summaryrefslogtreecommitdiff
path: root/drivers/staging/fsl_qbman
AgeCommit message (Collapse)Author
2013-09-17Merge branch 'b4860rev2' into sdk-v1.4.xJ. German Rivera
2013-09-16Fix USDPAA dma_mem allocator when blocks needed to be splitRoy Pledge
Also rework the fragment management to eliminate fragmentation Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: Ieb1aaf3b7d7e3d42b78efe2411952f10bbd2803d Reviewed-on: http://git.am.freescale.net:8181/4774 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Rivera Jose-B46482 <German.Rivera@freescale.com>
2013-09-10fsl_qman: Fix flipping of CSCI interrupt bitBogdan Hamciuc
Commit 88d4c504 "fsl_qman: implement CEETM CCSCI and update some ccg APIs" inadvertently flips the QM_PIRQ_CSCI bit, reactivating a bug which allowed congestion state to become irreversible because of a missed interrupt. Clearing the CSCI bit puts the system back on track. Signed-off-by: Bogdan Hamciuc <bogdan.hamciuc@freescale.com> Change-Id: I18ffa06a694911567a7a690c7a7aa1e7b4cd85b9 Reviewed-on: http://git.am.freescale.net:8181/3031 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-09-10fsl_qman: Fix flipping of CSCI interrupt bitBogdan Hamciuc
Commit 88d4c504 "fsl_qman: implement CEETM CCSCI and update some ccg APIs" inadvertently flips the QM_PIRQ_CSCI bit, reactivating a bug which allowed congestion state to become irreversible because of a missed interrupt. Clearing the CSCI bit puts the system back on track. Signed-off-by: Bogdan Hamciuc <bogdan.hamciuc@freescale.com> Change-Id: I18ffa06a694911567a7a690c7a7aa1e7b4cd85b9 Reviewed-on: http://git.am.freescale.net:8181/3031 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-09-03Removed dump_frag() duplicate definitionJ. German Rivera
2013-08-30Merge branch 'b4860rev2' into sdk-v1.4.xJ. German Rivera
2013-08-28fsl_qman: fix the incorrect return for xsfdr read in debugfsHaiying Wang
and fix the mask value for correctly getting the XSFDR value. Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: I72ba857bd01b93ca6042e354c7ca8c391f430e83 Reviewed-on: http://git.am.freescale.net:8181/4059 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Rivera Jose-B46482 <German.Rivera@freescale.com>
2013-08-27Merge branch 'b4860rev2' into sdk-v1.4.xJ. German Rivera
2013-08-26Modify USDPAA DMA mapping code to allow non power of 4 mappingsRoy Pledge
This patch modifies the USDPAA code to allow non power of 4 DMA maps. The code will use multiple TLB1 entries if needed. DMA maps are still phyically and virually contiguous. Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I42942067059a3c06f0b0d031d266d228295c7c45 Reviewed-on: http://git.am.freescale.net:8181/3857 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Rivera Jose-B46482 <Jose.G.Rivera@freescale.com>
2013-08-26Add API to allocate specific portals based on index. This allows an ↵Roy Pledge
application to get back the exact portal it was previously using by specifing the portals index value. Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I8233816f0519731eb65b3671d68a01266eee42dd Reviewed-on: http://git.am.freescale.net:8181/4002 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Rivera Jose-B46482 <Jose.G.Rivera@freescale.com>
2013-08-26Make stash id and operation mapping index per window attributes.Varun Sethi
Stash ID and operation mapping can now be set per dma window. Signed-off-by: Varun Sethi <Varun.Sethi@freescale.com> Change-Id: I987abbcba0575fea1b43843c2bce342f4eae4df2 Reviewed-on: http://git.am.freescale.net:8181/3439 Reviewed-by: Yoder Stuart-B08248 <stuart.yoder@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Conflicts: drivers/iommu/fsl_pamu.c drivers/iommu/fsl_pamu.h drivers/iommu/fsl_pamu_domain.c
2013-08-15Modify USDPAA DMA mapping code to allow non power of 4 mappingsRoy Pledge
This patch modifies the USDPAA code to allow non power of 4 DMA maps. The code will use multiple TLB1 entries if needed. DMA maps are still phyically and virually contiguous. Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I42942067059a3c06f0b0d031d266d228295c7c45 Reviewed-on: http://git.am.freescale.net:8181/3857 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Rivera Jose-B46482 <Jose.G.Rivera@freescale.com>
2013-08-15Add API to allocate specific portals based on index.Roy Pledge
This allows an application to get back the exact portal it was previously using by specifing the portals index value. Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I8233816f0519731eb65b3671d68a01266eee42dd Reviewed-on: http://git.am.freescale.net:8181/4002 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Rivera Jose-B46482 <Jose.G.Rivera@freescale.com>
2013-08-10qman: Add CI-stashing support for QMan rev3.0 or laterHaiying Wang
Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: Icda6a8547559ab45ceea7160cde566ca022e92e8 Reviewed-on: http://git.am.freescale.net:8181/3698 Reviewed-by: Schmitt Richard-B43082 <B43082@freescale.com> Tested-by: Schmitt Richard-B43082 <B43082@freescale.com>
2013-08-10qman: remove eqcr_cmodeGeoff Thorpe
It was unused, and confusing efforts to implement support for EQCR_CI-stashing. Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Change-Id: Ia390a4b4b54efba60b4e9b12a73b7d1ec88bf530 Reviewed-on: http://git.am.freescale.net:8181/3697 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Schmitt Richard-B43082 <B43082@freescale.com>
2013-07-24Merge remote-tracking branch 'fsl_devel/b4860rev2' into sdk1.4Andy Fleming
2013-07-24Make stash id and operation mapping index per window attributes.Varun Sethi
Stash ID and operation mapping can now be set per dma window. Signed-off-by: Varun Sethi <Varun.Sethi@freescale.com> Change-Id: I987abbcba0575fea1b43843c2bce342f4eae4df2 Reviewed-on: http://git.am.freescale.net:8181/3439 Reviewed-by: Yoder Stuart-B08248 <stuart.yoder@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-07-23Set SDQCR to ensure frame queues can reach the retired stateRoy Pledge
In some situations frame queues may still be on a work queue when a retirement command is sent during cleanup. In order to reach the retired state these frame queues must be scheduled. This patch sets an appropriate SDQCR value to ensure that the Frame Queue is scheduled. Since Frame Queues could be 'locked' to a particular portal if the Hold Active feature is enabled the shutrown routine must service all portals to ensure that the FQ reaches a retired state Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I97f79d35c62f179f21b6bd11c23bc0150e54ff5f Reviewed-on: http://git.am.freescale.net:8181/3339 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-29fsl_bman: remove the extra kmalloc which causes memleakHaiying Wang
because the later pointer assignments overwrite the results of the kmalloc. This memleak can be detect after turning on kernel memleak detector. Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: If21cc0f8084271d9fe6f73e51dd3ad200ebdad67 Reviewed-on: http://git.am.freescale.net:8181/2747 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Pledge Roy-R01356 <roy.pledge@freescale.com> Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-24fsl_qbman: initialise structures to zeroJeffrey Ladouceur
The cgr and cgrd are passed as parameters to the qman_query_cgr api. Initialise to all zero before using them. Signed-off-by: Jeffrey Ladouceur <Jeffrey.Ladouceur@freescale.com> Change-Id: I3a6c3fdb0107ded82aec61842ae6463d4849512c Reviewed-on: http://git.am.freescale.net:8181/2680 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-17qman: use math64 instead of direct 64-bit division.Haiying Wang
In 32-bit builds, the ROUNDING macro was breaking kernel assumptions when fed with 64-bit parameters. This forces it to use the recommended wrappers in <linux/math64.h> instead. Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Change-Id: Id708cdad58593f38683112adf59984ffd3d763f7 Reviewed-on: http://git.am.freescale.net:8181/2580 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-16fsl_qbman: remove stale (and unused) stubGeoff Thorpe
Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Change-Id: I3e47ac16f9d119194aeb15da1186d6038f33f722 Reviewed-on: http://git.am.freescale.net:8181/2530 Tested-by: Review Code-CDREVIEW <CDREVIEW@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-15Fix USDPAA IRQ handling to work correctly in 32 bit modeRoy Pledge
Also properly respect the NONBLOCK flag in the read() API Make sure IRQ is properly inhibited in the IRQ handler Create a dependancy between USDPAA and USDPAA_IRQ file pointers Change-Id: Idc0c33c8448a402d5d127e7e4e22e629dbfa5912 Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Reviewed-on: http://git.am.freescale.net:8181/2310 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-15Fix pool channel ID checking so it works based on the globalRoy Pledge
pool channel ID variable Signed-off-by: Roy Pledge <Roy.Pledge@freescale.com> Change-Id: I076964896bd1a54cf72aa16a25270a978c7d73d3 Reviewed-on: http://git.am.freescale.net:8181/2493 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-05-10fsl_qbman: fix the non-SMP buildGeoff Thorpe
The <linux/smp.h> header only includes <asm/smp.h> if CONFIG_SMP is defined, yet it is required in the non-SMP case too. Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Change-Id: I0644bca53a0afeb3eb331956f7e4b20959f2a3d6 Reviewed-on: http://git.am.freescale.net:8181/2419 Reviewed-by: Wood Scott-B07421 <scottwood@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-24Fix USDPAA memory mappings so they can no longer occur at address 0Roy Pledge
