linux/Documentation/core-api/kernel-api.rst
Luis Chamberlain df3e764d8e module: add debug stats to help identify memory pressure
Loading modules with finit_module() can end up using vmalloc(), vmap()
and vmalloc() again, for a total of up to 3 separate allocations in the
worst case for a single module. We always kernel_read*() the module,
that's a vmalloc(). Then vmap() is used for the module decompression,
and if so the last read buffer is freed as we use the now decompressed
module buffer to stuff data into our copy module. The last allocation is
specific to each architectures but pretty much that's generally a series
of vmalloc() calls or a variation of vmalloc to handle ELF sections with
special permissions.

Evaluation with new stress-ng module support [1] with just 100 ops
is proving that you can end up using GiBs of data easily even with all
care we have in the kernel and userspace today in trying to not load modules
which are already loaded. 100 ops seems to resemble the sort of pressure a
system with about 400 CPUs can create on module loading. Although issues
relating to duplicate module requests due to each CPU inucurring a new
module reuest is silly and some of these are being fixed, we currently lack
proper tooling to help diagnose easily what happened, when it happened
and who likely is to blame -- userspace or kernel module autoloading.

Provide an initial set of stats which use debugfs to let us easily scrape
post-boot information about failed loads. This sort of information can
be used on production worklaods to try to optimize *avoiding* redundant
memory pressure using finit_module().

There's a few examples that can be provided:

A 255 vCPU system without the next patch in this series applied:

Startup finished in 19.143s (kernel) + 7.078s (userspace) = 26.221s
graphical.target reached after 6.988s in userspace

And 13.58 GiB of virtual memory space lost due to failed module loading:

root@big ~ # cat /sys/kernel/debug/modules/stats
         Mods ever loaded       67
     Mods failed on kread       0
Mods failed on decompress       0
  Mods failed on becoming       0
      Mods failed on load       1411
        Total module size       11464704
      Total mod text size       4194304
       Failed kread bytes       0
  Failed decompress bytes       0
    Failed becoming bytes       0
        Failed kmod bytes       14588526272
 Virtual mem wasted bytes       14588526272
         Average mod size       171115
    Average mod text size       62602
  Average fail load bytes       10339140
Duplicate failed modules:
              module-name        How-many-times                    Reason
                kvm_intel                   249                      Load
                      kvm                   249                      Load
                irqbypass                     8                      Load
         crct10dif_pclmul                   128                      Load
      ghash_clmulni_intel                    27                      Load
             sha512_ssse3                    50                      Load
           sha512_generic                   200                      Load
              aesni_intel                   249                      Load
              crypto_simd                    41                      Load
                   cryptd                   131                      Load
                    evdev                     2                      Load
                serio_raw                     1                      Load
               virtio_pci                     3                      Load
                     nvme                     3                      Load
                nvme_core                     3                      Load
    virtio_pci_legacy_dev                     3                      Load
    virtio_pci_modern_dev                     3                      Load
                   t10_pi                     3                      Load
                   virtio                     3                      Load
             crc32_pclmul                     6                      Load
           crc64_rocksoft                     3                      Load
             crc32c_intel                    40                      Load
              virtio_ring                     3                      Load
                    crc64                     3                      Load

The following screen shot, of a simple 8vcpu 8 GiB KVM guest with the
next patch in this series applied, shows 226.53 MiB are wasted in virtual
memory allocations which due to duplicate module requests during boot.
It also shows an average module memory size of 167.10 KiB and an an
average module .text + .init.text size of 61.13 KiB. The end shows all
modules which were detected as duplicate requests and whether or not
they failed early after just the first kernel_read*() call or late after
we've already allocated the private space for the module in
layout_and_allocate(). A system with module decompression would reveal
more wasted virtual memory space.

We should put effort now into identifying the source of these duplicate
module requests and trimming these down as much possible. Larger systems
will obviously show much more wasted virtual memory allocations.

root@kmod ~ # cat /sys/kernel/debug/modules/stats
         Mods ever loaded       67
     Mods failed on kread       0
Mods failed on decompress       0
  Mods failed on becoming       83
      Mods failed on load       16
        Total module size       11464704
      Total mod text size       4194304
       Failed kread bytes       0
  Failed decompress bytes       0
    Failed becoming bytes       228959096
        Failed kmod bytes       8578080
 Virtual mem wasted bytes       237537176
         Average mod size       171115
    Average mod text size       62602
  Avg fail becoming bytes       2758544
  Average fail load bytes       536130
Duplicate failed modules:
              module-name        How-many-times                    Reason
                kvm_intel                     7                  Becoming
                      kvm                     7                  Becoming
                irqbypass                     6           Becoming & Load
         crct10dif_pclmul                     7           Becoming & Load
      ghash_clmulni_intel                     7           Becoming & Load
             sha512_ssse3                     6           Becoming & Load
           sha512_generic                     7           Becoming & Load
              aesni_intel                     7                  Becoming
              crypto_simd                     7           Becoming & Load
                   cryptd                     3           Becoming & Load
                    evdev                     1                  Becoming
                serio_raw                     1                  Becoming
                     nvme                     3                  Becoming
                nvme_core                     3                  Becoming
                   t10_pi                     3                  Becoming
               virtio_pci                     3                  Becoming
             crc32_pclmul                     6           Becoming & Load
           crc64_rocksoft                     3                  Becoming
             crc32c_intel                     3                  Becoming
    virtio_pci_modern_dev                     2                  Becoming
    virtio_pci_legacy_dev                     1                  Becoming
                    crc64                     2                  Becoming
                   virtio                     2                  Becoming
              virtio_ring                     2                  Becoming

