- 14 Dec, 2015 18 commits
-
-
Aneesh Kumar K.V authored
Convert from asm to C Acked-by:
Scott Wood <scottwood@freescale.com> Signed-off-by:
Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au>
-
Aneesh Kumar K.V authored
No real change, only style changes Acked-by:
-
Aneesh Kumar K.V authored
Signed-off-by:
-
Aneesh Kumar K.V authored
This free up 11 bits in pte_t. In the later patch we also change the pte_t format so that we can start supporting migration pte at pmd level. We now track 4k subpage valid bit as below If we have _PAGE_COMBO set, we override the _PAGE_F_GIX_SHIFT and _PAGE_F_SECOND. Together we have 4 bits, each of them used to indicate whether any of the 4 4k subpage in that group is valid. ie, [ group 1 bit ] [ group 2 bit ] ..... [ group 4 ] [ subpage 1 - 4] [ subpage 5- 8] ..... [ subpage 13 - 16] We still track each 4k subpage slot number and secondary hash information in the second half of pgtable_t. Removing the subpage tracking have some significant overhead on aim9 and ebizzy benchmark and to support THP with 4K subpage, we do need a pgtable_t of 4096 bytes. Signed-off-by:
-
Aneesh Kumar K.V authored
We should not expect pte bit position in asm code. Simply by moving part of that to C Acked-by:
-
Aneesh Kumar K.V authored
Acked-by:
-
Aneesh Kumar K.V authored
Move the booke related headers below booke/32 or booke/64 Acked-by:
-
Aneesh Kumar K.V authored
functions which operate on pte bits are moved to hash*.h and other generic functions are moved to pgtable.h Acked-by:
-
Aneesh Kumar K.V authored
This enables us to keep hash64 related bits together, and makes it easy to follow. Acked-by:
-
Aneesh Kumar K.V authored
We convert them static inline function here as we did with pte_val in the previous patch Acked-by:
-
Aneesh Kumar K.V authored
We also convert few #define to static inline in this patch for better type checking Acked-by:
-
Aneesh Kumar K.V authored
We copy only needed PTE bits define from pte-common.h to respective hash related header. This should greatly simply later patches in which we are going to change the pte format for hash config Acked-by:
-
Aneesh Kumar K.V authored
We are going to drop pte_common.h in the later patch. The idea is to enable hash code not require to define all PTE bits. Having PTE bits defined in pte_common.h made the code unnecessarily complex. Acked-by:
-
Aneesh Kumar K.V authored
We also move __ASSEMBLY__ towards the end of header. This avoid having #ifndef __ASSEMBLY___ all over the header Acked-by:
-
Aneesh Kumar K.V authored
This further make a copy of pte defines to book3s/64/hash*.h. This remove the dependency on pgtable-ppc64-4k.h and pgtable-ppc64-64k.h Acked-by:
-
Aneesh Kumar K.V authored
In this patch we do: cp pgtable-ppc32.h book3s/32/pgtable.h cp pgtable-ppc64.h book3s/64/pgtable.h This enable us to do further changes to hash specific config. We will change the page table format for 64bit hash in later patches. Acked-by:
-
Aneesh Kumar K.V authored
Acked-by:
-
Aneesh Kumar K.V authored
This is the same bug we fixed as part of 09567e7f ("powerpc/mm: Check paca psize is up to date for huge mappings"). Please check that for details. The difference here is that faults were happening on a 4K page at an address previously mapped by hugetlb. Signed-off-by:
Anshuman Khandual <khandual@linux.vnet.ibm.com> Signed-off-by:
-
- 10 Dec, 2015 3 commits
-
-
Anton Blanchard authored
Two DSCR tests have a hack in them: /* * XXX: Force a context switch out so that DSCR * current value is copied into the thread struct * which is required for the child to inherit the * changed value. */ sleep(1); We should not be working around this in the testcase, it is a kernel bug. Fix it by copying the current DSCR to the child, instead of what we had in the thread struct at last context switch. Signed-off-by:
Anton Blanchard <anton@samba.org> Signed-off-by:
-
Anton Blanchard authored
commit 152d523e ("powerpc: Create context switch helpers save_sprs() and restore_sprs()") moved the restore of SPRs after the call to _switch(). There is an issue with this approach - new tasks do not return through _switch(), they are set up by copy_thread() to directly return through ret_from_fork() or ret_from_kernel_thread(). This means restore_sprs() is not getting called for new tasks. Fix this by moving restore_sprs() before _switch(). Fixes: 152d523e ("powerpc: Create context switch helpers save_sprs() and restore_sprs()") Signed-off-by:
-
Anton Blanchard authored
Commit a0e72cf1 ("powerpc: Create msr_check_and_{set,clear}()") removed a call to check_if_tm_restore_required() in the enable_kernel_*() functions. Add them back in. Fixes: a0e72cf1 ("powerpc: Create msr_check_and_{set,clear}()") Reported-by:
Rashmica Gupta <rashmicy@gmail.com> Signed-off-by:
-
- 02 Dec, 2015 4 commits
-
-
Anton Blanchard authored
Remove a bunch of unnecessary fallback functions and group things in a more logical way. Signed-off-by:
-
Anton Blanchard authored
