Commit Graph

516 Commits

Author SHA1 Message Date
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
Ville Juven
39a567db20 mm/circbuf.c: Fix incorrect usage of void* arithmetics 2022-11-23 23:22:06 +08:00
wangbowen6
f7dec2c250 mm_size2ndx: using flsl to calculate the ndx
Signed-off-by: wangbowen6 <wangbowen6@xiaomi.com>
2022-11-23 13:19:41 +08:00
Ville Juven
48b9a8d6f4 mm/shm: Move the vma allocators to separate functions
This will allow changing the underlying backend, i.e. granule allocator,
to something more efficient, if this is needed later.

Also, it gives easier access to the common SHM book keeping.
2022-11-22 08:54:34 +01:00
Ville Juven
458ff380e5 mm/gran: Allow run-time execution of gran_reserve
User can ask for specific granules to be allocated.

This is useful for one thing only: when mmap() is called for a specific
vaddr. The parameter itself is non-sensical, this is just to satisfy
the POSIX standard.
2022-11-22 08:54:34 +01:00
qinwei1
8021dfece6 sched/task/task_getpid: getpid should return process id not thread id
Summary:
   implement the right semantics:
1. getpid should return the main thread id
2. gettid should return the current thread id

Refer to:
 https://github.com/apache/incubator-nuttx/issues/2499
 https://github.com/apache/incubator-nuttx/pull/2518

Signed-off-by: qinwei1 <qinwei1@xiaomi.com>
2022-11-17 17:58:08 +08:00
Ville Juven
192a639f8f mm/shm: Fix several build errors with shm due to missing headers 2022-11-17 09:16:54 +08:00
Xiang Xiao
33dabe3c38 sim: Always enable full UBSan feature to catch more error
since the resource is plenty on simulator

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-08 10:18:27 -03:00
Xiang Xiao
d6b5a345a4 mm: Let MM_SMALL and MM_REGIONS depend on MM_DEFAULT_MANAGER
since these options are coupled with the default heap implementation

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-08 10:18:27 -03:00
Xiang Xiao
38d1244751 mm/mempool: Remove MM_MEMPOOL option from Kconfig
since the linker can remove the unused object file from the final image

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-08 10:18:27 -03:00
Xiang Xiao
a446b5816f mm/circbuf: Remove MM_CIRCBUF option from Kconfig
since the linker can remove the unused object file from the final image

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-08 10:18:27 -03:00
Xiang Xiao
7dcf35cf64 mm: Remove the unused macro MM_IS_ALLOCATED
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-08 14:57:48 +09:00
Xiang Xiao
85b4177913 mm: Remove mm_ prefix from mm_[add|free]_delaylist
follow the convention of other static mm functions

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-07 10:01:52 +01:00
Xiang Xiao
b567e09c3c mm: Restore the return type of mm_lock from bool to int
Fix the issue reported here better:
https://github.com/apache/incubator-nuttx/pull/6995

Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-11-07 10:01:52 +01:00
Xiang Xiao
4cc13c19c6 Revert "mm: Check the function result with suitable macro."
This reverts commit 460d94729a.
2022-11-07 10:01:52 +01:00
yinshengkai
85f727f232 tools: replace INCDIR to Makefile variable
In the past, header file paths were generated by the incdir command
Now they are generated by concatenating environment variables

In this way, when executing makefile, no shell command will be executed,
it will improve the speed of executing makfile
Signed-off-by: yinshengkai <yinshengkai@xiaomi.com>
2022-11-03 19:59:55 +08:00
yinshengkai
95d9abcf58 tools: replace DEFINE script to Makefile variable
In the past, predefined macros were generated by define.sh scripts
Now they are generated by concatenating environment variables

In this way, when executing makefile, no shell command will be executed,
it will improve the speed of executing makfile

Signed-off-by: yinshengkai <yinshengkai@xiaomi.com>
2022-11-03 19:59:55 +08:00
ligd
8be4bca3eb kasan: fix kasan race-condition
Change-Id: I1c729b8a85422a1f4326785e5d52cb0fc60d4822
Signed-off-by: ligd <liguiding1@xiaomi.com>
2022-11-03 08:58:16 +08:00
wangbowen6
fccda0c08b mm_heap: add debug assert to check the alignment problem
Signed-off-by: wangbowen6 <wangbowen6@xiaomi.com>
Signed-off-by: YAMAMOTO Takashi <yamamoto@midokura.com>
2022-11-01 19:21:01 +08:00
Xiang Xiao
e08c296a8e Change the type of tg_joinlock, mm_lock and md_lock from sem_t to mutex_t
Signed-off-by: Xiang Xiao <xiaoxiang@xiaomi.com>
2022-10-31 10:35:53 +01:00
yinshengkai
65dc1fe0fc mm: add kmm/umm_memdump
Signed-off-by: yinshengkai <yinshengkai@xiaomi.com>
2022-10-29 11:35:27 +08:00
dongjiuzhu1
579e47347e mm/mm_heap: define MM_MASK_BIT as significant bits mask
using MM_MASK_BIT to expand different bits of preceding field to store the
block status.

Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
2022-10-29 00:12:02 +08:00
dongjiuzhu1
5982cafbe0 mm/mm_heap: using LOG2_CEIL to generate MM_MIN_SHIFT at compile time
Signed-off-by: dongjiuzhu1 <dongjiuzhu1@xiaomi.com>
2022-10-29 00:12:02 +08:00