[0] https://github.com/ColinIanKing/stress-ng.git
[1] echo 0 > /proc/sys/vm/oom_dump_tasks
    ./stress-ng --module 100 --module-name xfs

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
2023-04-18 11:15:24 -07:00

415 lines
8.6 KiB
ReStructuredText

====================
The Linux Kernel API
====================
List Management Functions
=========================
.. kernel-doc:: include/linux/list.h
:internal:
Basic C Library Functions
=========================
When writing drivers, you cannot in general use routines which are from
the C Library. Some of the functions have been found generally useful
and they are listed below. The behaviour of these functions may vary
slightly from those defined by ANSI, and these deviations are noted in
the text.
String Conversions
------------------
.. kernel-doc:: lib/vsprintf.c
:export:
.. kernel-doc:: include/linux/kstrtox.h
:functions: kstrtol kstrtoul
.. kernel-doc:: lib/kstrtox.c
:export:
.. kernel-doc:: lib/string_helpers.c
:export:
String Manipulation
-------------------
.. kernel-doc:: include/linux/fortify-string.h
:internal:
.. kernel-doc:: lib/string.c
:export:
.. kernel-doc:: include/linux/string.h
:internal:
.. kernel-doc:: mm/util.c
:functions: kstrdup kstrdup_const kstrndup kmemdup kmemdup_nul memdup_user
vmemdup_user strndup_user memdup_user_nul
Basic Kernel Library Functions
==============================
The Linux kernel provides more basic utility functions.
Bit Operations
--------------
.. kernel-doc:: include/asm-generic/bitops/instrumented-atomic.h
:internal:
.. kernel-doc:: include/asm-generic/bitops/instrumented-non-atomic.h
:internal:
.. kernel-doc:: include/asm-generic/bitops/instrumented-lock.h
:internal:
Bitmap Operations
-----------------
.. kernel-doc:: lib/bitmap.c
:doc: bitmap introduction
.. kernel-doc:: include/linux/bitmap.h
:doc: declare bitmap
.. kernel-doc:: include/linux/bitmap.h
:doc: bitmap overview
.. kernel-doc:: include/linux/bitmap.h
:doc: bitmap bitops
.. kernel-doc:: lib/bitmap.c
:export:
.. kernel-doc:: lib/bitmap.c
:internal:
.. kernel-doc:: include/linux/bitmap.h
:internal:
Command-line Parsing
--------------------
.. kernel-doc:: lib/cmdline.c
:export:
Sorting
-------
.. kernel-doc:: lib/sort.c
:export:
.. kernel-doc:: lib/list_sort.c
:export:
Text Searching
--------------
.. kernel-doc:: lib/textsearch.c
:doc: ts_intro
.. kernel-doc:: lib/textsearch.c
:export:
.. kernel-doc:: include/linux/textsearch.h
:functions: textsearch_find textsearch_next \
textsearch_get_pattern textsearch_get_pattern_len
CRC and Math Functions in Linux
===============================
Arithmetic Overflow Checking
----------------------------
.. kernel-doc:: include/linux/overflow.h
:internal:
CRC Functions
-------------
.. kernel-doc:: lib/crc4.c
:export:
.. kernel-doc:: lib/crc7.c
:export:
.. kernel-doc:: lib/crc8.c
:export:
.. kernel-doc:: lib/crc16.c
:export:
.. kernel-doc:: lib/crc32.c
.. kernel-doc:: lib/crc-ccitt.c
:export:
.. kernel-doc:: lib/crc-itu-t.c
:export:
Base 2 log and power Functions
------------------------------
.. kernel-doc:: include/linux/log2.h
:internal:
Integer power Functions
-----------------------
.. kernel-doc:: lib/math/int_pow.c
:export:
.. kernel-doc:: lib/math/int_sqrt.c
:export:
Division Functions
------------------
.. kernel-doc:: include/asm-generic/div64.h
:functions: do_div
.. kernel-doc:: include/linux/math64.h
:internal:
.. kernel-doc:: lib/math/gcd.c
:export:
UUID/GUID
---------
.. kernel-doc:: lib/uuid.c
:export:
Kernel IPC facilities
=====================
IPC utilities
-------------
.. kernel-doc:: ipc/util.c
:internal:
FIFO Buffer
===========
kfifo interface
---------------
.. kernel-doc:: include/linux/kfifo.h
:internal:
relay interface support
=======================
Relay interface support is designed to provide an efficient mechanism
for tools and facilities to relay large amounts of data from kernel
space to user space.
relay interface
---------------
.. kernel-doc:: kernel/relay.c
:export:
.. kernel-doc:: kernel/relay.c
:internal:
Module Support
==============
Kernel module auto-loading
--------------------------
.. kernel-doc:: kernel/module/kmod.c
:export:
Module debugging
----------------
.. kernel-doc:: kernel/module/stats.c
:doc: module debugging statistics overview
dup_failed_modules - tracks duplicate failed modules