Most of __switch_to() is housekeeping, TLB batching, timekeeping etc. Move these away from the more complex and critical context switching code. Signed-off-by:
-
Anton Blanchard authored
Create a single function that flushes everything (FP, VMX, VSX, SPE). Doing this all at once means we only do one MSR write. Signed-off-by:
-
Anton Blanchard authored
Create a single function that gives everything up (FP, VMX, VSX, SPE). Doing this all at once means we only do one MSR write. A context switch microbenchmark using yield(): http://ozlabs.org/~anton/junkcode/context_switch2.c ./context_switch2 --test=yield --fp --altivec --vector 0 0 shows an improvement of 3% on POWER8. Signed-off-by:
-
- 01 Dec, 2015 15 commits
-
-
Anton Blanchard authored
More consolidation of our MSR available bit handling. Signed-off-by:
-
Anton Blanchard authored
Add a boot option that strictly manages the MSR unavailable bits. This catches kernel uses of FP/Altivec/SPE that would otherwise corrupt user state. Signed-off-by:
-
Anton Blanchard authored
The enable_kernel_*() functions leave the relevant MSR bits enabled until we exit the kernel sometime later. Create disable versions that wrap the kernel use of FP, Altivec VSX or SPE. While we don't want to disable it normally for performance reasons (MSR writes are slow), it will be used for a debug boot option that does this and catches bad uses in other areas of the kernel. Signed-off-by:
-
Anton Blanchard authored
Create helper functions to set and clear MSR bits after first checking if they are already set. Grouping them will make it easy to avoid the MSR writes in a subsequent optimisation. Signed-off-by:
-
Anton Blanchard authored
With the recent change to enable_kernel_vsx(), we no longer need to call enable_kernel_fp() and enable_kernel_altivec(). Signed-off-by:
-
Anton Blanchard authored
Move the MSR modification into c. Removing it from the assembly function will allow us to avoid costly MSR writes by batching them up. Check the FP and VMX bits before calling the relevant giveup_*() function. This makes giveup_vsx() and flush_vsx_to_thread() perform more like their sister functions, and allows us to use flush_vsx_to_thread() in the signal code. Move the check_if_tm_restore_required() check in. Signed-off-by:
-
Anton Blanchard authored
Move the MSR modification into new c functions. Removing it from the low level functions will allow us to avoid costly MSR writes by batching them up. Move the check_if_tm_restore_required() check into these new functions. Signed-off-by:
-
Anton Blanchard authored
We used to allow giveup_*() to be called with a NULL task struct pointer. Now those cases are handled in the caller we can remove the checks. We can also remove giveup_altivec_notask() which is also unused. Signed-off-by:
-
Anton Blanchard authored
mtmsrd_isync() will do an mtmsrd followed by an isync on older processors. On newer processors we avoid the isync via a feature fixup. Signed-off-by:
-
Anton Blanchard authored
Instead of having multiple giveup_*_maybe_transactional() functions, separate out the TM check into a new function called check_if_tm_restore_required(). This will make it easier to optimise the giveup_*() functions in a subsequent patch. Signed-off-by:
-
Anton Blanchard authored
The UP only lazy floating point and vector optimisations were written back when SMP was not common, and neither glibc nor gcc used vector instructions. Now SMP is very common, glibc aggressively uses vector instructions and gcc autovectorises. We want to add new optimisations that apply to both UP and SMP, but in preparation for that remove these UP only optimisations. Signed-off-by:
-
Anton Blanchard authored
No need to execute mflr twice. Signed-off-by:
-
Anton Blanchard authored
Move all our context switch SPR save and restore code into two helpers. We do a few optimisations: - Group all mfsprs and all mtsprs. In many cases an mtspr sets a scoreboarding bit that an mfspr waits on, so the current practise of mfspr A; mtspr A; mfpsr B; mtspr B is the worst scheduling we can do. - SPR writes are slow, so check that the value is changing before writing it. A context switch microbenchmark using yield(): http://ozlabs.org/~anton/junkcode/context_switch2.c ./context_switch2 --test=yield 0 0 shows an improvement of almost 10% on POWER8. Signed-off-by:
-
Anton Blanchard authored
Similar to the non TM load_up_*() functions, don't disable the MSR bits on the way out. Signed-off-by:
-
Anton Blanchard authored
Writing the MSR is slow, so we want to avoid it whenever possible. A subsequent patch will add a debug option that strictly manages the FP/VMX/VSX unavailable bits. For now just remove it, matching what we do in other areas of the kernel (eg enable_kernel_altivec()). A context switch microbenchmark using yield(): http://ozlabs.org/~anton/junkcode/context_switch2.c ./context_switch2 --test=yield --fp 0 0 shows an improvement of almost 3% on POWER8. Signed-off-by:
-
