On Mon, Jun 17, 2024 at 7:17 AM Pavel Begunkov [off-list ref] wrote:

On 6/13/24 02:35, Mina Almasry wrote:

quoted

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 <redacted>

Apart from small comments below

Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

quoted

---
  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

...

quoted

-/* 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.

quoted

+
      return page_to_pfn(netmem_to_page(netmem));
  }

...

quoted

  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/da89baa81873d457cbf7b49ee6b4f0d66855b205

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.

quoted

+{
+     if (netmem_is_net_iov(netmem))
+             return NULL;
+
+     return page_address(netmem_to_page(netmem));
+}
+

...

quoted

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 @@

...

quoted

  /* 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!


-- 
Thanks,
Mina