which confused any SW checking for NULL pointers Change-Id: Ic0ac5e61f1776ce8d4ddb622e401942ce2750705 Reviewed-on: http://git.am.freescale.net:8181/2062 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-24squash! fsl_qman: Set stashing using the IOMMU APIEmil Medve
Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com> Change-Id: I60be3c3f94f50fca47a53328a70a552b74808ad1 Reviewed-on: http://git.am.freescale.net:8181/1772 Reviewed-by: Yoder Stuart-B08248 <stuart.yoder@freescale.com> Reviewed-by: Pledge Roy-R01356 <roy.pledge@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-23fsl_qbman: Enable preemption in bman_create_affine_portal()Priyanka Jain
bman_create_affine_portal() calls bman_create_portal() which in turn calls request_irq() to register portal_isr. In case of PREEMPT_RT enabled, request_irq() is converted into request_threaded_irq() as portal_isr is threaded IRQ handler. But this request_threaded_irq() can sleep, so it is mandatory to call request_threaded_irq() only from context that can sleep. bman_create_affine_portal() is called from context that is already affine to CPU or in other words this is non-migratable to other CPUs. Hence, it is not required to run this function in non-preemptible context. Enabling preemption will allow subsequent functions to sleep. Call put_affine_portal() on entry i.e. before calling bman_create_portal() to enable preemption. Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com> Fixes CQ: ENGR00259733 kernel crash in bman_init when PREEMPT_RT is enabled Change-Id: I628b6fbc986a5bd980ffa68af4fd1ec7a2661758 Reviewed-on: http://git.am.freescale.net:8181/1717 Reviewed-by: Medve Emilian-EMMEDVE1 <Emilian.Medve@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-22Revert "ASF-QOS: Adding API to configure QMAN Scheduler via ASF"Fleming Andrew-AFLEMING
This reverts commit 5f2780e55e6885e1b89c28fc23f998a27a26d455 I must have grabbed this one by accident. A proper solution needs to be discussed. Change-Id: I276218aef9ea663d183a1233d79bf303e2113360 Reviewed-on: http://git.am.freescale.net:8181/1703 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-19fsl_qman: add debugfs support for query some ceetm featuresHaiying Wang
Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: I344f564af3cad4d46a1437559ece080dfef59cd2 Reviewed-on: http://git.am.freescale.net:8181/1639 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-18ASF-QOS: Adding API to configure QMAN Scheduler via ASFSachin Saxena
- API shall be defined & Exported only when ASF QOS is in use Change-Id: I026b34d6dec70f70cf44bcaa23573c18ff457b19 Signed-off-by: Sachin Saxena <sachin.saxena@freescale.com> Reviewed-on: http://git.am.freescale.net:8181/1378 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-18Cleanup USDPAA resources when a process exitsRoy Pledge
Add an API to query the usage levels of DMA memory Elminates UIO and converts USDPAA to interact with the kernel via a character devicc Removed misc/devices fsl_usdpaa file Remove unneeded file Change-Id: I797548e2c79f7098e6378484bcae2b455f022cd4 Reviewed-on: http://git.am.freescale.net:8181/1546 Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Wang Haiying-R54964 <Haiying.Wang@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-16fsl_qman: Add QMan3.1 reversion supportHaiying Wang
The QMan revision on both T4240 and B4860 rev2 silicon is 3.1, and both T2080 and T1040 also have QMan rev3.1. Update the qman driver to support rev3.1. Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: I7ea2149f982023cd5f99729df6c6b61cba46b668 Reviewed-on: http://git.am.freescale.net:8181/1261 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-16fsl_qman: some fixes for CEETM APIsHaiying Wang
- Fix the parameter order in disable ceetm mode of sp. - Alloc memory for CQ after confirming CQ is available for group CQs - Check prio_b to be non-zero if group_b is set. - Use object qm_ceetm_weight_code to convert wbfs and ratio. - Adjust weight code index from W8 to W15 in set/get queue weight - Fix the byte_cnt field of ceetm statistics counter Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: I28e4978e1cc13957e64dd6f0e376d239d1161933 Reviewed-on: http://git.am.freescale.net:8181/1260 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-16fsl_qman: implement CEETM CCSCI and update some ccg APIsHaiying Wang
The CEETM congestion state change notification uses a seperate bit for CSCN interrupt in software portal's ISR register, and different command to query congestion state. This patch implmentes the CCSCI interrupt handling, and combines the ccg's swp setting into qman_ceetm_ccg_set(), because we can only register ccgr callback to the affine portal. Signed-off-by: Haiying Wang <Haiying.Wang@freescale.com> Change-Id: I246bd70ea33786d39b6a18ae90e03f9fa09c3912 Reviewed-on: http://git.am.freescale.net:8181/1259 Reviewed-by: Thorpe Geoff-R01361 <Geoff.Thorpe@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-16fsl_qman: use a single CGR list per-portal, not 256Haiying Wang
