| Message ID | 162982123298.1124374.22718002900700392.stgit@dwillia2-desk3.amr.corp.intel.com (mailing list archive) |
|---|---|
| State | Superseded |
| Headers | show |
| Series | cxl_test: Enable CXL Topology and UAPI regression tests | expand |
On Tue, 24 Aug 2021 09:07:13 -0700 Dan Williams <dan.j.williams@intel.com> wrote: > The CXL_PMEM driver expects exclusive control of the label storage area > space. Similar to the LIBNVDIMM expectation that the label storage area > is only writable from userspace when the corresponding memory device is > not active in any region, the expectation is the native CXL_PCI UAPI > path is disabled while the cxl_nvdimm for a given cxl_memdev device is > active in LIBNVDIMM. > > Add the ability to toggle the availability of a given command for the > UAPI path. Use that new capability to shutdown changes to partitions and > the label storage area while the cxl_nvdimm device is actively proxying > commands for LIBNVDIMM. > > Acked-by: Ben Widawsky <ben.widawsky@intel.com> > Signed-off-by: Dan Williams <dan.j.williams@intel.com> > --- > drivers/cxl/core/mbox.c | 5 +++++ > drivers/cxl/core/memdev.c | 31 +++++++++++++++++++++++++++++++ > drivers/cxl/cxlmem.h | 4 ++++ > drivers/cxl/pmem.c | 35 ++++++++++++++++++++++++++++------- > 4 files changed, 68 insertions(+), 7 deletions(-) > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > index 73107b302224..6a5c4f3679ba 100644 > --- a/drivers/cxl/core/mbox.c > +++ b/drivers/cxl/core/mbox.c > @@ -230,6 +230,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) > * * %-EINVAL - Reserved fields or invalid values were used. > * * %-ENOMEM - Input or output buffer wasn't sized properly. > * * %-EPERM - Attempted to use a protected command. > + * * %-EBUSY - Kernel has claimed exclusive access to this opcode > * > * The result of this command is a fully validated command in @out_cmd that is > * safe to send to the hardware. > @@ -305,6 +306,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, > if (!test_bit(info->id, cxlm->enabled_cmds)) > return -ENOTTY; > > + /* Check that the command is not claimed for exclusive kernel use */ > + if (test_bit(info->id, cxlm->exclusive_cmds)) > + return -EBUSY; > + > /* Check the input buffer is the expected size */ > if (info->size_in >= 0 && info->size_in != send_cmd->in.size) > return -ENOMEM; > #endif /* __CXL_MEM_H__ */ > diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c > index 9652c3ee41e7..469b984176a2 100644 > --- a/drivers/cxl/pmem.c > +++ b/drivers/cxl/pmem.c > @@ -16,9 +16,21 @@ > */ > static struct workqueue_struct *cxl_pmem_wq; > > -static void unregister_nvdimm(void *nvdimm) > +static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); > + > +static void unregister_nvdimm(void *_cxl_nvd) > { > - nvdimm_delete(nvdimm); > + struct cxl_nvdimm *cxl_nvd = _cxl_nvd; > + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; > + struct cxl_mem *cxlm = cxlmd->cxlm; > + struct device *dev = &cxl_nvd->dev; > + struct nvdimm *nvdimm; > + > + nvdimm = dev_get_drvdata(dev); > + if (nvdimm) > + nvdimm_delete(nvdimm); > + > + clear_exclusive_cxl_commands(cxlm, exclusive_cmds); > } > > static int match_nvdimm_bridge(struct device *dev, const void *data) > @@ -39,9 +51,11 @@ static struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) > static int cxl_nvdimm_probe(struct device *dev) > { > struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); > + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; > + struct cxl_mem *cxlm = cxlmd->cxlm; > struct cxl_nvdimm_bridge *cxl_nvb; > + struct nvdimm *nvdimm = NULL; > unsigned long flags = 0; > - struct nvdimm *nvdimm; > int rc = -ENXIO; > > cxl_nvb = cxl_find_nvdimm_bridge(); > @@ -52,17 +66,20 @@ static int cxl_nvdimm_probe(struct device *dev) > if (!cxl_nvb->nvdimm_bus) > goto out; > > + set_exclusive_cxl_commands(cxlm, exclusive_cmds); > + > set_bit(NDD_LABELING, &flags); > nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, 0, 0, > NULL); > - if (!nvdimm) > - goto out; > - > - rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); > + dev_set_drvdata(dev, nvdimm); > + rc = devm_add_action_or_reset(dev, unregister_nvdimm, cxl_nvd); I think this ends up less readable than explicit devm handling of each part rather than combining them. set_exclusive...