Message ID | 20240516081202.27023-10-alucerop@amd.com |
---|---|
State | New, archived |
Headers | show |
Series | RFC: add Type2 device support | expand |
From: Alejandro Lucero <alucerop@amd.com> Search and reserve DPA given input constraints. Based on: https://lore.kernel.org/linux-cxl/168592149709.1948938.8663425987110396027.stgit@dwillia2-xfh.jf.intel.com/T/#m4271ee49a91615c8af54e3ab20679f8be3099393 Signed-off-by: Alejandro Lucero <alucerop@amd.com> Co-developed-by: Dan Williams <dan.j.williams@intel.com> On 5/16/24 09:11, alucerop@amd.com wrote: > From: Alejandro Lucero <alucerop@amd.com> > > Search and reserve DPA given input constraints. > > Signed-off-by: Alejandro Lucero <alucerop@amd.com> > Signed-off-by: Dan Williams <dan.j.williams@intel.com> > --- > drivers/cxl/core/core.h | 1 - > drivers/cxl/core/hdm.c | 153 +++++++++++++++++++++++----- > include/linux/cxlmem.h | 5 + > tools/testing/cxl/type2/pci_type2.c | 12 ++- > 4 files changed, 145 insertions(+), 26 deletions(-) > > diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h > index bc5a95665aa0..c0a2e2c1ccb3 100644 > --- a/drivers/cxl/core/core.h > +++ b/drivers/cxl/core/core.h > @@ -61,7 +61,6 @@ struct dentry *cxl_debugfs_create_dir(const char *dir); > int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, > enum cxl_decoder_mode mode); > int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size); > -int cxl_dpa_free(struct cxl_endpoint_decoder *cxled); > resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled); > resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled); > > diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c > index c5f70741d70a..6459b6ecde88 100644 > --- a/drivers/cxl/core/hdm.c > +++ b/drivers/cxl/core/hdm.c > @@ -404,6 +404,7 @@ int cxl_dpa_free(struct cxl_endpoint_decoder *cxled) > up_write(&cxl_dpa_rwsem); > return rc; > } > +EXPORT_SYMBOL_NS_GPL(cxl_dpa_free, CXL); > > int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, > enum cxl_decoder_mode mode) > @@ -451,30 +452,17 @@ int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, > return rc; > } > > -int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) > +static resource_size_t cxl_dpa_freespace(struct cxl_endpoint_decoder *cxled, > + resource_size_t *start_out, > + resource_size_t *skip_out) > { > struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); > resource_size_t free_ram_start, free_pmem_start; > - struct cxl_port *port = cxled_to_port(cxled); > struct cxl_dev_state *cxlds = cxlmd->cxlds; > - struct device *dev = &cxled->cxld.dev; > resource_size_t start, avail, skip; > struct resource *p, *last; > - int rc; > - > - down_write(&cxl_dpa_rwsem); > - if (cxled->cxld.region) { > - dev_dbg(dev, "decoder attached to %s\n", > - dev_name(&cxled->cxld.region->dev)); > - rc = -EBUSY; > - goto out; > - } > > - if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { > - dev_dbg(dev, "decoder enabled\n"); > - rc = -EBUSY; > - goto out; > - } > + lockdep_assert_held(&cxl_dpa_rwsem); > > for (p = cxlds->ram_res.child, last = NULL; p; p = p->sibling) > last = p; > @@ -496,7 +484,6 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) > skip = 0; > } else if (cxled->mode == CXL_DECODER_PMEM) { > resource_size_t skip_start, skip_end; > - > start = free_pmem_start; > avail = cxlds->pmem_res.end - start + 1; > skip_start = free_ram_start; > @@ -506,21 +493,50 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) > * already handled the skip. > */ > if (cxlds->pmem_res.child && > - skip_start == cxlds->pmem_res.child->start) > + skip_start == cxlds->pmem_res.child->start) > skip_end = skip_start - 1; > else > skip_end = start - 1; > skip = skip_end - skip_start + 1; > } else { > - dev_dbg(dev, "mode not set\n"); > - rc = -EINVAL; > + avail = 0; > + } > + > + if (!avail) > + return 0; > + if (start_out) > + *start_out = start; > + if (skip_out) > + *skip_out = skip; > + return avail; > +} > + > +int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) > +{ > + struct cxl_port *port = cxled_to_port(cxled); > + struct device *dev = &cxled->cxld.dev; > + resource_size_t start, avail, skip; > + int rc; > + > + down_write(&cxl_dpa_rwsem); > + if (cxled->cxld.region) { > + dev_dbg(dev, "EBUSY, decoder attached to %s\n", > + dev_name(&cxled->cxld.region->dev)); > + rc = -EBUSY; > goto out; > } > > + if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { > + dev_dbg(dev, "EBUSY, decoder enabled\n"); > + rc = -EBUSY; > + goto out; > + } > + > + avail = cxl_dpa_freespace(cxled, &start, &skip); > if (size > avail) { > dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size, > - cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem", > - &avail); > + cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem", > + &avail); > rc = -ENOSPC; > goto out; > } > @@ -532,9 +548,98 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) > if (rc) > return rc; > > - return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); > + return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); > } > > +static int find_free_decoder(struct device *dev, void *data) > +{ > + struct cxl_endpoint_decoder *cxled; > + struct cxl_port *port; > + > + if (!is_endpoint_decoder(dev)) > + return 0; > + > + cxled = to_cxl_endpoint_decoder(dev); > + port = cxled_to_port(cxled); > + > + if (cxled->cxld.id != port->hdm_end + 1) { > + return 0; > + } > + return 1; > +} > + > +/** > + * cxl_request_dpa - search and reserve DPA given input constraints > + * @endpoint: an endpoint port with available decoders > + * @mode: DPA operation mode (ram vs pmem) > + * @min: the minimum amount of capacity the call needs > + * @max: extra capacity to allocate after min is satisfied > + * > + * Given that a region needs to allocate from limited HPA capacity it > + * may be the case that a device has more mappable DPA capacity than > + * available HPA. So, the expectation is that @min is a driver known > + * value for how much capacity is needed, and @max is based the limit of > + * how much HPA space is available for a new region. > + * > + * Returns a pinned cxl_decoder with at least @min bytes of capacity > + * reserved, or an error pointer. The caller is also expected to own the > + * lifetime of the memdev registration associated with the endpoint to > + * pin the decoder registered as well. > + */ > +struct cxl_endpoint_decoder *cxl_request_dpa(struct cxl_port *endpoint, > + enum cxl_decoder_mode mode, > + resource_size_t min, > + resource_size_t max) > +{ > + struct cxl_endpoint_decoder *cxled; > + struct device *cxled_dev; > + resource_size_t alloc; > + int rc; > + > + if (!IS_ALIGNED(min | max, SZ_256M)) > + return ERR_PTR(-EINVAL); > + > + down_read(&cxl_dpa_rwsem); > + > + cxled_dev = device_find_child(&endpoint->dev, NULL, find_free_decoder); > + if (!cxled_dev) > + cxled = ERR_PTR(-ENXIO); > + else > + cxled = to_cxl_endpoint_decoder(cxled_dev); > + > + up_read(&cxl_dpa_rwsem); > + > + if (IS_ERR(cxled)) { > + return cxled; > + } > + > + rc = cxl_dpa_set_mode(cxled, mode); > + if (rc) > + goto err; > + > + down_read(&cxl_dpa_rwsem); > + alloc = cxl_dpa_freespace(cxled, NULL, NULL); > + up_read(&cxl_dpa_rwsem); > + > + if (max) > + alloc = min(max, alloc); > + if (alloc < min) { > + rc = -ENOMEM; > + goto err; > + } > + > + rc = cxl_dpa_alloc(cxled, alloc); > + if (rc) > + goto err; > + > + return cxled; > +err: > + put_device(cxled_dev); > + return ERR_PTR(rc); > +} > +EXPORT_SYMBOL_NS_GPL(cxl_request_dpa, CXL); > + > + > static void cxld_set_interleave(struct cxl_decoder *cxld, u32 *ctrl) > { > u16 eig; > diff --git a/include/linux/cxlmem.h b/include/linux/cxlmem.h > index 342ccd5486d3..caf1cd86421c 100644 > --- a/include/linux/cxlmem.h > +++ b/include/linux/cxlmem.h > @@ -870,4 +870,9 @@ struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_port *endpoint, > int interleave_ways, > unsigned long flags, > resource_size_t *max); > +struct cxl_endpoint_decoder *cxl_request_dpa(struct cxl_port *endpoint, > + enum cxl_decoder_mode mode, > + resource_size_t min, > + resource_size_t max); > +int cxl_dpa_free(struct cxl_endpoint_decoder *cxled); > #endif /* __CXL_MEM_H__ */ > diff --git a/tools/testing/cxl/type2/pci_type2.c b/tools/testing/cxl/type2/pci_type2.c > index deb5eeae501b..6499d709f54d 100644 > --- a/tools/testing/cxl/type2/pci_type2.c > +++ b/tools/testing/cxl/type2/pci_type2.c > @@ -4,6 +4,7 @@ > #include <linux/cxlpci.h> > #include <linux/cxlmem.h> > > +struct cxl_endpoint_decoder *cxled; > struct cxl_root_decoder *cxlrd; > struct cxl_dev_state *cxlds; > struct cxl_memdev *cxlmd; > @@ -99,6 +100,15 @@ static int type2_pci_probe(struct pci_dev *pci_dev, > goto out; > } > > + pci_info(pci_dev, "cxl request_dpa..."); > + cxled = cxl_request_dpa(endpoint, CXL_DECODER_RAM, CXL_TYPE2_MEM_SIZE, > + CXL_TYPE2_MEM_SIZE); > + if (IS_ERR(cxled)) { > + dev_dbg(&pci_dev->dev, "cxl_request_dpa error\n"); > + rc = PTR_ERR(cxled); > + goto out; > + } > + > out: > cxl_release_endpoint(cxlmd, endpoint); > > @@ -107,7 +117,7 @@ static int type2_pci_probe(struct pci_dev *pci_dev, > > static void type2_pci_remove(struct pci_dev *pci_dev) > { > - > + cxl_dpa_free(cxled); > } > > /* PCI device ID table */
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index bc5a95665aa0..c0a2e2c1ccb3 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -61,7 +61,6 @@ struct dentry *cxl_debugfs_create_dir(const char *dir); int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, enum cxl_decoder_mode mode); int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size); -int cxl_dpa_free(struct cxl_endpoint_decoder *cxled); resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled); resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled); diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index c5f70741d70a..6459b6ecde88 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -404,6 +404,7 @@ int cxl_dpa_free(struct cxl_endpoint_decoder *cxled) up_write(&cxl_dpa_rwsem); return rc; } +EXPORT_SYMBOL_NS_GPL(cxl_dpa_free, CXL); int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, enum cxl_decoder_mode mode) @@ -451,30 +452,17 @@ int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled, return rc; } -int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) +static resource_size_t cxl_dpa_freespace(struct cxl_endpoint_decoder *cxled, + resource_size_t *start_out, + resource_size_t *skip_out) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); resource_size_t free_ram_start, free_pmem_start; - struct cxl_port *port = cxled_to_port(cxled); struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct device *dev = &cxled->cxld.dev; resource_size_t start, avail, skip; struct resource *p, *last; - int rc; - - down_write(&cxl_dpa_rwsem); - if (cxled->cxld.region) { - dev_dbg(dev, "decoder attached to %s\n", - dev_name(&cxled->cxld.region->dev)); - rc = -EBUSY; - goto out; - } - if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { - dev_dbg(dev, "decoder enabled\n"); - rc = -EBUSY; - goto out; - } + lockdep_assert_held(&cxl_dpa_rwsem); for (p = cxlds->ram_res.child, last = NULL; p; p = p->sibling) last = p; @@ -496,7 +484,6 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) skip = 0; } else if (cxled->mode == CXL_DECODER_PMEM) { resource_size_t skip_start, skip_end; - start = free_pmem_start; avail = cxlds->pmem_res.end - start + 1; skip_start = free_ram_start; @@ -506,21 +493,50 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) * already handled the skip. */ if (cxlds->pmem_res.child && - skip_start == cxlds->pmem_res.child->start) + skip_start == cxlds->pmem_res.child->start) skip_end = skip_start - 1; else skip_end = start - 1; skip = skip_end - skip_start + 1; } else { - dev_dbg(dev, "mode not set\n"); - rc = -EINVAL; + avail = 0; + } + + if (!avail) + return 0; + if (start_out) + *start_out = start; + if (skip_out) + *skip_out = skip; + return avail; +} + +int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) +{ + struct cxl_port *port = cxled_to_port(cxled); + struct device *dev = &cxled->cxld.dev; + resource_size_t start, avail, skip; + int rc; + + down_write(&cxl_dpa_rwsem); + if (cxled->cxld.region) { + dev_dbg(dev, "EBUSY, decoder attached to %s\n", + dev_name(&cxled->cxld.region->dev)); + rc = -EBUSY; goto out; } + if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) { + dev_dbg(dev, "EBUSY, decoder enabled\n"); + rc = -EBUSY; + goto out; + } + + avail = cxl_dpa_freespace(cxled, &start, &skip); if (size > avail) { dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size, - cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem", - &avail); + cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem", + &avail); rc = -ENOSPC; goto out; } @@ -532,9 +548,98 @@ int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size) if (rc) return rc; - return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); + return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled); } +static int find_free_decoder(struct device *dev, void *data) +{ + struct cxl_endpoint_decoder *cxled; + struct cxl_port *port; + + if (!is_endpoint_decoder(dev)) + return 0; + + cxled = to_cxl_endpoint_decoder(dev); + port = cxled_to_port(cxled); + + if (cxled->cxld.id != port->hdm_end + 1) { + return 0; + } + return 1; +} + +/** + * cxl_request_dpa - search and reserve DPA given input constraints + * @endpoint: an endpoint port with available decoders + * @mode: DPA operation mode (ram vs pmem) + * @min: the minimum amount of capacity the call needs + * @max: extra capacity to allocate after min is satisfied + * + * Given that a region needs to allocate from limited HPA capacity it + * may be the case that a device has more mappable DPA capacity than + * available HPA. So, the expectation is that @min is a driver known + * value for how much capacity is needed, and @max is based the limit of + * how much HPA space is available for a new region. + * + * Returns a pinned cxl_decoder with at least @min bytes of capacity + * reserved, or an error pointer. The caller is also expected to own the + * lifetime of the memdev registration associated with the endpoint to + * pin the decoder registered as well. + */ +struct cxl_endpoint_decoder *cxl_request_dpa(struct cxl_port *endpoint, + enum cxl_decoder_mode mode, + resource_size_t min, + resource_size_t max) +{ + struct cxl_endpoint_decoder *cxled; + struct device *cxled_dev; + resource_size_t alloc; + int rc; + + if (!IS_ALIGNED(min | max, SZ_256M)) + return ERR_PTR(-EINVAL); + + down_read(&cxl_dpa_rwsem); + + cxled_dev = device_find_child(&endpoint->dev, NULL, find_free_decoder); + if (!cxled_dev) + cxled = ERR_PTR(-ENXIO); + else + cxled = to_cxl_endpoint_decoder(cxled_dev); + + up_read(&cxl_dpa_rwsem); + + if (IS_ERR(cxled)) { + return cxled; + } + + rc = cxl_dpa_set_mode(cxled, mode); + if (rc) + goto err; + + down_read(&cxl_dpa_rwsem); + alloc = cxl_dpa_freespace(cxled, NULL, NULL); + up_read(&cxl_dpa_rwsem); + + if (max) + alloc = min(max, alloc); + if (alloc < min) { + rc = -ENOMEM; + goto err; + } + + rc = cxl_dpa_alloc(cxled, alloc); + if (rc) + goto err; + + return cxled; +err: + put_device(cxled_dev); + return ERR_PTR(rc); +} +EXPORT_SYMBOL_NS_GPL(cxl_request_dpa, CXL); + + static void cxld_set_interleave(struct cxl_decoder *cxld, u32 *ctrl) { u16 eig; diff --git a/include/linux/cxlmem.h b/include/linux/cxlmem.h index 342ccd5486d3..caf1cd86421c 100644 --- a/include/linux/cxlmem.h +++ b/include/linux/cxlmem.h @@ -870,4 +870,9 @@ struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_port *endpoint, int interleave_ways, unsigned long flags, resource_size_t *max); +struct cxl_endpoint_decoder *cxl_request_dpa(struct cxl_port *endpoint, + enum cxl_decoder_mode mode, + resource_size_t min, + resource_size_t max); +int cxl_dpa_free(struct cxl_endpoint_decoder *cxled); #endif /* __CXL_MEM_H__ */ diff --git a/tools/testing/cxl/type2/pci_type2.c b/tools/testing/cxl/type2/pci_type2.c index deb5eeae501b..6499d709f54d 100644 --- a/tools/testing/cxl/type2/pci_type2.c +++ b/tools/testing/cxl/type2/pci_type2.c @@ -4,6 +4,7 @@ #include <linux/cxlpci.h> #include <linux/cxlmem.h> +struct cxl_endpoint_decoder *cxled; struct cxl_root_decoder *cxlrd; struct cxl_dev_state *cxlds; struct cxl_memdev *cxlmd; @@ -99,6 +100,15 @@ static int type2_pci_probe(struct pci_dev *pci_dev, goto out; } + pci_info(pci_dev, "cxl request_dpa..."); + cxled = cxl_request_dpa(endpoint, CXL_DECODER_RAM, CXL_TYPE2_MEM_SIZE, + CXL_TYPE2_MEM_SIZE); + if (IS_ERR(cxled)) { + dev_dbg(&pci_dev->dev, "cxl_request_dpa error\n"); + rc = PTR_ERR(cxled); + goto out; + } + out: cxl_release_endpoint(cxlmd, endpoint); @@ -107,7 +117,7 @@ static int type2_pci_probe(struct pci_dev *pci_dev, static void type2_pci_remove(struct pci_dev *pci_dev) { - + cxl_dpa_free(cxled); } /* PCI device ID table */