sergiotarxz/nuttx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
47,908 Commits 1 Branch 0 Tags 291 MiB
b362f18d6a
Commit Graph

538 Commits

Author SHA1 Message Date
anjiahao
b362f18d6a mempool:Calibration total memory statistics 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 09:02:33 +01:00
anjiahao
d846004533 mempool:use two-dimensional array avoid competition 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 09:02:33 +01:00
anjiahao
288725a5f8 mempool:fix a bug when use smp on mempool backtrace 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 09:02:33 +01:00
anjiahao
632ed0d3a4 Optimize multipe mempool memory space usage 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 14:12:45 +08:00
anjiahao
6b530fceae mempool:change mempool_multiple way of initialization 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 14:12:45 +08:00
anjiahao
49ffd99eaf mempool:use single queue insdie of list 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-18 14:12:45 +08:00
anjiahao
e7d02ffac2 mempool:remove multiple fixed api 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 14:12:45 +08:00
anjiahao
f00d56337f mempool:remove unnecessary alignment 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-18 14:12:45 +08:00
anjiahao
bc30b294aa mm:add heap args to mm_malloc_size 
use malloc_size inside of where used mm_malloc_size

Signed-off-by: anjiahao <anjiahao@xiaomi.com>
Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-17 21:57:37 +08:00
Xiang Xiao
154bb93c45 mm: Terminate the backtrace array with one NULL pointer 
since one entry is enough to identify the end of back trace

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
 2023-01-17 16:48:30 +08:00
anjiahao
29404ef54e procmeminfo:support memdump can show specific task for tlsf 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-17 16:48:30 +08:00
dongjiuzhu1
c386a1a2d9 mm/mempool: support backtrace function for mempool 
Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-17 16:48:30 +08:00
anjiahao
af3978c1fa adjust the contents of memdump and meminfo 
memdump:just dump info
meminfo:statistics mem information

Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-17 16:48:30 +08:00
Gustavo Henrique Nihei
a3e253b4a3 mm: Enable a dedicated kernel heap on BUILD_FLAT via MM_KERNEL_HEAP 
Signed-off-by: Gustavo Henrique Nihei <gustavo.nihei@espressif.com>
 2023-01-17 10:30:00 +08:00
anjiahao
cb404167a7 mm/tlsf:add mempool to optimize small block perfomance 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-16 20:32:17 +08:00
anjiahao
bdcb1f6a25 fix:mmsize_t need support 64bit 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-16 20:32:17 +08:00
dongjiuzhu1
c82f44c4f3 mm/mm_heap: add mempool to optimize small block performance 
There are many small memory block in NuttX system, eg: struct tcb_s,
struct inode, etc, and several disadvantages about them:
1.Their frequent allocate and free cause the system memory fragmentation.
2.Since each memory block has an overhead, the utilization of small memory
blocks is relatively low, which will cause memory waste.

So we can use mempool to alloc smallo block, to improve alloc speed
and utilization, to reduce fragmentation.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-16 20:32:17 +08:00
dongjiuzhu1
7cd325f3be mm/mm_heap: remove kasan in MM_ADD_BACKTRACE 
do simple copy to instead of memset and memcpy operation because
they have been instrumented, if you access the posion area,
the system will crash.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-16 20:32:17 +08:00
chao an
613bfd0fde mm/tlsf: fix compile error/warning on tlsf 
1.
make[1]: Entering directory '/home/archer/code/nuttx/n2/incubator-nuttx/mm'
/bin/sh: 1: Syntax error: "(" unexpected

2.
tools/Unix.mk:681: warning: overriding recipe for target 'mm_clean'
tools/Unix.mk:681: warning: ignoring old recipe for target 'mm_clean'
tools/Unix.mk:700: warning: overriding recipe for target 'mm_distclean'
tools/Unix.mk:700: warning: ignoring old recipe for target 'mm_distclean'

Signed-off-by: chao an <anchao@xiaomi.com>
 2023-01-16 16:14:13 +08:00
dongjiuzhu1
5c0a5a6627 mm/mempool: support memalign about mempool and mulitple mempool 
The memalign is special to multiple mempool because multiple mempool
doesn't support split and shrink chunk operate. So When you alloc a
memory block and find an aligned address in this block, you need to
occupy 8 bytes before the address to save the address of the padding
size and pool to ensure correct use in realloc and free operations.
So we will use bit1 in the previous address of the address to represent
that it is applied by memalign.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-15 20:05:55 +08:00
dongjiuzhu1
f5ee767c46 mm/mempool: fix crash about mempool_multiple_realloc 
kasan_report (addr=0xf3c68618, size=1, is_write=false) at
kasan/kasan.c:106
0x56585fbf in __asan_loadN_noabort (addr=0xf3c68618, size=1) at
kasan/kasan.c:300
0x565860ac in __asan_load1_noabort (addr=0xf3c68618) at
kasan/kasan.c:354
0x565843af in memcpy (dest=0xf3de9d6c, src=0xf3c685cc, n=3) at
string/lib_memcpy.c:44
0x56587ae8 in mempool_multiple_realloc (mpool=0xf3c670fc,
oldblk=0xf3c685cc, size=416) at mempool/mempool_multiple.c:218
0x5658707a in mm_realloc (heap=0xf3c67000, oldmem=0xf3c685cc,
size=416) at mm_heap/mm_realloc.c:98
0x5658524e in realloc (oldmem=0xf3c685cc, size=416) at
umm_heap/umm_realloc.c:97

