[PATCH RFC] proc/meminfo: add KernelMisc counter

[PATCH RFC] proc/meminfo: add KernelMisc counter

[Konstantin Khlebnikov]

Some kernel memory allocations are not accounted anywhere.
This adds easy-read counter for them by subtracting all tracked kinds.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
---
 Documentation/filesystems/proc.txt |    2 ++
 fs/proc/meminfo.c                  |   41 +++++++++++++++++++++++++-----------
 2 files changed, 30 insertions(+), 13 deletions(-)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 66cad5c86171..f11ce167124c 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -891,6 +891,7 @@ VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
 Percpu:          62080 kB
+KernelMisc:     212856 kB
 HardwareCorrupted:   0 kB
 AnonHugePages:   49152 kB
 ShmemHugePages:      0 kB
@@ -988,6 +989,7 @@ VmallocTotal: total size of vmalloc memory area
 VmallocChunk: largest contiguous block of vmalloc area which is free
       Percpu: Memory allocated to the percpu allocator used to back percpu
               allocations. This stat excludes the cost of metadata.
+  KernelMisc: All other kinds of kernel memory allocaitons
 
 ..............................................................................
 
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 568d90e17c17..7bc14716fc5d 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -38,15 +38,21 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	long cached;
 	long available;
 	unsigned long pages[NR_LRU_LISTS];
-	unsigned long sreclaimable, sunreclaim;
+	unsigned long sreclaimable, sunreclaim, misc_reclaimable;
+	unsigned long kernel_stack_kb, page_tables, percpu_pages;
+	unsigned long anon_pages, file_pages, swap_cached;
+	long kernel_misc;
 	int lru;
 
 	si_meminfo(&i);
 	si_swapinfo(&i);
 	committed = percpu_counter_read_positive(&vm_committed_as);
 
-	cached = global_node_page_state(NR_FILE_PAGES) -
-			total_swapcache_pages() - i.bufferram;
+	anon_pages = global_node_page_state(NR_ANON_MAPPED);
+	file_pages = global_node_page_state(NR_FILE_PAGES);
+	swap_cached = total_swapcache_pages();
+
+	cached = file_pages - swap_cached - i.bufferram;
 	if (cached < 0)
 		cached = 0;
 
@@ -56,13 +62,25 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	available = si_mem_available();
 	sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
 	sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
+	misc_reclaimable = global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+	kernel_stack_kb = global_zone_page_state(NR_KERNEL_STACK_KB);
+	page_tables = global_zone_page_state(NR_PAGETABLE);
+	percpu_pages = pcpu_nr_pages();
+
+	/* all other kinds of kernel memory allocations */
+	kernel_misc = i.totalram - i.freeram - anon_pages - file_pages
+		      - sreclaimable - sunreclaim - misc_reclaimable
+		      - (kernel_stack_kb >> (PAGE_SHIFT - 10))
+		      - page_tables - percpu_pages;
+	if (kernel_misc < 0)
+		kernel_misc = 0;
 
 	show_val_kb(m, "MemTotal:       ", i.totalram);
 	show_val_kb(m, "MemFree:        ", i.freeram);
 	show_val_kb(m, "MemAvailable:   ", available);
 	show_val_kb(m, "Buffers:        ", i.bufferram);
 	show_val_kb(m, "Cached:         ", cached);
-	show_val_kb(m, "SwapCached:     ", total_swapcache_pages());
+	show_val_kb(m, "SwapCached:     ", swap_cached);
 	show_val_kb(m, "Active:         ", pages[LRU_ACTIVE_ANON] +
 					   pages[LRU_ACTIVE_FILE]);
 	show_val_kb(m, "Inactive:       ", pages[LRU_INACTIVE_ANON] +
@@ -92,20 +110,16 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		    global_node_page_state(NR_FILE_DIRTY));
 	show_val_kb(m, "Writeback:      ",
 		    global_node_page_state(NR_WRITEBACK));
-	show_val_kb(m, "AnonPages:      ",
-		    global_node_page_state(NR_ANON_MAPPED));
+	show_val_kb(m, "AnonPages:      ", anon_pages);
 	show_val_kb(m, "Mapped:         ",
 		    global_node_page_state(NR_FILE_MAPPED));
 	show_val_kb(m, "Shmem:          ", i.sharedram);
-	show_val_kb(m, "KReclaimable:   ", sreclaimable +
-		    global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
+	show_val_kb(m, "KReclaimable:   ", sreclaimable + misc_reclaimable);
 	show_val_kb(m, "Slab:           ", sreclaimable + sunreclaim);
 	show_val_kb(m, "SReclaimable:   ", sreclaimable);
 	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
-	seq_printf(m, "KernelStack:    %8lu kB\n",
-		   global_zone_page_state(NR_KERNEL_STACK_KB));
-	show_val_kb(m, "PageTables:     ",
-		    global_zone_page_state(NR_PAGETABLE));
+	seq_printf(m, "KernelStack:    %8lu kB\n", kernel_stack_kb);
+	show_val_kb(m, "PageTables:     ", page_tables);
 #ifdef CONFIG_QUICKLIST
 	show_val_kb(m, "Quicklists:     ", quicklist_total_size());
 #endif
@@ -122,7 +136,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		   (unsigned long)VMALLOC_TOTAL >> 10);
 	show_val_kb(m, "VmallocUsed:    ", 0ul);
 	show_val_kb(m, "VmallocChunk:   ", 0ul);
-	show_val_kb(m, "Percpu:         ", pcpu_nr_pages());
+	show_val_kb(m, "Percpu:         ", percpu_pages);
+	show_val_kb(m, "KernelMisc:     ", kernel_misc);
 
