0xfUL, 16))
return -EFAULT;
/* align to multiple of size */
@@ -707,6 +714,9 @@ static nokprobe_inline int do_vec_store(int rn, unsigned long ea,
u8 b[sizeof(__vector128)];
} u;
+ if (size > sizeof(u))
+ return -EINVAL;
+
if (!address_ok(regs, ea & ~0xfUL, 16))
return -EFAULT;
/* align to multiple of size */
--
2.43.0
From: Zhiquan Li <[email protected]>
[ Upstream commit 9f3b130048bfa2e44a8cfb1b616f826d9d5d8188 ]
Memory errors don't happen very often, especially fatal ones. However,
in large-scale scenarios such as data centers, that probability
increases with the amount of machines present.
When a fatal machine check happens, mce_panic() is called based on the
severity grading of that error. The page containing the error is not
marked as poison.
However, when kexec is enabled, tools like makedumpfile understand when
pages are marked as poison and do not touch them so as not to cause
a fatal machine check exception again while dumping the previous
kernel's memory.
Therefore, mark the page containing the error as poisoned so that the
kexec'ed kernel can avoid accessing the page.
[ bp: Rewrite commit message and comment. ]
Co-developed-by: Youquan Song <[email protected]>
Signed-off-by: Youquan Song <[email protected]>
Signed-off-by: Zhiquan Li <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Reviewed-by: Naoya Horiguchi <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/kernel/cpu/mce/core.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index f1a748da5fab..cad6ea1911e9 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -44,6 +44,7 @@
#include <linux/sync_core.h>
#include <linux/task_work.h>
#include <linux/hardirq.h>
+#include <linux/kexec.h>
#include <asm/intel-family.h>
#include <asm/processor.h>
@@ -239,6 +240,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
struct llist_node *pending;
struct mce_evt_llist *l;
int apei_err = 0;
+ struct page *p;
/*
* Allow instrumentation around external facilities usage. Not that it
@@ -292,6 +294,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp)
if (!fake_panic) {
if (panic_timeout == 0)
panic_timeout = mca_cfg.panic_timeout;
+
+ /*
+ * Kdump skips the poisoned page in order to avoid
+ * touching the error bits again. Poison the page even
+ * if the error is fatal and the machine is about to
+ * panic.
+ */
+ if (kexec_crash_loaded()) {
+ if (final && (final->status & MCI_STATUS_ADDRV)) {
+ p = pfn_to_online_page(final->addr >> PAGE_SHIFT);
+ if (p)
+ SetPageHWPoison(p);
+ }
+ }
panic(msg);
} else
pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);
--
2.43.0
On Tue, Jan 16, 2024 at 1:46 AM Sasha Levin <[email protected]> wrote:
>
> From: Miklos Szeredi <[email protected]>
>
> [ Upstream commit 98d2b43081972abeb5bb5a087bc3e3197531c46e ]
>
> If a mount is released then its mnt_id can immediately be reused. This is
> bad news for user interfaces that want to uniquely identify a mount.
>
Sasha,
This is a new API, not a bug fix.
Maybe AUTOSEL was triggered by the words "This is bad news for user...."?
You have also selected this to other 6.*.y kernels.
Thanks,
Amir.
> Implementing a unique mount ID is trivial (use a 64bit counter).
> Unfortunately userspace assumes 32bit size and would overflow after the
> counter reaches 2^32.
>
> Introduce a new 64bit ID alongside the old one. Initialize the counter to
> 2^32, this guarantees that the old and new IDs are never mixed up.
