PAGE_RW Should be added to PAGE_COPY ?
Quoted 10 lines
PAGE_COPY(without the write bit) is used when the area was mmap'edMAP_PRIVATE: which indeed is asking for private copies of pages to be made - which will be left containing the data written there by the application, rather than shared data received later by the driver.You want to mmap
MAP_SHARED, which will usePAGE_SHAREDinstead, including the write bit, both before and after the mprotects. There should be no problem then: do you actually see a problem whenMAP_SHAREDis used?
It's ok to mmap MAP_SHARED. But is it not a normal way to malloc() a space and then registered to NIC ?
Quoted 7 lines
(You don't mention which release you're describing, and some of the details may vary: the not-yet-started 2.6.19 is likely to use
PAGE_COPYeven whenMAP_SHARED, to help it keep track of the number of dirty pages; but in that case,do_wp_page()won't make a copy.)Quoted 1 line
Quoted 5 lines
Quoted 3 lines
The reson is that :
1) User-level network driver locks phy pages when memory space is registered;
2) 2 calls to mprotect change ptes in the space toPAGE_COPY, so write any page in the space will cause a page fault;Not if
PROT_WRITE,MAP_SHAREDI think.
Yeah, of course.
Quoted 8 lines
Quoted 2 lines
3) In the page fault handler, it goes to
do_wp_page, and in it if Page Is Locked, a new page is generated and filled into the pte. So the physical page seen by the host is not the same one by the NIC.When
MAP_PRIVATE, it's not the page being locked that causes the copy (it's not normally locked there, is it?), it's that it's not PageAnon; or if you're looking at 2.6.12 or older, thatpage_countis raised.Quoted 1 line
Quoted 4 lines
Quoted 1 line
Adding
PAGE_RWtoPAGE_COPYwill resolve this problem.No! That would give every user write access to shared files they should have no write access to.
I guess you refer to mmap a file MAP_READ|MAP_WRITE in MAP_PRIVATE way.
I think it is probably more logical to read the file data into an anoymous page and filled the pte with _PAGE_RW in the first time page-fault. It will probably reduce numbers of page fault interrupt.
Quoted 4 lines
Quoted 2 lines
In my option, the reason for absense of RW is to save memory by mapping all those only read pages into
ZERO_PAGE. But is there really programs which make many read-ops in memory space without even initialize them?Not just the
ZERO_PAGE: initial program data is another common example.
Ok, we can deal with initial program data using the above flow.
Quoted 3 lines
Hugh
Best regards
Yingchao Zhou
Quoted 7 lines · Yingchao Zhou
Quoted 5 lines
You want to mmap
MAP_SHARED, which will usePAGE_SHAREDinstead, including the write bit, both before and after the mprotects. There should be no problem then: do you actually see a problem whenMAP_SHAREDis used?It's ok to mmap
MAP_SHARED. But is it not a normal way tomalloc()a space and then registered to NIC ?
Not that I know of. How would one register malloc()ed space to a NIC? Sorry, I may well be misunderstanding you.
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Adding
PAGE_RWtoPAGE_COPYwill resolve this problem.No! That would give every user write access to shared files they should have no write access to.
I guess you refer to mmap a file MAP_READ|MAP_WRITE in
MAP_PRIVATEway.
I think it is probably more logical to read the file data into an anoymous page and filled the pte with_PAGE_RWin the first time page-fault. It will probably reduce numbers of page fault interrupt.
do_no_page() does just that when its fault demands write access; but doesn't waste memory and time on copying when it's only a read access.
Hugh