 #ifdef CONFIG_MEMORY_FAILURE
 	seq_printf(m, "HardwareCorrupted: %5lu kB\n",

Re: [PATCH RFC] proc/meminfo: add KernelMisc counter

[Roman Gushchin]

On Wed, May 15, 2019 at 02:49:48PM +0300, Konstantin Khlebnikov wrote:
> Some kernel memory allocations are not accounted anywhere.
> This adds easy-read counter for them by subtracting all tracked kinds.
> 
> Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>

We have something similar in userspace, and it was very useful several times.
In our case, it was mostly vmallocs and percpu stuff (which are now shown
in meminfo), but for sure there are other memory users who are not.

I don't particularly like the proposed name, but have no better ideas.
It's really a gray area, everything we know, it's that the memory is occupied
by something.

> ---
>  Documentation/filesystems/proc.txt |    2 ++
>  fs/proc/meminfo.c                  |   41 +++++++++++++++++++++++++-----------
>  2 files changed, 30 insertions(+), 13 deletions(-)
> 
> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
> index 66cad5c86171..f11ce167124c 100644
> --- a/Documentation/filesystems/proc.txt
> +++ b/Documentation/filesystems/proc.txt
> @@ -891,6 +891,7 @@ VmallocTotal:   112216 kB
>  VmallocUsed:       428 kB
>  VmallocChunk:   111088 kB
>  Percpu:          62080 kB
> +KernelMisc:     212856 kB
>  HardwareCorrupted:   0 kB
>  AnonHugePages:   49152 kB
>  ShmemHugePages:      0 kB
> @@ -988,6 +989,7 @@ VmallocTotal: total size of vmalloc memory area
>  VmallocChunk: largest contiguous block of vmalloc area which is free
>        Percpu: Memory allocated to the percpu allocator used to back percpu
>                allocations. This stat excludes the cost of metadata.
> +  KernelMisc: All other kinds of kernel memory allocaitons
                                                       ^^^
						       typo
>  
>  ..............................................................................
>  
> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
> index 568d90e17c17..7bc14716fc5d 100644
> --- a/fs/proc/meminfo.c
> +++ b/fs/proc/meminfo.c
> @@ -38,15 +38,21 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>  	long cached;
>  	long available;
>  	unsigned long pages[NR_LRU_LISTS];
> -	unsigned long sreclaimable, sunreclaim;
> +	unsigned long sreclaimable, sunreclaim, misc_reclaimable;
> +	unsigned long kernel_stack_kb, page_tables, percpu_pages;
> +	unsigned long anon_pages, file_pages, swap_cached;
> +	long kernel_misc;
>  	int lru;
>  
>  	si_meminfo(&i);
>  	si_swapinfo(&i);
>  	committed = percpu_counter_read_positive(&vm_committed_as);
>  
> -	cached = global_node_page_state(NR_FILE_PAGES) -
> -			total_swapcache_pages() - i.bufferram;
> +	anon_pages = global_node_page_state(NR_ANON_MAPPED);
> +	file_pages = global_node_page_state(NR_FILE_PAGES);
> +	swap_cached = total_swapcache_pages();
> +
> +	cached = file_pages - swap_cached - i.bufferram;
>  	if (cached < 0)
>  		cached = 0;
>  
> @@ -56,13 +62,25 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>  	available = si_mem_available();
>  	sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
>  	sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
> +	misc_reclaimable = global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
> +	kernel_stack_kb = global_zone_page_state(NR_KERNEL_STACK_KB);
> +	page_tables = global_zone_page_state(NR_PAGETABLE);
> +	percpu_pages = pcpu_nr_pages();
> +
> +	/* all other kinds of kernel memory allocations */
> +	kernel_misc = i.totalram - i.freeram - anon_pages - file_pages
> +		      - sreclaimable - sunreclaim - misc_reclaimable
> +		      - (kernel_stack_kb >> (PAGE_SHIFT - 10))
> +		      - page_tables - percpu_pages;
> +	if (kernel_misc < 0)
> +		kernel_misc = 0;

Hm, why? Is there any realistic scenario (not caused by the kernel doing
the memory accounting wrong) when it's negative?

