- 10 Mar, 2024 11 commits
-
-
Ricardo B. Marliere authored
Since commit 43a7206b ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the st_sysfs_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
Ricardo B. Marliere <ricardo@marliere.net> Link: https://lore.kernel.org/r/20240302-class_cleanup-scsi-v1-5-b9096b990e27@marliere.netSigned-off-by:
Martin K. Petersen <martin.petersen@oracle.com>
-
Ricardo B. Marliere authored
Since commit 43a7206b ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the ch_sysfs_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Ricardo B. Marliere authored
Since commit 43a7206b ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the cxlflash_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Ricardo B. Marliere authored
Since commit 43a7206b ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the pmcraid_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Ricardo B. Marliere authored
Since commit 43a7206b ("driver core: class: make class_register() take a const *"), the driver core allows for struct class to be in read-only memory, so move the sg_sysfs_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Peter Wang authored
Add config_scsi_dev vops comment. Signed-off-by:
Peter Wang <peter.wang@mediatek.com> Link: https://lore.kernel.org/r/20240301034610.24928-1-peter.wang@mediatek.comReviewed-by:
Bart Van Assche <bvanassche@acm.org> Signed-off-by:
-
Dmitry Baryshkov authored
The MSM8996 DT doesn't provide frequency limits for the core_clk_unipro clock, which results in miscalculation of the cycles_in_1us value. Provide the backwards-compatible default to support existing MSM8996 DT files. Fixes: b4e13e1a ("scsi: ufs: qcom: Add multiple frequency support for MAX_CORE_CLK_1US_CYCLES") Cc: Nitin Rawat <quic_nitirawa@quicinc.com> Cc: stable@vger.kernel.org # 6.7.x Reviewed-by:
Konrad Dybcio <konrad.dybcio@linaro.org> Reviewed-by:
Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Signed-off-by:
Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Link: https://lore.kernel.org/r/20240218-msm8996-fix-ufs-v3-1-40aab49899a3@linaro.orgSigned-off-by:
-
Xingui Yang authored
As of commit d8649fc1 ("scsi: libsas: Do discovery on empty PHY to update PHY info"), do discovery will send a new SMP_DISCOVER and update phy->phy_change_count. We found that if the disk is reconnected and phy change_count changes at this time, the disk scanning process will not be triggered. Therefore, call sas_set_ex_phy() to update the PHY info with the results of the last query. And because the previous phy info will be used when calling sas_unregister_devs_sas_addr(), sas_unregister_devs_sas_addr() should be called before sas_set_ex_phy(). Fixes: d8649fc1 ("scsi: libsas: Do discovery on empty PHY to update PHY info") Signed-off-by:
Xingui Yang <yangxingui@huawei.com> Link: https://lore.kernel.org/r/20240307141413.48049-3-yangxingui@huawei.comReviewed-by:
John Garry <john.g.garry@oracle.com> Signed-off-by:
-
Xingui Yang authored
Add a helper to get attached_sas_addr and device type from disc_resp. Suggested-by:
-
Colin Ian King authored
The variable 'xfer_len' is being initialized and incremented but it is never actually referenced in any other way. The variable is redundant and can be removed. Cleans up clang scan build warning: drivers/target/iscsi/iscsi_target_erl1.c:586:45: warning: variable 'xfer_len' set but not used [-Wunused-but-set-variable] Signed-off-by:
Colin Ian King <colin.i.king@gmail.com> Link: https://lore.kernel.org/r/20240307104553.1980860-1-colin.i.king@gmail.comSigned-off-by:
-
Rohit Ner authored
As per JEDEC Standard No. 223E Section 5.9.2, the max # active commands value programmed by the host sw in MCQConfig.MAC should be one less than the actual value. Signed-off-by:
Rohit Ner <rohitner@google.com> Link: https://lore.kernel.org/r/20240220095637.2900067-1-rohitner@google.comReviewed-by:
Can Guo <quic_cang@quicinc.com> Signed-off-by:
-
- 27 Feb, 2024 6 commits
-
-
Ricardo B. Marliere authored
Since commit aed65af1 ("drivers: make device_type const"), the driver core can properly handle constant struct device_type. Move the scsi_host_type, scsi_target_type and scsi_dev_type variables to be constant structures as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
-
Justin Stitt authored
