- 14 Dec, 2013 17 commits
-
-
Rebecca Schultz Zavin authored
On some systems there is a performance benefit to reducing tlb pressure by minimizing the number of chunks in an allocation. Signed-off-by:
Rebecca Schultz Zavin <rebecca@android.com> [jstultz: modified patch to apply to staging directory] Signed-off-by:
John Stultz <john.stultz@linaro.org> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Rebecca Schultz Zavin authored
This patch adds cache maintenance operations to ion. As per mailing list discussions regarding dma_buf, cache operations are done implicitly. At buffer allocaiton time the user can select whether he'd like mappings (both kernel and user) to be cached. When cached mappings are selected, no mappings will be created for a buffer at mmap time. Instead pages will be faulted in one at a time so we can track which pages require flushing before dma. When the buffers are mapped for dma (via the dma_buf apis) any pages which were touched will be synced for device. Signed-off-by:
-
Laura Abbott authored
When mapping carveout buffers into userspace, only map the size of the vma given, not the full size of the buffer since clients may map less than the buffer size. Signed-off-by:
Laura Abbott <lauraa@codeaurora.org> [jstultz: modified patch to apply to staging directory] Signed-off-by:
-
Laura Abbott authored
When destroying a handle, all kernel mappings to that handle should be destroyed. Other handles may still have references and valid mappings to the buffer underneath which should not be destroyed. Loop on the handle reference count, not the buffer reference count to get rid of all kernel mappings for the handle. Signed-off-by:
-
Rebecca Schultz Zavin authored
Previously the ion_system_heap was using GFP_KERNEL, forcing all allocations to be in lowmem. This quickly causes us to run out of lowmem. Signed-off-by:
-
Rebecca Schultz Zavin authored
This patch sets the dma_address field of the sglist representing an allocation at allocation time. This technically breaks the dma api which states that these addresses should be set when a particular device takes ownership of a buffer via the dma_map apis. In the case of our systems the only dma address space is physical addresses. Additionally, we can not afford the overhead of calling dma_map_sg from this location as it implies a cache invalidate that is not necessary if the memory was previously mapped cached. Instead, the expectation is that memory being returned from the heaps is ready for dma in that if any cached mappings of that memory exist they have been invalidated. Signed-off-by:
-
Greg Hackmann authored
At least one map_dma() implementation (EXYNOS_CONTIG) assumes the fields are filled in Signed-off-by:
Greg Hackmann <ghackmann@google.com> [jstultz: modified patch to apply to staging directory] Signed-off-by:
-
Rebecca Schultz Zavin authored
This patch adds an interface to return and sg_table given a valid ion handle. Signed-off-by:
-
Rebecca Schultz Zavin authored
Rather than calling map_dma on the allocations dynamically, this patch switches to creating the sg_table at the time the buffer is created. This is necessary because in future updates the sg_table will be used for cache maintenance. Signed-off-by:
-
Rebecca Schultz Zavin authored
These ops were added in the 3.4 kernel. This patch adds support for them to ion. Previous ion_map/unmap_kernel api is also retained in addition to this new api. Signed-off-by:
-
Rebecca Schultz Zavin authored
With this change the ion_system_heap will only use kernel address space when the memory is mapped into the kernel (rare case). Signed-off-by:
-
Rebecca Schultz Zavin authored
Ion now uses dma-buf file descriptors to share buffers with userspace. Ion becomes a dma-buf exporter and any driver that can import dma-bufs can now import ion file descriptors. Signed-off-by:
-
KyongHo Cho authored
1. Verifying if the size of memory allocation in ion_alloc() is aligned by PAGE_SIZE at least. If it is not, this change makes the size to be aligned by PAGE_SIZE. 2. Unmaps all mappings to the kernel and DMA address spaces when destroying ion_buffer in ion_buffer_destroy(). This prevents leaks in those virtual address spaces. 3. Makes the return value of ion_alloc() to be explicit Linux error code when it fails to allocate a buffer. 4. Makes ion_alloc() implementation simpler. Removes 'goto' statement and relavant call to ion_buffer_put(). 5. Checks if the task is valid before calling put_task_struct() due to failure on creating a ion client in ion_client_create(). 6. Returns error when buffer allocation requested by userspace is failed. Signed-off-by:
KyongHo Cho <pullip.cho@samsung.com> [jstultz: modified patch to apply to staging directory] Signed-off-by:
-
Rebecca Schultz Zavin authored
Rather than requiring each platform call memblock_remove or reserve from the board file, add this to ion Signed-off-by:
-
Rebecca Schultz Zavin authored
Switch these api's from scatterlists to sg_tables Signed-off-by:
-
Colin Cross authored
__arch_ioremap is no longer available, use __arm_ioremap instead. Signed-off-by:
Colin Cross <ccross@android.com> [jstultz: modified patch to apply to staging directory] Signed-off-by:
-
Rebecca Schultz Zavin authored
Signed-off-by:
-
- 11 Dec, 2013 23 commits
-
-
H Hartley Sweeten authored
