| Message ID | 1682252271-2544-6-git-send-email-guwen@linux.alibaba.com (mailing list archive) |
|---|---|
| State | RFC |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | net/smc: Introduce SMC-D-based OS internal communication acceleration | expand |
| Context | Check | Description |
|---|---|---|
| netdev/series_format | success | Posting correctly formatted |
| netdev/tree_selection | success | Clearly marked for net-next |
| netdev/fixes_present | success | Fixes tag not required for -next series |
| netdev/header_inline | success | No static functions without inline keyword in header files |
| netdev/build_32bit | success | Errors and warnings before: 8 this patch: 8 |
| netdev/cc_maintainers | success | CCed 9 of 9 maintainers |
| netdev/build_clang | fail | Errors and warnings before: 13 this patch: 13 |
| netdev/verify_signedoff | success | Signed-off-by tag matches author and committer |
| netdev/deprecated_api | success | None detected |
| netdev/check_selftest | success | No net selftest shell script |
| netdev/verify_fixes | success | No Fixes tag |
| netdev/build_allmodconfig_warn | fail | Errors and warnings before: 14 this patch: 14 |
| netdev/checkpatch | success | total: 0 errors, 0 warnings, 0 checks, 38 lines checked |
| netdev/kdoc | success | Errors and warnings before: 0 this patch: 0 |
| netdev/source_inline | success | Was 0 now: 0 |
On Sun, Apr 23, 2023 at 08:17:47PM +0800, Wen Gu wrote: > On s390, since all OSs run on a kind of machine level hypervisor which > is a partitioning hypervisor without paging, the sndbufs and DMBs in > such case are unable to be mapped to the same physical memory. > > However, in other scene, such as communication within the same OS instance > (loopback) or between guests of a paging hypervisor (eg. KVM), the sndbufs > and DMBs can be mapped to the same physical memory to avoid memory copy > from sndbufs to DMBs. > > So this patch introduces an interface to smcd_ops for users to judge > whether DMB-map is available. And for reuse, the interface is designed > to return DMB attribute, not only mappability. > > Signed-off-by: Wen Gu <guwen@linux.alibaba.com> ... > diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c > index 8ad4c71..1d97e77 100644 > --- a/net/smc/smc_ism.c > +++ b/net/smc/smc_ism.c > @@ -213,6 +213,14 @@ int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc) > return rc; > } > > +bool smc_ism_dmb_mappable(struct smcd_dev *smcd) > +{ > + if (smcd->ops->get_dev_dmb_attr && > + (smcd->ops->get_dev_dmb_attr(smcd) & (1 << ISM_DMB_MAPPABLE))) nit: this could use BIT(ISM_DMB_MAPPABLE) > + return true; > + return false; > +} > + > int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, > struct smc_buf_desc *dmb_desc) > { ...
diff --git a/include/net/smc.h b/include/net/smc.h index 021ca42..e39ac41 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -55,6 +55,10 @@ struct smcd_seid { #define ISM_ERROR 0xFFFF +enum { + ISM_DMB_MAPPABLE = 0, +}; + struct smcd_dev; struct smcd_ops { @@ -77,6 +81,7 @@ struct smcd_ops { u64 (*get_local_gid)(struct smcd_dev *dev); u16 (*get_chid)(struct smcd_dev *dev); struct device* (*get_dev)(struct smcd_dev *dev); + int (*get_dev_dmb_attr)(struct smcd_dev *dev); }; struct smcd_dev { diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 8ad4c71..1d97e77 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -213,6 +213,14 @@ int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc) return rc; } +bool smc_ism_dmb_mappable(struct smcd_dev *smcd) +{ + if (smcd->ops->get_dev_dmb_attr && + (smcd->ops->get_dev_dmb_attr(smcd) & (1 << ISM_DMB_MAPPABLE))) + return true; + return false; +} + int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len, struct smc_buf_desc *dmb_desc) { diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index d18c50a..0b1913a 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -40,6 +40,7 @@ struct smc_ism_vlanid { /* VLAN id set on ISM device */ int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size, struct smc_buf_desc *dmb_desc); int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); +bool smc_ism_dmb_mappable(struct smcd_dev *smcd); int smc_ism_signal_shutdown(struct smc_link_group *lgr); void smc_ism_get_system_eid(u8 **eid); u16 smc_ism_get_chid(struct smcd_dev *dev);
On s390, since all OSs run on a kind of machine level hypervisor which is a partitioning hypervisor without paging, the sndbufs and DMBs in such case are unable to be mapped to the same physical memory. However, in other scene, such as communication within the same OS instance (loopback) or between guests of a paging hypervisor (eg. KVM), the sndbufs and DMBs can be mapped to the same physical memory to avoid memory copy from sndbufs to DMBs. So this patch introduces an interface to smcd_ops for users to judge whether DMB-map is available. And for reuse, the interface is designed to return DMB attribute, not only mappability. Signed-off-by: Wen Gu <guwen@linux.alibaba.com> --- include/net/smc.h | 5 +++++ net/smc/smc_ism.c | 8 ++++++++ net/smc/smc_ism.h | 1 + 3 files changed, 14 insertions(+)