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-15 20:05:55 +08:00
dongjiuzhu1
e5394be881 mempool/multiple_mempool: add private member delta in multiple-mempool 
This delta describes the relationship between the block size of each
mempool in multiple mempool by user initialized. It is automatically
detected by the mempool_multiple_init function. If the delta is not
equal to 0, the block size of the pool in the multiple mempool is an
arithmetic progressions, otherwise it is an increasing progressions.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-15 20:05:55 +08:00
dongjiuzhu1
cd97134c7c mm/mempool: update nexpand/ninitial/ninterrupt to xxxsize 
Let's specify size instead of number, so that we can unify the size of
expansion memory in the multiple mempool.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-15 20:05:55 +08:00
dongjiuzhu1
adaca6a5ce mm/mempool: using inline list instead of queue to avoid kasan report 
the crash backtrace:
kasan_report (addr=0xf3d02fd4, size=4, is_write=false) at
kasan/kasan.c:106
0x5658518d in __asan_loadN_noabort (addr=0xf3d02fd4, size=4) at
kasan/kasan.c:300
0x565851ee in __asan_load4_noabort (addr=0xf3d02fd4) at
kasan/kasan.c:334
0x56580b02 in sq_remfirst (queue=0xf3d02b08) at
queue/sq_remfirst.c:45
0x565e0e0b in mempool_alloc (pool=0xf3d02aec) at
mempool/mempool.c:161
0x566033d2 in mempool_multiple_alloc (mpool=0xf3d02a30, size=16) at
mempool/mempool_multiple.c:147

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
 2023-01-15 20:05:55 +08:00
Xiang Xiao
a6428f4c27 mm: Integrate TLSF manager 
can be enabled by CONFIG_MM_TLSF_MANAGER=y

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2023-01-15 03:43:37 +08:00
Jukka Laitinen
a2a10c87e3 mm/shm: Switch to use process' common virtual memory region allocator 
- Also remove the nuttx private shm.h file nuttx/mm/shm.h, which became redundant
- Also remove the gran allocator initialization/release in binfmt since common
  vpage allocator is initialized in group_create/group_leave

Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-13 02:20:13 +08:00
Jukka Laitinen
2236facca9 mm/map: Add a common virtual memory region allocator 
Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-13 02:20:13 +08:00
Jukka Laitinen
70de321de3 arch/Kconfig: remove virtual memory allocator dependency from MM_SHM 
The dependency should be vice versa; the MM_SHM should depend on the
existence of the virtual memory range allocator.

Create a new CONFIG flag CONFIG_ARCH_VMA_MAPPING, which will define that
there is a virtual memory range allocator. Make MM_SHM select that flag

Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-13 02:20:13 +08:00
Jukka Laitinen
3ea7a6fb77 mm/shm: Clean up the System-V shm driver 
Move shmdt functionality into shm_unmap, and use shm_unmap as the common
detach function.

Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-10 23:24:50 +08:00
Jukka Laitinen
5150979488 mm/shm: Remove gs_vaddr from task group and use dynamic vm_map instead 
Replace static gs_vaddr with a new dynamic mapping list. Collecting all
this kind of virtual memory mappings into a single structure makes
things more consistent.

This still leaves the task group specific granule alloocator, gs_handle,
in the task group

Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-10 18:34:25 +08:00
Jukka Laitinen
7f8bec7070 Add mm/mm_map virtual memory mapping list 
The task_group specific list can be used to store information about
mmappings.

For a driver or filesystem performing mmap can also enable munmap by
adding an item to this list using mm_map_add(). The item is then
returned in the corresponding munmap call.