strncpy() is deprecated [1] and as such we should use different apis to copy string data. We can see that ct is NUL-initialized with fc_ct_hdr_fill: | ct = fc_ct_hdr_fill(fp, op, sizeof(struct fc_ns_rspn) + len, ... In fc_ct_hdr_fill(): | memset(ct, 0, ct_plen); We also calculate the length of the source string: | len = strnlen(fc_host_symbolic_name(lport->host), 255); ...then this argument is used in strncpy(), which is bad because the pattern of (dest, src, strlen(src)) usually leaves the destination buffer without NUL-termination. However, it looks as though we do not require NUL-termination since fr_name is part of a seq_buf-like structure wherein its length is monitored: | struct fc_ns_rspn { | struct fc_ns_fid fr_fid; /* port ID object */ | __u8 fr_name_len; | char fr_name[]; | } __attribute__((__packed__)); So, this is really just a byte copy into a length-bounded buffer. Let's use memcpy(). Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings [1] Link: https://github.com/KSPP/linux/issues/90 Cc: linux-hardening@vger.kernel.org Signed-off-by:Justin Stitt <justinstitt@google.com> Link: https://lore.kernel.org/r/20240221-strncpy-drivers-scsi-libfc-fc_encode-h-v2-1-019a0889c5ca@google.comReviewed-by:
Kees Cook <keescook@chromium.org> Signed-off-by:
-
Justin Stitt authored
strncpy() is deprecated for use on NUL-terminated destination strings [1] and as such we should prefer more robust and less ambiguous string interfaces. We expect ae->value_string to be NUL-terminated because there's a comment that says as much; these attr strings are also used with other string APIs, further cementing the fact. Now, the question of whether or not to NUL-pad the destination buffer: lpfc_fdmi_rprt_defer() initializes vports (all zero-initialized), then we call lpfc_fdmi_cmd() with each vport and a mask. Then, inside of lpfc_fdmi_cmd() we check each bit in the mask to invoke the proper callback. Importantly, the zero-initialized vport is passed in as the "attr" parameter. Seeing this: | struct lpfc_fdmi_attr_string *ae = attr; ... we can tell that ae->value_string is entirely zero-initialized. Due to this, NUL-padding is _not_ required as it would be redundant. Considering the above, a suitable replacement is strscpy() [2]. Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings [1] Link: https://manpages.debian.org/testing/linux-manual-4.8/strscpy.9.en.html [2] Link: https://github.com/KSPP/linux/issues/90 Cc: linux-hardening@vger.kernel.org Signed-off-by:
-
Arnd Bergmann authored
The bfa driver is full of state machines and a generic abstraction layer for them. This relies on casting function pointers, but that is no longer allowed when CONFIG_CFI_CLANG is enabled and causes a huge number of warnings like: drivers/scsi/bfa/bfad.c:169:3: error: cast from 'void (*)(struct bfad_s *, enum bfad_sm_event)' to 'bfa_sm_t' (aka 'void (*)(void *, int)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] bfa_sm_set_state(bfad, bfad_sm_created); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Rework the mechanism to no longer require the function pointer casts, by having separate types for each individual state machine. This in turn requires moving the enum definitions for each state machine into the header files in order to define the typedef. Reviewed-by:Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20240222124433.2046570-2-arnd@kernel.orgSigned-off-by:
-
Arnd Bergmann authored
Some callback functions used here take a boolean argument, others take a status argument. This breaks KCFI type checking, so clang now warns about the function pointer cast: drivers/scsi/bfa/bfad_bsg.c:2138:29: error: cast from 'void (*)(void *, enum bfa_status)' to 'bfa_cb_cbfn_t' (aka 'void (*)(void *, enum bfa_boolean)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] Assuming the code is actually correct here and the callers always match the argument types of the callee, rework this to replace the explicit cast with a union of the two pointer types. This does not change the behavior of the code, so if something is actually broken here, a larger rework may be necessary. Fixes: 37ea0558 ("[SCSI] bfa: Added support to collect and reset fcport stats") Fixes: 3ec4f2c8 ("[SCSI] bfa: Added support to configure QOS and collect stats.") Reviewed-by:
-
Simone Weiß authored
Commit c3b0d087 ("scsi: bfa: Remove unnecessary struct declarations") removed duplicate struct declarations for struct bfa_fcs_s and struct bfa_fcs_fabric_s. However, there are further duplications: - struct bfad_vf_s is declared in line 165 remove the duplication in line 834. - struct bfad_rport_s is declared in line 394 remove the duplication in line 836. Remove them. Signed-off-by:
Simone Weiß <simone.p.weiss@posteo.com> Link: https://lore.kernel.org/r/20240217191409.6260-1-simone.p.weiss@posteo.comSigned-off-by:
