Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

uio: msm_sharedmem: add guard page around shared memory

Browse source 
If guard_memory dtsi property is set, then the shared memory
region will be guarded by SZ_4K at the start and at the end.
This is needed to overcome the XPU limitation on few MSM HW,
so as to make this memory not contiguous with other allocations
that may possibly happen from other clients in the system.

Change-Id: I57637619cea8fe7f0f7254624e07177ea4a4fce0
Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
[riteshh@codeaurora.org: fixed trivial merge conflicts]
Signed-off-by: Ritesh Harjani <riteshh@codeaurora.org>
Signed-off-by: Ankit Jain <jankit@codeaurora.org>
This commit is contained in:
Sahitya Tummala 2017-10-05 14:39:40 +05:30 committed by Ankit Jain
parent 01e9a9ed18
commit 298212fa35
1 changed files with 20 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
drivers/uio/msm_sharedmem/msm_sharedmem.c
View file

@ -97,9 +97,11 @@ static int msm_sharedmem_probe(struct platform_device *pdev)
struct resource *clnt_res = NULL;
u32 client_id = ((u32)~0U);
u32 shared_mem_size = 0;
u32 shared_mem_tot_sz = 0;
void *shared_mem = NULL;
phys_addr_t shared_mem_pyhsical = 0;
bool is_addr_dynamic = false;
bool guard_memory = false;
/* Get the addresses from platform-data */
if (!pdev->dev.of_node) {
@ -134,13 +136,30 @@ static int msm_sharedmem_probe(struct platform_device *pdev)
if (shared_mem_pyhsical == 0) {
is_addr_dynamic = true;
shared_mem = dma_alloc_coherent(&pdev->dev, shared_mem_size,
/*
* If guard_memory is set, then the shared memory region
* will be guarded by SZ_4K at the start and at the end.
* This is needed to overcome the XPU limitation on few
* MSM HW, so as to make this memory not contiguous with
* other allocations that may possibly happen from other
* clients in the system.
*/
guard_memory = of_property_read_bool(pdev->dev.of_node,
"qcom,guard-memory");
shared_mem_tot_sz = guard_memory ? shared_mem_size + SZ_8K :
shared_mem_size;
shared_mem = dma_alloc_coherent(&pdev->dev, shared_mem_tot_sz,
&shared_mem_pyhsical, GFP_KERNEL);
if (shared_mem == NULL) {
pr_err("Shared mem alloc client=%s, size=%u\n",
clnt_res->name, shared_mem_size);
return -ENOMEM;
}
if (guard_memory)
shared_mem_pyhsical += SZ_4K;
}
/* Set up the permissions for the shared ram that was allocated. */