Signed-off-by: Jukka Laitinen <jukkax@ssrc.tii.ae>
 2023-01-10 18:34:25 +08:00
Xiang Xiao
6214f3cde7 mm/heap: Fix the minor style issue 
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
 2023-01-08 01:25:18 +02:00
Xiang Xiao
54de894e52 mm/heap: Skip memset backtrace buffer 
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
 2023-01-08 01:25:18 +02:00
Xiang Xiao
70ecb4ef26 mm/heap: Changee mmchunk_handler_t to mm_node_handler_t 
to unify the term usage(chunk v.s. node and mm v.s. mm_)

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
 2023-01-08 01:25:18 +02:00
YAMAMOTO Takashi
bf7db14feb Suppress -Wsign-compare warning on a few places 2022-12-26 18:23:41 +08:00
anjiahao
f403118647 mm:fix typos 
./mm_heap/mm.h:86:27: error: expected '=', ',', ';', 'asm' or '__attribute__' before '*' token
   86 |          FAR strcut tcb_s *tcb; \
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2022-12-22 20:19:05 +08:00
chao an
e6b37f2b2d mm/iob: revert "modify iob to support header padding and alignment features" 
we don't need to implement l2 isolation through io_head, iob offload will use io_offset

-------------------------------------------------------------
Layout of different NICs implementation:

        iob_data (aligned by CONFIG_IOB_ALIGNMENT)
            |
            |                 io_offset(CONFIG_NET_LL_GUARDSIZE)
            |                                |
            -------------------------------------------------
 Ethernet   |       Reserved    | ETH_HDRLEN |    io_len    |
            ---------------------------------|---------------
 8021Q      |   Reserved  | ETH_8021Q_HDRLEN |    io_len    |
            ---------------------------------|---------------
 ipforward  |            Reserved            |    io_len    |
            -------------------------------------------------

--------------------------------------------------------------------

Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-21 01:43:02 +08:00
chao an
6e380c0978 mm/iob: add a helper function to get iob count in chain 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-21 01:40:24 +08:00
anjiahao
70791af8e2 procmeminfo:support memdump can show specific task 
Signed-off-by: anjiahao <anjiahao@xiaomi.com>
 2022-12-19 20:43:33 +08:00
chao an
4f239e145e Revert "mm/iob/contig: enhance iob contig to support iob chain" 
This reverts commit 56a4e90dc4.
 2022-12-19 01:32:05 +08:00
chao an
56a4e90dc4 mm/iob/contig: enhance iob contig to support iob chain 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-18 21:15:47 +08:00
chao an
881c9d9fac mm/iob: add support of partial bytes clone 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-14 21:37:20 +08:00
chao an
d6d56c3372 mm/iob: add support of nonblock iob_clone 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-14 21:37:20 +08:00
chao an
e2b00a9fcc mm/iob: reserved bytes should be updated after each iteration 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-07 21:24:25 +08:00
Xiang Xiao
800fac05d9 mm: Change the default of MM_UBSAN_TRAP_ON_ERROR to n 
let's give more information by default

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
 2022-12-06 19:01:25 +08:00
chao an
415fa25eb7 mm/ubsan: fix build warning 
ubsan/ubsan.c: In function ‘get_signed_val’:
ubsan/ubsan.c:162:22: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
  162 |       uint64_t ret = (uint64_t)val & mask;
      |

Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-05 14:06:27 +08:00
chao an
34d2cde8a8 net/l2/l3/l4: add support of iob offload 
1. Add new config CONFIG_NET_LL_GUARDSIZE to isolation of l2 stack,
   which will benefit l3(IP) layer for multi-MAC(l2) implementation,
   especially in some NICs such as celluler net driver.

new configuration options: CONFIG_NET_LL_GUARDSIZE

CONFIG_NET_LL_GUARDSIZE will reserved l2 buffer header size of
network buffer to isolate the L2/L3 (MAC/IP) data on network layer,
which will be beneficial to L3 network layer protocol transparent
transmission and forwarding

------------------------------------------------------------
Layout of frist iob entry:

        iob_data (aligned by CONFIG_IOB_ALIGNMENT)
            |
            |                  io_offset(CONFIG_NET_LL_GUARDSIZE)
            |                                |
            -------------------------------------------------
      iob   |            Reserved            |    io_len    |
            -------------------------------------------------

-------------------------------------------------------------
Layout of different NICs implementation:

        iob_data (aligned by CONFIG_IOB_ALIGNMENT)
            |
            |                 io_offset(CONFIG_NET_LL_GUARDSIZE)
            |                                |
            -------------------------------------------------
 Ethernet   |       Reserved    | ETH_HDRLEN |    io_len    |
            ---------------------------------|---------------
 8021Q      |   Reserved  | ETH_8021Q_HDRLEN |    io_len    |
            ---------------------------------|---------------
 ipforward  |            Reserved            |    io_len    |
            -------------------------------------------------

--------------------------------------------------------------------

2. Support iob offload to l2 driver to avoid unnecessary memory copy

Support send/receive iob vectors directly between the NICs and l3/l4
stack to avoid unnecessary memory copies, especially on hardware that
supports Scatter/gather, which can greatly improve performance.