-
- 15 Feb, 2024 2 commits
-
-
Arnd Bergmann authored
csiostor uses function pointer casts to keep the csio_ln_ev state machine hidden, but this causes warnings about control flow integrity (KCFI) violations in clang-16 and higher: drivers/scsi/csiostor/csio_lnode.c:1098:33: error: cast from 'void (*)(struct csio_lnode *, enum csio_ln_ev)' to 'csio_sm_state_t' (aka 'void (*)(void *, unsigned int)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1098 | return (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/csiostor/csio_lnode.c:1369:29: error: cast from 'void (*)(struct csio_lnode *, enum csio_ln_ev)' to 'csio_sm_state_t' (aka 'void (*)(void *, unsigned int)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1369 | if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_uninit)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/csiostor/csio_lnode.c:1373:29: error: cast from 'void (*)(struct csio_lnode *, enum csio_ln_ev)' to 'csio_sm_state_t' (aka 'void (*)(void *, unsigned int)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1373 | if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_ready)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/csiostor/csio_lnode.c:1377:29: error: cast from 'void (*)(struct csio_lnode *, enum csio_ln_ev)' to 'csio_sm_state_t' (aka 'void (*)(void *, unsigned int)') converts to incompatible function type [-Werror,-Wcast-function-type-strict] 1377 | if (csio_get_state(ln) == ((csio_sm_state_t)csio_lns_offline)) { | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Move the enum into a shared header so the correct types can be used without the need for casts. Fixes: a3667aae ("[SCSI] csiostor: Chelsio FCoE offload driver") Signed-off-by: -
Colin Ian King authored
The variable 'mr' being assigned a value that is never read, the assignment is redundant and can be removed. Cleans up clang scan build warning: drivers/scsi/qla1280.c:2481:2: warning: Value stored to 'mr' is never read [deadcode.DeadStores] Signed-off-by:
-
- 13 Feb, 2024 2 commits
-
-
Ricardo B. Marliere authored
Since commit d492cc25 ("driver core: device.h: make struct bus_type a const *"), the driver core can properly handle constant struct bus_type, move the scsi_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Lukas Bulwahn authored
Commit 25a1f7a0 ("scsi: core: Add kunit tests for scsi_check_passthrough()") adds the config SCSI_LIB_KUNIT_TEST and corresponding tests. Due to naming confusion, the actual tests would only be included when the non-existing config SCSI_KUNIT_TEST is enabled (note this missing 'LIB' in the config name). So, they are basically dead right now. Adjust the name to actual existing config. Signed-off-by:
Lukas Bulwahn <lukas.bulwahn@gmail.com> Link: https://lore.kernel.org/r/20240207145603.15680-1-lukas.bulwahn@gmail.comReviewed-by:
Mike Christie <michael.christie@oracle.com> Signed-off-by:
-
- 06 Feb, 2024 19 commits
-
-
Ricardo B. Marliere authored
Now that the driver core can properly handle constant struct bus_type, move the tcm_loop_lld_bus variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Ricardo B. Marliere authored
Now that the driver core can properly handle constant struct bus_type, move the pseudo_lld_bus variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Ricardo B. Marliere authored
Now that the driver core can properly handle constant struct bus_type, move the iscsi_flashnode_bus variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
Lee Duncan <lduncan@suse.com> Reviewed-by:
-
Ricardo B. Marliere authored
Now that the driver core can properly handle constant struct bus_type, move the fcoe_bus_type variable to be a constant structure as well, placing it into read-only memory which can not be modified at runtime. Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Suggested-by:
-
Martin K. Petersen authored
Justin Tee <justintee8345@gmail.com> says: Update lpfc to revision 14.4.0.0 This patch set contains fixes identified by static code analyzers, updates to log messaging, bug fixes related to discovery and congestion management, and clean up patches regarding the abuse of shost lock in the driver. The patches were cut against Martin's 6.9/scsi-queue tree. Link: https://lore.kernel.org/r/20240131185112.149731-1-justintee8345@gmail.comSigned-off-by:
-
Justin Tee authored
Update copyrights to 2024 for files modified in the 14.4.0.0 patch set. Signed-off-by:
