| To: | saw@xxxxxxxxxxxxx |
|---|---|
| Subject: | Re: NAPI for eepro100 |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Thu, 13 Jun 2002 01:47:00 -0700 (PDT) |
| Cc: | fxzhang@xxxxxxxxx, linux-mips@xxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, jgarzik@xxxxxxxxxxxxxxxx |
| In-reply-to: | <20020613125753.A23693@castle.nmd.msu.ru> |
| References: | <3D07D270.5060902@mandrakesoft.com> <20020612.160532.134201977.davem@redhat.com> <20020613125753.A23693@castle.nmd.msu.ru> |
| Sender: | owner-netdev@xxxxxxxxxxx |
From: Andrey Savochkin <saw@xxxxxxxxxxxxx> Date: Thu, 13 Jun 2002 12:57:53 +0400 On Wed, Jun 12, 2002 at 04:05:32PM -0700, David S. Miller wrote: > No, it's worse than that. > > See how non-consistent memory is used by the eepro100 driver > for descriptor bits? The skb->tail bits? > > That is very problematic. What's the problem? If it isn't allowed to do, then what is the meaning of PCI_DMA_BIDIRECTIONAL mappings? It's slow. Not wrong, just inefficient. Descriptors were meant to be done using consistent mappings, not "pci_map_*()"'d memory. The latter is meant to be used for long linear DMA transfers to/from the device. It is not meant for things the cpu pokes small bits of data in and out of, that is what consistent DMA memory is for. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: NAPI for eepro100, Andrey Savochkin |
|---|---|
| Next by Date: | Re: RFC: per-socket statistics on received/dropped packets, David Schwartz |
| Previous by Thread: | Re: NAPI for eepro100, Andrey Savochkin |
| Next by Thread: | Masqurading Question..., Sung-jae. Lee. |
| Indexes: | [Date] [Thread] [Top] [All Lists] |