gh0s7/mckernel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,802 Commits 1 Branch 61 Tags
91d732308d2aa2b89b3ab490195eb79dd1e12a8f
Commit Graph

27 Commits

Author SHA1 Message Date
Balazs Gerofi
5a2f8388a6 HFI1: handle Linux queued_spin_locks in the receive path as well 2018-06-13 00:31:42 +09:00
Balazs Gerofi
8164b63fc2 HFI1: port to IFS 10.7 rpv1 and support queued_spin_lock in Linux 3.10.0-693.11.6 2018-06-13 00:31:42 +09:00
Balazs Gerofi
22992780cf HFI1: use kmalloc_cache_free() in clear_tid_node() for TID nodes 2018-06-13 00:31:42 +09:00
Balazs Gerofi
3043591e9a hfi1_user_exp_rcv_overlapping(): fix return value when overlapping 2018-06-13 00:31:42 +09:00
Balazs Gerofi
7193f165cc HFI1: fix page border iteration bug in hfi1_user_exp_rcv_setup() 2018-06-13 00:31:42 +09:00
Balazs Gerofi
fcc8310454 HFI1: track receive TIDs in a tree 2018-06-13 00:31:40 +09:00
Balazs Gerofi
e2e773d883 HFI: fix tidinfo and length calculation in program_rcvarray() 2018-06-13 00:31:39 +09:00
Balazs Gerofi
5bea237581 HFI1: make kmalloc caches per-CPU and pre-allocate at boot time 2018-06-13 00:31:39 +09:00
Balazs Gerofi
6848c2ecf7 HFI1: move tid_rb_node to header 2018-06-13 00:31:39 +09:00
Balazs Gerofi
2900ce20f7 HFI1: hfi1_unmap_device_addresses() at process terminate time 2018-06-13 00:31:39 +09:00
Balazs Gerofi
7a1ad31183 HFI: call hfi1_map_device_addresses() at initialization time 
Conflicts:
	kernel/syscall.c
 2018-06-13 00:31:38 +09:00
Balazs Gerofi
a5aa68744f hfi1: use kmalloc_cache for tid_rb_node allocations 2018-06-13 00:31:38 +09:00
Balazs Gerofi
89c5aaa9e9 hfi1_user_exp_rcv_setup(): rewrite main loop 2018-06-13 00:31:37 +09:00
Dominique Martinet
de82cf8779 hfi1/user_exp_rcv/setup: keep track of position within page 
ihk_mc_pt_lookup_pte + pte_get_phys will get us the physical address
for the start of the page we're looking at.
Re-offset it by position within buffer.
 2018-06-13 00:31:37 +09:00
Dominique Martinet
662895c020 hfi1/user_exp_rcv: explicitely call hfi1_map_device_addresses 
There were cases where nobody else did this mapping for us
 2018-06-13 00:31:37 +09:00
Dominique Martinet
ce4eb0d409 hfi1/user_exp_rcv/setup: add access_ok check 2018-06-13 00:31:36 +09:00
Dominique Martinet
04434320fc hfi1/user_exp_rcv/setup: do not skip over pages 
If the vaddr we consider is not at the start of a page, we could skip
over (smaller, not contigous) areas.

For example consider this segment of virtual memory:
[ 2MB | 4k | 4k | ... ]
Starting at 1MB offset, we would get a pgsize of 2MB so would skip
straight over 1MB worth of 4k pages.
 2018-06-13 00:31:36 +09:00
Dominique Martinet
50fafa6d71 hfi1/user_exp_rcv/setup: use cache_alloc for tidlist 2018-06-13 00:31:36 +09:00
Dominique Martinet
f5ced648ef hfi1/user_exp_rcv: rework main loop 
New loop now takes into account pages not physically contiguous.
Also some minor improvements, e.g. make the spin_lock used more locally,
reuse a group we had if we had one, etc.
 2018-06-13 00:31:36 +09:00
Dominique Martinet
0f8f88ca46 hfi1/user_exp_rcv/invalid: Remove function 
user_exp_rcv_invalid is only used together with the mmu cache
(its purpose is the delayed freeing of tids that were invalidated in cache)

Since we do not use that cache, the function can go
 2018-06-13 00:31:36 +09:00
Dominique Martinet
e99f19e812 hfi1/user_exp_rcv/setup: set length in tidinfo 
This was dropped early on by mistake/excessive haste, it's actually
pretty useful.
 2018-06-13 00:31:36 +09:00
Dominique Martinet
9a36e5d213 hfi1/user_exp_rcv/setup: increment phys appropriately 
Old code was always registering the same section with different size,
instead of properly covering the requested map
 2018-06-13 00:31:36 +09:00
Dominique Martinet
4816f27639 hfi1/user_exp_rcv/setup: split into multiple tids 
Do not round up to next power of two, but issue multiple requests
if necessary (e.g. 260k would be 256 + 4k in two registrations)
 2018-06-13 00:31:36 +09:00
Dominique Martinet
23f178d718 hfi1/user_exp_rcv/clear: implement TID_FREE ioctl 2018-06-13 00:31:36 +09:00
Dominique Martinet
1847a3ac11 hfi1/user_exp_rcv/setup: cleanup locks/groups usage 2018-06-13 00:31:35 +09:00
Dominique Martinet
15b16ffbbb hfi1/user_exp_rcv/setup: map is noop, skip it 
In the original driver's dma.c hfi1_dma_map_single just passes
the physical address back, so directly use that.
 2018-06-13 00:31:35 +09:00
Dominique Martinet
e64d89cd48 hfi: bases for user_exp_rcv 
This implements a skeleton setup function and call it on ioctl

Many missing points:
 - missing pci mapping to make setup work
 - no clear (passed to linux, so will likely bug out)
 - missing locks/safe-guards

Conflicts:
	kernel/Makefile.build.in
 2018-06-13 00:31:35 +09:00