As pointed out by the kbuild test robot, and Ian Abbott, the dma >= 0 test is always true because dma is unsigned. This generates a warn message: drivers/staging/comedi/drivers/ni_at_a2150.c:715 a2150_attach() warn: always true condition '(dma >= 0) => (0-u32max >= 0)' Fix the test as suggested by Ian Abbott. Signed-off-by:
H Hartley Sweeten <hsweeten@visionengravers.com> Reported-by:
kbuild test robot <fengguang.wu@intel.com> Cc: Ian Abbott <abbotti@mev.co.uk> Signed-off-by:
-
Eli Billauer authored
The driver was forced to "module only" following a previous failure to build into the kernel. The problem was resolved several months ago. This has been successfully tested with "make allyesconfig" on x86_64. Reported-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
Eli Billauer <eli.billauer@gmail.com> Signed-off-by:
-
Malcolm Priestley authored
Signed-off-by:
Malcolm Priestley <tvboxspy@gmail.com> Signed-off-by:
-
Malcolm Priestley authored
byBBPreEDIndex value is initially 0, this means that from cold BBvUpdatePreEDThreshold is never set. This means that sensitivity may be in an ambiguous state, failing to scan any wireless points or at least distant ones. Signed-off-by:
-
Malcolm Priestley authored
Change s_vSaveTxPktInfo and BSSvUpdateNodeTxCounter to use vnt_tx_pkt_info relayed to BSSvUpdateNodeTxCounter via INTnsProcessData. pStatistic->abyTxPktInfo[byPktNum].byBroadMultiUni is unused and discarded. Signed-off-by:
-
Malcolm Priestley authored
Use netstats rx_packets and rx_frame_errors. Add frame errors to RXbBulkInProcessData The current scStatistic.RxFcsErrCnt only records USB errors not frame errors. The scStatistic.RxOkCnt only recorded successful USB transfers not actual successfully received packets. So a more accurate reading is to use netstats rx_packets and rx_frame_errors. Signed-off-by:
-
Malcolm Priestley authored
Calculate the qual from the tx_packets and wstats.discard.retries and apply to wstats.qual.qual Discard pDevice->scStatistic.LinkQuality. Signed-off-by:
-
Malcolm Priestley authored
Apply directly to net_device_stats and wireless stats. tx_bytes are relayed from s_vSaveTxPktInfo via scStatistic, so collect them there. All other statistics in STAvUpdateTDStatCounter are dead code and don't reach user. Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
ZHAO Gang <gamerh2o@gmail.com> Acked-by:
Mark Einon <mark.einon@gmail.com> Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
ZHAO Gang authored
Signed-off-by:
-
Paul Gortmaker authored
These serve no purpose at all, and can only mask real type clash issues that one would want to actually see. Signed-off-by:
Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by:
-
Mikhail Pershin authored
This is only part of the original Lustre tree commit. Main part of the original commit modifies server side code. Lustre-change: http://review.whamcloud.com/6765 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3467Signed-off-by:
Mikhail Pershin <mike.pershin@intel.com> Reviewed-by:
Alex Zhuravlev <alexey.zhuravlev@intel.com> Reviewed-by:
wangdi <di.wang@intel.com> Reviewed-by:
Oleg Drokin <oleg.drokin@intel.com> Signed-off-by:
Peng Tao <bergwolf@gmail.com> Signed-off-by:
Andreas Dilger <andreas.dilger@intel.com> Signed-off-by:
-
Mikhail Pershin authored
- Move OUT handler to the unified target code, so it can be used by both MDS and OST. Lustre-change: http://review.whamcloud.com/6763 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3467Signed-off-by:
-
JC Lafoucriere authored
Import creates a released file using new RAID pattern flag Import used a new ioctl() to implement the import in the client kernel. Lustre-change: http://review.whamcloud.com/6536 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3363Signed-off-by:
JC Lafoucriere <jacques-charles.lafoucriere@cea.fr> Reviewed-by:
Jinshan Xiong <jinshan.xiong@intel.com> [Fix up kuid_t/guid_t conversion in llite/file.c -- Peng Tao] Signed-off-by:
-
Doug Oucharek authored
This change adds a priority parameter to the route module settings. This paramter can be >= 0. Like hops, the lower the prioirty number the higher the priority. So lower numbered priorities will be selected over higher numbers. Lustre-change: http://review.whamcloud.com/5663 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2934Signed-off-by:
Doug Oucharek <doug.s.oucharek@intel.com> Reviewed-by:
Amir Shehata <amir.shehata@intel.com> Reviewed-by:
Isaac Huang <he.huang@intel.com> Reviewed-by:
-
Peng Tao authored
These macros are only used on server side. Cc: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by:
-
Nitin Cupta authored
This patch adds lots of comments and it will help others to review and enhance. Signed-off-by:
Seth Jennings <sjenning@linux.vnet.ibm.com> Signed-off-by:
Nitin Gupta <ngupta@vflare.org> Signed-off-by:
Minchan Kim <minchan@kernel.org> Signed-off-by:
-
Minchan Kim authored
Zsmalloc has two methods 1) copy-based and 2) pte based to access objects that span two pages. You can see history why we supported two approach from [1]. But it was bad choice that adding hard coding to select arch which want to use pte based method because there are lots of SoC in an architecure and they can have different cache size, CPU speed and so on so it would be better to expose it to user as selectable Kconfig option like Andrew Morton suggested. [1] https://lkml.org/lkml/2012/7/11/58Acked-by:
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by:
-
