Skip to contentSkip to conversation

PAGE_RW Should be added to PAGE_COPY ?

RFC Yingchao Zhou 2 participants 2 messages Sep 15, 2006

lore
Share & tools
lore
#0 lore raw
Quoted 10 lines

PAGE_COPY (without the write bit) is used when the area was mmap'ed
MAP_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 use PAGE_SHARED instead, including the write bit, both before and after the mprotects. There should be no problem then: do you actually see a problem when MAP_SHARED is 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_COPY even when MAP_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 to PAGE_COPY, so write any page in the space will cause a page fault;

Not if PROT_WRITE, MAP_SHARED I 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, that page_count is raised.

Quoted 1 line
Quoted 4 lines
Quoted 1 line

Adding PAGE_RW to PAGE_COPY will 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

#1 lore raw
Quoted 7 lines · Yingchao Zhou
Quoted 5 lines

You want to mmap MAP_SHARED, which will use PAGE_SHARED instead, including the write bit, both before and after the mprotects. There should be no problem then: do you actually see a problem when MAP_SHARED is used?

It's ok to mmap MAP_SHARED. But is it not a normal way to malloc() 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_RW to PAGE_COPY will 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.

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