>
> Signed-off-by: Miklos Szeredi <[email protected]>
> Link: https://lore.kernel.org/r/[email protected]
> Reviewed-by: Ian Kent <[email protected]>
> Signed-off-by: Christian Brauner <[email protected]>
> Signed-off-by: Sasha Levin <[email protected]>
> ---
> fs/mount.h | 3 ++-
> fs/namespace.c | 4 ++++
> fs/stat.c | 9 +++++++--
> include/uapi/linux/stat.h | 1 +
> 4 files changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/fs/mount.h b/fs/mount.h
> index 130c07c2f8d2..a14f762b3f29 100644
> --- a/fs/mount.h
> +++ b/fs/mount.h
> @@ -72,7 +72,8 @@ struct mount {
> struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
> __u32 mnt_fsnotify_mask;
> #endif
> - int mnt_id; /* mount identifier */
> + int mnt_id; /* mount identifier, reused */
> + u64 mnt_id_unique; /* mount ID unique until reboot */
> int mnt_group_id; /* peer group identifier */
> int mnt_expiry_mark; /* true if marked for expiry */
> struct hlist_head mnt_pins;
> diff --git a/fs/namespace.c b/fs/namespace.c
> index e04a9e9e3f14..12c8e2eeda91 100644
> --- a/fs/namespace.c
> +++ b/fs/namespace.c
> @@ -68,6 +68,9 @@ static u64 event;
> static DEFINE_IDA(mnt_id_ida);
> static DEFINE_IDA(mnt_group_ida);
>
> +/* Don't allow confusion with old 32bit mount ID */
> +static atomic64_t mnt_id_ctr = ATOMIC64_INIT(1ULL << 32);
> +
> static struct hlist_head *mount_hashtable __read_mostly;
> static struct hlist_head *mountpoint_hashtable __read_mostly;
> static struct kmem_cache *mnt_cache __read_mostly;
> @@ -130,6 +133,7 @@ static int mnt_alloc_id(struct mount *mnt)
> if (res < 0)
> return res;
> mnt->mnt_id = res;
> + mnt->mnt_id_unique = atomic64_inc_return(&mnt_id_ctr);
> return 0;
> }
>
> diff --git a/fs/stat.c b/fs/stat.c
> index ef50573c72a2..a003e891a682 100644
> --- a/fs/stat.c
> +++ b/fs/stat.c
> @@ -232,8 +232,13 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
>
> error = vfs_getattr(&path, stat, request_mask, flags);
>
> - stat->mnt_id = real_mount(path.mnt)->mnt_id;
> - stat->result_mask |= STATX_MNT_ID;
> + if (request_mask & STATX_MNT_ID_UNIQUE) {
> + stat->mnt_id = real_mount(path.mnt)->mnt_id_unique;
> + stat->result_mask |= STATX_MNT_ID_UNIQUE;
> + } else {
> + stat->mnt_id = real_mount(path.mnt)->mnt_id;
> + stat->result_mask |= STATX_MNT_ID;
> + }
>
> if (path.mnt->mnt_root == path.dentry)
> stat->attributes |= STATX_ATTR_MOUNT_ROOT;
> diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
> index 7cab2c65d3d7..2f2ee82d5517 100644
> --- a/include/uapi/linux/stat.h
> +++ b/include/uapi/linux/stat.h
> @@ -154,6 +154,7 @@ struct statx {
> #define STATX_BTIME 0x00000800U /* Want/got stx_btime */
> #define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
> #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
> +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
>
> #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
>
> --
> 2.43.0
>
>
On Tue, Jan 16, 2024 at 11:04:12AM +0200, Amir Goldstein wrote:
>On Tue, Jan 16, 2024 at 1:46 AM Sasha Levin <[email protected]> wrote:
>>
>> From: Miklos Szeredi <[email protected]>
>>
>> [ Upstream commit 98d2b43081972abeb5bb5a087bc3e3197531c46e ]
>>
>> If a mount is released then its mnt_id can immediately be reused. This is
>> bad news for user interfaces that want to uniquely identify a mount.
>>
>
>Sasha,
>
>This is a new API, not a bug fix.
>Maybe AUTOSEL was triggered by the words "This is bad news for user...."?
>
>You have also selected this to other 6.*.y kernels.
Ack, I'll drop it from everywhere. Thanks!
--
Thanks,
Sasha