CGR objects registered against a portal can receive CSCN notifications via that portal, and this supports the existence of there being more than one CGR object for the same CGRID (eg. two distinct drivers using the same portal and using FQs that are subscribed to the same CGR). The portal code was previously using a distinct list of registered CGRs for every possible CGRID, ie. a 256-element array of lists! This meant that when CSCN interrupts occurred and a 256-bit mask was calculated indicating which CGRIDs had changed state, we would iterate that bitmask and for each CGRID that had changed, we would iterate the corresponding list from the array, invoking callbacks for all CGR objects. Now, we just use a singe list for all CGRs, irrespective of CGRID. Rather than iterating the bitmask by CGRID and, for each CGRID that had a state-change, iterating the corresponding CGR list to invoke callbacks, we now just iterate the single CGR list and for each CGR with a callback, we check the bit in the bitmask corresponding to the CGRID to determine whether to invoke the callback. This is a more efficient use of memory (the 256-element array of lists used 2KB per portal on 32-bit cores, 4KB on 64-bit), and the code becomes simpler. And the "downside" doesn't occur, because there are never more than a small handful of CGR objects per portal at most, and quite often only one or two (or even none). So a single list is probably as efficient or even better in the conventional use cases, and much less wasteful of space. Furthermore, this logic will be extended for CEETM CCGRs, of which there are many more than for regular CGRs. So without this change, the extensions for CEETM would continue the previous bad approach, but with 2 or 4 times the unwelcome footprint. Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Change-Id: I00ff60edf191aabc9105c0b49e7437fad085f7dc Reviewed-on: http://git.am.freescale.net:8181/1258 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-10fsl_qman: Set stashing using the IOMMU APIEmil Medve
This is using thew new PAMU driver This integration uses a *horrible hack* in order to provide the IOMMU/PAMU driver with a 'struct device'. Making the QMan portal driver nice and proper is part of the upstreaming effort Change-Id: I5f03a3b662949162bff7ac8c7b14ad5fbc0394ce Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com> Change-Id: Ic66bb3904ffa537e497ba00c67e22d851087b435 Reviewed-on: http://git.am.freescale.net:8181/1173 Reviewed-by: Ladouceur Jeffrey-R11498 <Jeffrey.Ladouceur@freescale.com> Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-10fsl_qman: Remove integration code with the old platform PAMU driverEmil Medve
This is to make the ingration patch with the new IOMMU/PAMU driver more readable Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com> Change-Id: Ia8c2acef2f09d0dcbce47cc14f6f9dfbf1f55370 Reviewed-on: http://git.am.freescale.net:8181/1172 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-10fsl_bman: Make bpool depletion test output more readableEmil Medve
In case of depletion, the current output contains the BPID both as a number and as a mask, with the non-zero 'mask' conveying depletion on the respective bpool. Is less confusing to just use a binary/boolean value for displaying the depletion status of a bpool Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com> Change-Id: Idbab2fa2701405beb6f04327ea199377b36aea73 Reviewed-on: http://git.am.freescale.net:8181/1171 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-03qman: Temporary fix for broken PAMU supportAndy Fleming
Change-Id: I49eb1d51209d0df92e3d4add8854c40b31d1a7c2 Signed-off-by: Andy Fleming <afleming@freescale.com> Reviewed-on: http://git.am.freescale.net:8181/971 Reviewed-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com> Tested-by: Fleming Andrew-AFLEMING <AFLEMING@freescale.com>
2013-04-02fsl_qbman: Export unused portals as UIO devicesGeoff Thorpe
Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com>
2013-04-02fsl_qbman: Add drivers for the Freescale DPAA Q/BManGeoff Thorpe
Signed-off-by: Geoff Thorpe <Geoff.Thorpe@freescale.com> Signed-off-by: Bharat Bhushan <Bharat.Bhushan@freescale.com> Signed-off-by: Bogdan Hamciuc <bogdan.hamciuc@freescale.com> Signed-off-by: Hai-Ying Wang <Haiying.Wang@freescale.com> Signed-off-by: Jeffrey Ladouceur <jeffrey.ladouceur@freescale.com> Signed-off-by: Jia-Fei Pan <Jiafei.Pan@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org> Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com> Signed-off-by: Vakul Garg <vakul@freescale.com> Signed-off-by: Emil Medve <Emilian.Medve@Freescale.com>
generated by cgit v0.10.2 at 2024-08-08 08:26:42 (GMT)