Maybe it's better to show it as it is, if it's negative? Because
it might be a good indication that something's wrong with some of
the counters.

Thanks!

Re: [PATCH RFC] proc/meminfo: add KernelMisc counter

[Konstantin Khlebnikov]

On 16.05.2019 20:59, Roman Gushchin wrote:
> On Wed, May 15, 2019 at 02:49:48PM +0300, Konstantin Khlebnikov wrote:
>> Some kernel memory allocations are not accounted anywhere.
>> This adds easy-read counter for them by subtracting all tracked kinds.
>>
>> Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
> 
> We have something similar in userspace, and it was very useful several times.
> In our case, it was mostly vmallocs and percpu stuff (which are now shown
> in meminfo), but for sure there are other memory users who are not.
> 
> I don't particularly like the proposed name, but have no better ideas.
> It's really a gray area, everything we know, it's that the memory is occupied
> by something.
> 

Probably it's better to add overall 'MemKernel'.
Detailed analysis anyway requires special tools.

>> ---
>>   Documentation/filesystems/proc.txt |    2 ++
>>   fs/proc/meminfo.c                  |   41 +++++++++++++++++++++++++-----------
>>   2 files changed, 30 insertions(+), 13 deletions(-)
>>
>> diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
>> index 66cad5c86171..f11ce167124c 100644
>> --- a/Documentation/filesystems/proc.txt
>> +++ b/Documentation/filesystems/proc.txt
>> @@ -891,6 +891,7 @@ VmallocTotal:   112216 kB
>>   VmallocUsed:       428 kB
>>   VmallocChunk:   111088 kB
>>   Percpu:          62080 kB
>> +KernelMisc:     212856 kB
>>   HardwareCorrupted:   0 kB
>>   AnonHugePages:   49152 kB
>>   ShmemHugePages:      0 kB
>> @@ -988,6 +989,7 @@ VmallocTotal: total size of vmalloc memory area
>>   VmallocChunk: largest contiguous block of vmalloc area which is free
>>         Percpu: Memory allocated to the percpu allocator used to back percpu
>>                 allocations. This stat excludes the cost of metadata.
>> +  KernelMisc: All other kinds of kernel memory allocaitons
>                                                         ^^^
> 						       typo
>>   
>>   ..............................................................................
>>   
>> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
>> index 568d90e17c17..7bc14716fc5d 100644
>> --- a/fs/proc/meminfo.c
>> +++ b/fs/proc/meminfo.c
>> @@ -38,15 +38,21 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>>   	long cached;
>>   	long available;
>>   	unsigned long pages[NR_LRU_LISTS];
>> -	unsigned long sreclaimable, sunreclaim;
>> +	unsigned long sreclaimable, sunreclaim, misc_reclaimable;
>> +	unsigned long kernel_stack_kb, page_tables, percpu_pages;
>> +	unsigned long anon_pages, file_pages, swap_cached;
>> +	long kernel_misc;
>>   	int lru;
>>   
>>   	si_meminfo(&i);
>>   	si_swapinfo(&i);
>>   	committed = percpu_counter_read_positive(&vm_committed_as);
>>   
>> -	cached = global_node_page_state(NR_FILE_PAGES) -
>> -			total_swapcache_pages() - i.bufferram;
>> +	anon_pages = global_node_page_state(NR_ANON_MAPPED);
>> +	file_pages = global_node_page_state(NR_FILE_PAGES);
>> +	swap_cached = total_swapcache_pages();
>> +
>> +	cached = file_pages - swap_cached - i.bufferram;
>>   	if (cached < 0)
>>   		cached = 0;
>>   
>> @@ -56,13 +62,25 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
>>   	available = si_mem_available();
>>   	sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
>>   	sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
>> +	misc_reclaimable = global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
>> +	kernel_stack_kb = global_zone_page_state(NR_KERNEL_STACK_KB);
>> +	page_tables = global_zone_page_state(NR_PAGETABLE);
>> +	percpu_pages = pcpu_nr_pages();
>> +
>> +	/* all other kinds of kernel memory allocations */
>> +	kernel_misc = i.totalram - i.freeram - anon_pages - file_pages
>> +		      - sreclaimable - sunreclaim - misc_reclaimable
>> +		      - (kernel_stack_kb >> (PAGE_SHIFT - 10))
>> +		      - page_tables - percpu_pages;
>> +	if (kernel_misc < 0)
>> +		kernel_misc = 0;
> 
> Hm, why? Is there any realistic scenario (not caused by the kernel doing
> the memory accounting wrong) when it's negative?
> 
> Maybe it's better to show it as it is, if it's negative? Because
> it might be a good indication that something's wrong with some of
> the counters.

Such kind of sanitisation is a common practice for racy counters.
See 'cached' above.

> 
> Thanks!
>