() rc = devm_add_action_or_rset(dev, unset_exclusive, cxlm); if (rc) goto out; nvidimm = nvdim_create() if (!nvdimm) //return value looks dubious in old code but I've not checked it properly. goto out; rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); if (rc) goto out; dev_set_drvdata(dev, nvdimm); and two simpler unwinding functions doing just one thing each. > out: > device_unlock(&cxl_nvb->dev); > put_device(&cxl_nvb->dev); > > + if (!nvdimm && rc == 0) > + rc = -ENOMEM; > + > return rc; > } > > @@ -194,6 +211,10 @@ static __init int cxl_pmem_init(void) > { > int rc; > > + set_bit(CXL_MEM_COMMAND_ID_SET_PARTITION_INFO, exclusive_cmds); > + set_bit(CXL_MEM_COMMAND_ID_SET_SHUTDOWN_STATE, exclusive_cmds); > + set_bit(CXL_MEM_COMMAND_ID_SET_LSA, exclusive_cmds); > + > cxl_pmem_wq = alloc_ordered_workqueue("cxl_pmem", 0); > if (!cxl_pmem_wq) > return -ENXIO; >
On Thu, Sep 2, 2021 at 11:09 AM Jonathan Cameron <Jonathan.Cameron@huawei.com> wrote: > > On Tue, 24 Aug 2021 09:07:13 -0700 > Dan Williams <dan.j.williams@intel.com> wrote: > > > The CXL_PMEM driver expects exclusive control of the label storage area > > space. Similar to the LIBNVDIMM expectation that the label storage area > > is only writable from userspace when the corresponding memory device is > > not active in any region, the expectation is the native CXL_PCI UAPI > > path is disabled while the cxl_nvdimm for a given cxl_memdev device is > > active in LIBNVDIMM. > > > > Add the ability to toggle the availability of a given command for the > > UAPI path. Use that new capability to shutdown changes to partitions and > > the label storage area while the cxl_nvdimm device is actively proxying > > commands for LIBNVDIMM. > > > > Acked-by: Ben Widawsky <ben.widawsky@intel.com> > > Signed-off-by: Dan Williams <dan.j.williams@intel.com> > > --- > > drivers/cxl/core/mbox.c | 5 +++++ > > drivers/cxl/core/memdev.c | 31 +++++++++++++++++++++++++++++++ > > drivers/cxl/cxlmem.h | 4 ++++ > > drivers/cxl/pmem.c | 35 ++++++++++++++++++++++++++++------- > > 4 files changed, 68 insertions(+), 7 deletions(-) > > > > diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c > > index 73107b302224..6a5c4f3679ba 100644 > > --- a/drivers/cxl/core/mbox.c > > +++ b/drivers/cxl/core/mbox.c > > @@ -230,6 +230,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) > > * * %-EINVAL - Reserved fields or invalid values were used. > > * * %-ENOMEM - Input or output buffer wasn't sized properly. > > * * %-EPERM - Attempted to use a protected command. > > + * * %-EBUSY - Kernel has claimed exclusive access to this opcode > > * > > * The result of this command is a fully validated command in @out_cmd that is > > * safe to send to the hardware. > > @@ -305,6 +306,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, > > if (!test_bit(info->id, cxlm->enabled_cmds)) > > return -ENOTTY; > > > > + /* Check that the command is not claimed for exclusive kernel use */ > > + if (test_bit(info->id, cxlm->exclusive_cmds)) > > + return -EBUSY; > > + > > /* Check the input buffer is the expected size */ > > if (info->size_in >= 0 && info->size_in != send_cmd->in.size) > > return -ENOMEM; > > > > #endif /* __CXL_MEM_H__ */ > > diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c > > index 9652c3ee41e7..469b984176a2 100644 > > --- a/drivers/cxl/pmem.c > > +++ b/drivers/cxl/pmem.c > > @@ -16,9 +16,21 @@ > > */ > > static struct workqueue_struct *cxl_pmem_wq; > > > > -static