diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 20:15:40 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-07 20:15:40 +0300 |
commit | bac65d9d87b383471d8d29128319508d71b74180 (patch) | |
tree | c087cca1f1db1045cce08a3bff7c775c66e437bf /arch/powerpc/lib/ldstfp.S | |
parent | f92e3da18b7d5941468040af962c201235148301 (diff) | |
parent | 265601f034df3566f22da11240977aab8860f6a7 (diff) | |
download | linux-bac65d9d87b383471d8d29128319508d71b74180.tar.xz |
Merge tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Nothing really major this release, despite quite a lot of activity.
Just lots of things all over the place.
Some things of note include:
- Access via perf to a new type of PMU (IMC) on Power9, which can
count both core events as well as nest unit events (Memory
controller etc).
- Optimisations to the radix MMU TLB flushing, mostly to avoid
unnecessary Page Walk Cache (PWC) flushes when the structure of the
tree is not changing.
- Reworks/cleanups of do_page_fault() to modernise it and bring it
closer to other architectures where possible.
- Rework of our page table walking so that THP updates only need to
send IPIs to CPUs where the affected mm has run, rather than all
CPUs.
- The size of our vmalloc area is increased to 56T on 64-bit hash MMU
systems. This avoids problems with the percpu allocator on systems
with very sparse NUMA layouts.
- STRICT_KERNEL_RWX support on PPC32.
- A new sched domain topology for Power9, to capture the fact that
pairs of cores may share an L2 cache.
- Power9 support for VAS, which is a new mechanism for accessing
coprocessors, and initial support for using it with the NX
compression accelerator.
- Major work on the instruction emulation support, adding support for
many new instructions, and reworking it so it can be used to
implement the emulation needed to fixup alignment faults.
- Support for guests under PowerVM to use the Power9 XIVE interrupt
controller.
And probably that many things again that are almost as interesting,
but I had to keep the list short. Plus the usual fixes and cleanups as
always.
Thanks to: Alexey Kardashevskiy, Alistair Popple, Andreas Schwab,
Aneesh Kumar K.V, Anju T Sudhakar, Arvind Yadav, Balbir Singh,
Benjamin Herrenschmidt, Bhumika Goyal, Breno Leitao, Bryant G. Ly,
Christophe Leroy, Cédric Le Goater, Dan Carpenter, Dou Liyang,
Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff Levand, Hannes
Reinecke, Haren Myneni, Ivan Mikhaylov, John Allen, Julia Lawall,
LABBE Corentin, Laurentiu Tudor, Madhavan Srinivasan, Markus Elfring,
Masahiro Yamada, Matt Brown, Michael Neuling, Murilo Opsfelder Araujo,
Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran,
Paul Mackerras, Rashmica Gupta, Rob Herring, Rui Teng, Sam Bobroff,
Santosh Sivaraj, Scott Wood, Shilpasri G Bhat, Sukadev Bhattiprolu,
Suraj Jitindar Singh, Tobin C. Harding, Victor Aoqui"
* tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (321 commits)
powerpc/xive: Fix section __init warning
powerpc: Fix kernel crash in emulation of vector loads and stores
powerpc/xive: improve debugging macros
powerpc/xive: add XIVE Exploitation Mode to CAS
powerpc/xive: introduce H_INT_ESB hcall
powerpc/xive: add the HW IRQ number under xive_irq_data
powerpc/xive: introduce xive_esb_write()
powerpc/xive: rename xive_poke_esb() in xive_esb_read()
powerpc/xive: guest exploitation of the XIVE interrupt controller
powerpc/xive: introduce a common routine xive_queue_page_alloc()
powerpc/sstep: Avoid used uninitialized error
axonram: Return directly after a failed kzalloc() in axon_ram_probe()
axonram: Improve a size determination in axon_ram_probe()
axonram: Delete an error message for a failed memory allocation in axon_ram_probe()
powerpc/powernv/npu: Move tlb flush before launching ATSD
powerpc/macintosh: constify wf_sensor_ops structures
powerpc/iommu: Use permission-specific DEVICE_ATTR variants
powerpc/eeh: Delete an error out of memory message at init time
powerpc/mm: Use seq_putc() in two functions
macintosh: Convert to using %pOF instead of full_name
...
