On Mon, Jun 17, 2024 at 7:17 AM Pavel Begunkov asml.silence@gmail.com wrote:
On 6/13/24 02:35, Mina Almasry wrote:
Convert netmem to be a union of struct page and struct netmem. Overload the LSB of struct netmem* to indicate that it's a net_iov, otherwise it's a page.
Currently these entries in struct page are rented by the page_pool and used exclusively by the net stack:
struct { unsigned long pp_magic; struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; atomic_long_t pp_ref_count; };
Mirror these (and only these) entries into struct net_iov and implement netmem helpers that can access these common fields regardless of whether the underlying type is page or net_iov.
Implement checks for net_iov in netmem helpers which delegate to mm APIs, to ensure net_iov are never passed to the mm stack.
Signed-off-by: Mina Almasry almasrymina@google.com
Apart from small comments below
Reviewed-by: Pavel Begunkov asml.silence@gmail.com
include/net/netmem.h | 137 ++++++++++++++++++++++++++++++-- include/net/page_pool/helpers.h | 25 +++--- net/core/devmem.c | 3 + net/core/page_pool.c | 26 +++--- net/core/skbuff.c | 22 +++-- 5 files changed, 168 insertions(+), 45 deletions(-)
diff --git a/include/net/netmem.h b/include/net/netmem.h index 664df8325ece5..35ad237fdf29e 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h
...
-/* Converting from page to netmem is always safe, because a page can always be
- a netmem.
- */ static inline netmem_ref page_to_netmem(struct page *page) { return (__force netmem_ref)page;
@@ -68,17 +107,103 @@ static inline netmem_ref page_to_netmem(struct page *page)
static inline int netmem_ref_count(netmem_ref netmem) {
/* The non-pp refcount of net_iov is always 1. On net_iov, we only* support pp refcounting which uses the pp_ref_count field.*/if (netmem_is_net_iov(netmem))return 1;return page_ref_count(netmem_to_page(netmem));}
static inline unsigned long netmem_to_pfn(netmem_ref netmem) {
if (netmem_is_net_iov(netmem))return 0;IIRC 0 is a valid pfn. Not much of a concern since it's used only for tracing, but might make sense to pass some invalid pfn if there is one
AFAIU all non-negative pfns are technically valid pfns if the machine is big enough.
I could have this function return long long instead of unsigned long so I can return a negative number for errors, and then cast to unsigned long when I figure out it's actually a pfn. Seemed like such a hassle especially since the call site is just tracing that I figured it's not that worth it.
return page_to_pfn(netmem_to_page(netmem));...
static inline netmem_ref netmem_compound_head(netmem_ref netmem) {
/* niov are never compounded */if (netmem_is_net_iov(netmem))return netmem;return page_to_netmem(compound_head(netmem_to_page(netmem)));+static inline void *netmem_address(netmem_ref netmem)
I don't think it's used anywhere, do I miss it?
Ah, It's used by the GVE devmem implementation: https://github.com/mina/linux/commit/da89baa81873d457cbf7b49ee6b4f0d66855b20...
I could leave it out of this patch, then add it with the follow up GVE devmem implementation, but I figured almost for sure drivers are going to need this eventually, and it's small, so just put it here.
+{
if (netmem_is_net_iov(netmem))return NULL;return page_address(netmem_to_page(netmem));+}
...
diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a5957d3359762..1152e3547795a 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -26,6 +26,8 @@
...
/* If the page refcnt == 1, this will try to recycle the page. @@ -714,7 +713,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem, * refcnt == 1 means page_pool owns page, and can recycle it. * * page is NOT reusable when allocated when system is under
* some pressure. (page_is_pfmemalloc)
* some pressure. (page_pool_page_is_pfmemalloc)There is no page_pool_page_is_pfmemalloc()
Thanks done. I implemented most of your other comments on all the patches btw. I'm only responding to the ones I didn't apply for various reasons. Thanks for the review!