new interface to support iob offload:

  ------------------------------------------
  |    IOB version     |     original      |
  |----------------------------------------|
  |  devif_iob_poll()  |   devif_poll()    |
  |       ...          |       ...         |
  ------------------------------------------

--------------------------------------------------------------------

1> NIC hardware support Scatter/gather transfer

TX:

                tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4)
                           /              \
                          /                \
devif_poll_[l3|l4]_connections()     devif_iob_send() (nocopy:udp/icmp/...)
           /                                   \      (copy:tcp)
          /                                     \
  devif_iob_poll("NIC"_txpoll)                callback() // "NIC"_txpoll
                                                  |
                            dev->d_iob:           |
                                                ---------------         ---------------
                             io_data       iob1 |  |          |    iob3 |  |          |
                                    \           ---------------         ---------------
                                  ---------------  |       --------------- |
                             iob0 |  |          |  |  iob2 |  |          | |
                                  ---------------  |       --------------- |
                                     \             |          /           /
                                        \          |       /           /
                                   ----------------------------------------------
                    NICs io vector |    |    |    |    |    |    |    |    |    |
                                   ----------------------------------------------

RX:

  [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead)
                    |
                    |
      [tcp|udp|icmp|...]_ipv[4|6]_in()/...
                    |
                    |
          pkt/ipv[4/6]_input()/...
                    |
                    |
     NICs io vector receive(iov_base to each iobs)

--------------------------------------------------------------------

2> CONFIG_IOB_BUFSIZE is greater than MTU:

TX:

"(CONFIG_IOB_BUFSIZE) > (MAX_NETDEV_PKTSIZE + CONFIG_NET_GUARDSIZE + CONFIG_NET_LL_GUARDSIZE)"

                tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4)
                           /              \
                          /                \
devif_poll_[l3|l4]_connections()     devif_iob_send() (nocopy:udp/icmp/...)
           /                                   \      (copy:tcp)
          /                                     \
  devif_iob_poll("NIC"_txpoll)                callback() // "NIC"_txpoll
                                                  |
                                             "NIC"_send()
                          (dev->d_iob->io_data[CONFIG_NET_LL_GUARDSIZE - NET_LL_HDRLEN(dev)])

RX:

  [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead)
                    |
                    |
      [tcp|udp|icmp|...]_ipv[4|6]_in()/...
                    |
                    |
          pkt/ipv[4/6]_input()/...
                    |
                    |
     NICs io vector receive(iov_base to io_data)

--------------------------------------------------------------------

3> Compatible with all old flat buffer NICs

TX:
                tcp_poll()/udp_poll()/pkt_poll()/...(l3|l4)
                           /              \
                          /                \
devif_poll_[l3|l4]_connections()     devif_iob_send() (nocopy:udp/icmp/...)
           /                                   \      (copy:tcp)
          /                                     \
  devif_iob_poll(devif_poll_callback())  devif_poll_callback() /* new interface, gather iobs to flat buffer */
       /                                           \
      /                                             \
 devif_poll("NIC"_txpoll)                     "NIC"_send()(dev->d_buf)

RX:

  [tcp|udp|icmp|...]ipv[4|6]_data_handler()(iob_concat/append to readahead)
                    |
                    |
      [tcp|udp|icmp|...]_ipv[4|6]_in()/...
                    |
                    |
               netdev_input()  /* new interface, Scatter/gather flat/iob buffer */
                    |
                    |
          pkt/ipv[4|6]_input()/...
                    |
                    |
    NICs io vector receive(Orignal flat buffer)

3. Iperf passthrough on NuttX simulator:

  -------------------------------------------------
  |  Protocol      | Server | Client |            |
  |-----------------------------------------------|
  |  TCP           |  813   |   834  |  Mbits/sec |
  |  TCP(Offload)  | 1720   |  1100  |  Mbits/sec |
  |  UDP           |   22   |   757  |  Mbits/sec |
  |  UDP(Offload)  |   25   |  1250  |  Mbits/sec |
  -------------------------------------------------

Signed-off-by: chao an <anchao@xiaomi.com>
 2022-12-03 11:47:04 +08:00
zouboan
eaea38e0f2 libc and mm/Makefile:Fix an error caused by backslash in Windows native build 
libc and mm/Makefile:Fix an error caused by backslash in Windows native build
 2022-12-01 01:47:46 +08:00
chao an
cdaa2ba8d4 mm/iob: new function iob_update_pktlen() to update packet length of the iob 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-11-29 13:16:23 +08:00
chao an
b452e2fddf mm/iob: new function iob_reserve() to adjust headroom offset 
Signed-off-by: chao an <anchao@xiaomi.com>
 2022-11-29 13:16:23 +08:00