void unregister_nvdimm(void *nvdimm) > > +static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); > > + > > +static void unregister_nvdimm(void *_cxl_nvd) > > { > > - nvdimm_delete(nvdimm); > > + struct cxl_nvdimm *cxl_nvd = _cxl_nvd; > > + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; > > + struct cxl_mem *cxlm = cxlmd->cxlm; > > + struct device *dev = &cxl_nvd->dev; > > + struct nvdimm *nvdimm; > > + > > + nvdimm = dev_get_drvdata(dev); > > + if (nvdimm) > > + nvdimm_delete(nvdimm); > > + > > + clear_exclusive_cxl_commands(cxlm, exclusive_cmds); > > } > > > > static int match_nvdimm_bridge(struct device *dev, const void *data) > > @@ -39,9 +51,11 @@ static struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) > > static int cxl_nvdimm_probe(struct device *dev) > > { > > struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); > > + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; > > + struct cxl_mem *cxlm = cxlmd->cxlm; > > struct cxl_nvdimm_bridge *cxl_nvb; > > + struct nvdimm *nvdimm = NULL; > > unsigned long flags = 0; > > - struct nvdimm *nvdimm; > > int rc = -ENXIO; > > > > cxl_nvb = cxl_find_nvdimm_bridge(); > > @@ -52,17 +66,20 @@ static int cxl_nvdimm_probe(struct device *dev) > > if (!cxl_nvb->nvdimm_bus) > > goto out; > > > > + set_exclusive_cxl_commands(cxlm, exclusive_cmds); > > + > > set_bit(NDD_LABELING, &flags); > > nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, 0, 0, > > NULL); > > - if (!nvdimm) > > - goto out; > > - > > - rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); > > + dev_set_drvdata(dev, nvdimm); > > + rc = devm_add_action_or_reset(dev, unregister_nvdimm, cxl_nvd); > > I think this ends up less readable than explicit devm handling of each part > rather than combining them. > > > set_exclusive...() > rc = devm_add_action_or_rset(dev, unset_exclusive, cxlm); > if (rc) > goto out; > > nvidimm = nvdim_create() > if (!nvdimm) //return value looks dubious in old code but I've not checked it properly. > goto out; > > rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); > if (rc) > goto out; > dev_set_drvdata(dev, nvdimm); > > and two simpler unwinding functions doing just one thing each. Taking it a step further, the unwind is so simple here, might as well just have a typical cxl_nvdimm_remove() and drop the devm.
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 73107b302224..6a5c4f3679ba 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -230,6 +230,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * * %-EINVAL - Reserved fields or invalid values were used. * * %-ENOMEM - Input or output buffer wasn't sized properly. * * %-EPERM - Attempted to use a protected command. + * * %-EBUSY - Kernel has claimed exclusive access to this opcode * * The result of this command is a fully validated command in @out_cmd that is * safe to send to the hardware. @@ -305,6 +306,10 @@ static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm, if (!test_bit(info->id, cxlm->enabled_cmds)) return -ENOTTY; + /* Check that the command is not claimed for exclusive kernel use */ + if (test_bit(info->id, cxlm->exclusive_cmds)) + return -EBUSY; + /* Check the input buffer is the expected size */ if (info->size_in >= 0 && info->size_in != send_cmd->in.size) return -ENOMEM; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index a2a9691568af..ee61202c7aab 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -134,6 +134,37 @@ static const struct device_type cxl_memdev_type = { .groups = cxl_memdev_attribute_groups, }; +/** + * set_exclusive_cxl_commands() - atomically disable user cxl commands + * @cxlm: cxl_mem instance to modify + * @cmds: bitmap of commands to mark exclusive + * + * Flush the ioctl path and disable future execution of commands with + * the command ids set in @cmds. + */ +void set_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds) +{ + down_write(&cxl_memdev_rwsem); + bitmap_or(cxlm->exclusive_cmds, cxlm->exclusive_cmds, cmds, + CXL_MEM_COMMAND_ID_MAX); + up_write(&cxl_memdev_rwsem); +} +EXPORT_SYMBOL_GPL(set_exclusive_cxl_commands); + +/** + * clear_exclusive_cxl_commands() - atomically enable user cxl commands + * @cxlm: cxl_mem instance to modify + * @cmds: bitmap of commands to mark available for userspace + */ +void clear_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds) +{ + down_write(&cxl_memdev_rwsem); + bitmap_andnot(cxlm->exclusive_cmds, cxlm->exclusive_cmds, cmds, + CXL_MEM_COMMAND_ID_MAX); + up_write(&cxl_memdev_rwsem); +} +EXPORT_SYMBOL_GPL(clear_exclusive_cxl_commands); + static void cxl_memdev_shutdown(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index df4f3636a999..45d5347b5d61 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -102,6 +102,7 @@ struct cxl_mbox_cmd { * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. * @enabled_cmds: Hardware commands found enabled in CEL. + * @exclusive_cmds: Commands that are kernel-internal only * @pmem_range: Persistent memory capacity information. * @ram_range: Volatile memory capacity information. * @mbox_send: @dev specific transport for transmitting mailbox commands @@ -117,6 +118,7 @@ struct cxl_mem { struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); + DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); struct range pmem_range; struct range ram_range; @@ -190,4 +192,6 @@ int cxl_mem_identify(struct cxl_mem *cxlm); int cxl_mem_enumerate_cmds(struct cxl_mem *cxlm); int cxl_mem_create_range_info(struct cxl_mem *cxlm); struct cxl_mem *cxl_mem_create(struct device *dev); +void set_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds); +void clear_exclusive_cxl_commands(struct cxl_mem *cxlm, unsigned long *cmds); #endif /* __CXL_MEM_H__ */ diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 9652c3ee41e7..469b984176a2 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -16,9 +16,21 @@ */ static struct workqueue_struct *cxl_pmem_wq; -static void unregister_nvdimm(void *nvdimm) +static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); + +static void unregister_nvdimm(void *_cxl_nvd) { - nvdimm_delete(nvdimm); + struct cxl_nvdimm *cxl_nvd = _cxl_nvd; + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mem *cxlm = cxlmd->cxlm; + struct device *dev = &cxl_nvd->dev; + struct nvdimm *nvdimm; + + nvdimm = dev_get_drvdata(dev); + if (nvdimm) + nvdimm_delete(nvdimm); + + clear_exclusive_cxl_commands(cxlm, exclusive_cmds); } static int match_nvdimm_bridge(struct device *dev, const void *data) @@ -39,9 +51,11 @@ static struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(void) static int cxl_nvdimm_probe(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mem *cxlm = cxlmd->cxlm; struct cxl_nvdimm_bridge *cxl_nvb; + struct nvdimm *nvdimm = NULL; unsigned long flags = 0; - struct nvdimm *nvdimm; int rc = -ENXIO; cxl_nvb = cxl_find_nvdimm_bridge(); @@ -52,17 +66,20 @@ static int cxl_nvdimm_probe(struct device *dev) if (!cxl_nvb->nvdimm_bus) goto out; + set_exclusive_cxl_commands(cxlm, exclusive_cmds); + set_bit(NDD_LABELING, &flags); nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, 0, 0, NULL); - if (!nvdimm) - goto out; - - rc = devm_add_action_or_reset(dev, unregister_nvdimm, nvdimm); + dev_set_drvdata(dev, nvdimm); + rc = devm_add_action_or_reset(dev, unregister_nvdimm, cxl_nvd); out: device_unlock(&cxl_nvb->dev); put_device(&cxl_nvb->dev); + if (!nvdimm && rc == 0) + rc = -ENOMEM; + return rc; } @@ -194,6 +211,10 @@ static __init int cxl_pmem_init(void) { int rc; + set_bit(CXL_MEM_COMMAND_ID_SET_PARTITION_INFO, exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_SET_SHUTDOWN_STATE, exclusive_cmds); + set_bit(CXL_MEM_COMMAND_ID_SET_LSA, exclusive_cmds); + cxl_pmem_wq = alloc_ordered_workqueue("cxl_pmem", 0); if (!cxl_pmem_wq) return -ENXIO;