****************************************************
.. kernel-doc:: kernel/module/stats.c
:doc: dup_failed_modules - tracks duplicate failed modules
module statistics debugfs counters
**********************************
.. kernel-doc:: kernel/module/stats.c
:doc: module statistics debugfs counters
Inter Module support
--------------------
Refer to the files in kernel/module/ for more information.
Hardware Interfaces
===================
DMA Channels
------------
.. kernel-doc:: kernel/dma.c
:export:
Resources Management
--------------------
.. kernel-doc:: kernel/resource.c
:internal:
.. kernel-doc:: kernel/resource.c
:export:
MTRR Handling
-------------
.. kernel-doc:: arch/x86/kernel/cpu/mtrr/mtrr.c
:export:
Security Framework
==================
.. kernel-doc:: security/security.c
:internal:
.. kernel-doc:: security/inode.c
:export:
Audit Interfaces
================
.. kernel-doc:: kernel/audit.c
:export:
.. kernel-doc:: kernel/auditsc.c
:internal:
.. kernel-doc:: kernel/auditfilter.c
:internal:
Accounting Framework
====================
.. kernel-doc:: kernel/acct.c
:internal:
Block Devices
=============
.. kernel-doc:: include/linux/bio.h
.. kernel-doc:: block/blk-core.c
:export:
.. kernel-doc:: block/blk-core.c
:internal:
.. kernel-doc:: block/blk-map.c
:export:
.. kernel-doc:: block/blk-sysfs.c
:internal:
.. kernel-doc:: block/blk-settings.c
:export:
.. kernel-doc:: block/blk-flush.c
:export:
.. kernel-doc:: block/blk-lib.c
:export:
.. kernel-doc:: block/blk-integrity.c
:export:
.. kernel-doc:: kernel/trace/blktrace.c
:internal:
.. kernel-doc:: block/genhd.c
:internal:
.. kernel-doc:: block/genhd.c
:export:
.. kernel-doc:: block/bdev.c
:export:
Char devices
============
.. kernel-doc:: fs/char_dev.c
:export:
Clock Framework
===============
The clock framework defines programming interfaces to support software
management of the system clock tree. This framework is widely used with
System-On-Chip (SOC) platforms to support power management and various
devices which may need custom clock rates. Note that these "clocks"
don't relate to timekeeping or real time clocks (RTCs), each of which
have separate frameworks. These :c:type:`struct clk <clk>`
instances may be used to manage for example a 96 MHz signal that is used
to shift bits into and out of peripherals or busses, or otherwise
trigger synchronous state machine transitions in system hardware.
Power management is supported by explicit software clock gating: unused
clocks are disabled, so the system doesn't waste power changing the
state of transistors that aren't in active use. On some systems this may
be backed by hardware clock gating, where clocks are gated without being
disabled in software. Sections of chips that are powered but not clocked
may be able to retain their last state. This low power state is often
called a *retention mode*. This mode still incurs leakage currents,
especially with finer circuit geometries, but for CMOS circuits power is
mostly used by clocked state changes.
Power-aware drivers only enable their clocks when the device they manage
is in active use. Also, system sleep states often differ according to
which clock domains are active: while a "standby" state may allow wakeup
from several active domains, a "mem" (suspend-to-RAM) state may require
a more wholesale shutdown of clocks derived from higher speed PLLs and
oscillators, limiting the number of possible wakeup event sources. A
driver's suspend method may need to be aware of system-specific clock
constraints on the target sleep state.
Some platforms support programmable clock generators. These can be used
by external chips of various kinds, such as other CPUs, multimedia
codecs, and devices with strict requirements for interface clocking.
.. kernel-doc:: include/linux/clk.h
:internal:
Synchronization Primitives
==========================
Read-Copy Update (RCU)
----------------------
.. kernel-doc:: include/linux/rcupdate.h
.. kernel-doc:: kernel/rcu/tree.c
.. kernel-doc:: kernel/rcu/tree_exp.h
.. kernel-doc:: kernel/rcu/update.c
.. kernel-doc:: include/linux/srcu.h
.. kernel-doc:: kernel/rcu/srcutree.c
.. kernel-doc:: include/linux/rculist_bl.h
.. kernel-doc:: include/linux/rculist.h
.. kernel-doc:: include/linux/rculist_nulls.h
.. kernel-doc:: include/linux/rcu_sync.h
.. kernel-doc:: kernel/rcu/sync.c