Justin Tee <justin.tee@broadcom.com> Link: https://lore.kernel.org/r/20240131185112.149731-18-justintee8345@gmail.comReviewed-by:
Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by:
-
Justin Tee authored
Update lpfc version to 14.4.0.0. Signed-off-by:
-
Justin Tee authored
In attempt to reduce the amount of unnecessary shost_lock acquisitions in the lpfc driver, change load_flag into an unsigned long bitmask and use clear_bit/test_bit bitwise atomic APIs instead of reliance on shost_lock for synchronization. Also, correct the test for FC_UNLOADING in lpfc_ct_handle_mibreq, which incorrectly tests vport->fc_flag rather than vport->load_flag. Signed-off-by:
-
Justin Tee authored
In attempt to reduce the amount of unnecessary shost_lock acquisitions in the lpfc driver, change fc_flag into an unsigned long bitmask and use clear_bit/test_bit bitwise atomic APIs instead of reliance on shost_lock for synchronization. Signed-off-by:
-
Justin Tee authored
In attempt to reduce the amount of unnecessary shost_lock acquisitions in the lpfc driver, replace shost_lock with an explicit fc_nodes_list_lock spinlock when accessing vport->fc_nodes lists. Although vport memory region is owned by shost->hostdata, it is driver private memory and an explicit fc_nodes list lock for fc_nodes list mutations is more appropriate than locking the entire shost. Signed-off-by:
-
Justin Tee authored
There is no reason to use the shost_lock to synchronize an LLDD statistics counter. Convert all the nlp state statistic counters into atomic_t. Corresponding zeroing, increments, and reads are converted to atomic versions. Signed-off-by:
-
Justin Tee authored
Desiring to reduce the amount of unnecessary shost_lock acquisitions in the lpfc driver, it has been determined that there is no need for shost_lock protection when retrieving fc_host port information because it is only for display to user via sysfs. Signed-off-by:
-
Justin Tee authored
The ACQE notification event to reset congestion statistics should be moved into the specific lpfc_sli4_async_sli_evt() routine instead of being processed from the generic lpfc_sli4_async_event_proc() routine. Signed-off-by:
-
Justin Tee authored
FPIN frequency is provided by the fabric in peer congestion notifications. Currently, the frequency is only logged in a message, but it should also be saved into the phba's cgn_fpin statistics member for proper application functionality. Signed-off-by:
-
Justin Tee authored
The "Nodelist not empty" log message and an accompanying delay may be observed when deleting an NPIV port or unloading the lpfc driver. This can occur due to receipt of an ABTS for which there is no corresponding login context or ndlp allocated. In such cases, the driver allocates a new ndlp object to send a BLS_RJT after which the ndlp object unintentionally remains in the NLP_STE_UNUSED_NODE state forever. Add a check to conditionally remove ndlp's initial reference count when queuing a BLS response. If the initial reference is removed, then set the NLP_DROPPED flag to notify other code paths. Signed-off-by:
-
Justin Tee authored
Requests to delete an NPIV port may fail repeatedly if the initial request is received during discovery. If the FC_UNLOADING load_flag is set, then skip CT response processing for the physical port. This allows discovery processing for other lpfc_vport objects to reach their cmpl routines before deleting the vport. Signed-off-by:
-
Justin Tee authored
Upon first RSCN receipt of a target server's remote port that is initially acting as an initiator function, the driver marks the ndlp->nlp_type as an initiator role. Then later, when processing an RSCN for a target function role switch, that ndlp remote port is permanently stuck as an initiator role and can never transition to be discovered as an updated target role function. Remove the NLP_RCV_PLOGI early return if statement clause so that the NLP_NPR_2B_DISC flag gets set. This allows for role change detections. Signed-off-by:
-
Justin Tee authored
Remove the early return NLP_FABRIC check in lpfc_plogi_confirm_nport() because it is possible for switch domain controllers to change WWPN. As a result, allow lpfc_plogi_confirm_nport() to detect that a new ndlp should be initialized in such cases. The old ndlp object will be cleaned up when dev_loss_tmo callbk executes. Signed-off-by:
-
Justin Tee authored
D_ID swaps are common during cable swaps in a SAN. Thus, there's no reason to log the event at a KERN_ERR level with the trace event logger. Change the log level to KERN_INFO and the normal LOG_ELS flag. Signed-off-by:
-