Diffstat (limited to 'arch/powerpc/lib/ldstfp.S')
-rw-r--r-- | arch/powerpc/lib/ldstfp.S | 299 |
1 files changed, 85 insertions, 214 deletions
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index a58777c1b2cb..ae15eba49c1f 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -21,27 +21,19 @@ #define STKFRM (PPC_MIN_STKFRM + 16) - .macro inst32 op -reg = 0 - .rept 32 -20: \op reg,0,r4 - b 3f - EX_TABLE(20b,99f) -reg = reg + 1 - .endr - .endm - -/* Get the contents of frN into fr0; N is in r3. */ +/* Get the contents of frN into *p; N is in r3 and p is in r4. */ _GLOBAL(get_fpr) mflr r0 + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* fr0 is already in fr0 */ - nop -reg = 1 - .rept 31 - fmr fr0,reg - blr +reg = 0 + .rept 32 + stfd reg, 0(r4) + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -49,18 +41,23 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr +2: MTMSRD(r6) + isync + blr -/* Put the contents of fr0 into frN; N is in r3. */ +/* Put the contents of *p into frN; N is in r3 and p is in r4. */ _GLOBAL(put_fpr) mflr r0 + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* fr0 is already in fr0 */ - nop -reg = 1 - .rept 31 - fmr reg,fr0 - blr +reg = 0 + .rept 32 + lfd reg, 0(r4) + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -68,127 +65,24 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr - -/* Load FP reg N from float at *p. N is in r3, p in r4. */ -_GLOBAL(do_lfs) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) -1: li r9,-EFAULT -2: lfs fr0,0(r4) - li r9,0 -3: bl put_fpr - beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Load FP reg N from double at *p. N is in r3, p in r4. */ -_GLOBAL(do_lfd) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) -1: li r9,-EFAULT -2: lfd fr0,0(r4) - li r9,0 -3: beq cr7,4f - bl put_fpr - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) +2: MTMSRD(r6) isync - mr r3,r9 - addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) -/* Store FP reg N to float at *p. N is in r3, p in r4. */ -_GLOBAL(do_stfs) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) - bl get_fpr -1: li r9,-EFAULT -2: stfs fr0,0(r4) - li r9,0 -3: beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Store FP reg N to double at *p. N is in r3, p in r4. */ -_GLOBAL(do_stfd) - PPC_STLU r1,-STKFRM(r1) +#ifdef CONFIG_ALTIVEC +/* Get the contents of vrN into *p; N is in r3 and p is in r4. */ +_GLOBAL(get_vr) mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 + oris r7, r6, MSR_VEC@h MTMSRD(r7) isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) - bl get_fpr -1: li r9,-EFAULT -2: stfd fr0,0(r4) - li r9,0 -3: beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -#ifdef CONFIG_ALTIVEC -/* Get the contents of vrN into v0; N is in r3. */ -_GLOBAL(get_vr) - mflr r0 rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* v0 is already in v0 */ - nop -reg = 1 - .rept 31 - vor v0,reg,reg /* assembler doesn't know vmr? */ - blr +reg = 0 + .rept 32 + stvx reg, 0, r4 + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -196,18 +90,23 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr +2: MTMSRD(r6) + isync + blr -/* Put the contents of v0 into vrN; N is in r3. */ +/* Put the contents of *p into vrN; N is in r3 and p is in r4. */ _GLOBAL(put_vr) mflr r0 + mfmsr r6 + oris r7, r6, MSR_VEC@h + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* v0 is already in v0 */ - nop -reg = 1 - .rept 31 - vor reg,v0,v0 - blr +reg = 0 + .rept 32 + lvx reg, 0, r4 + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -215,62 +114,9 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr - -/* Load vector reg N from *p. N is in r3, p in r4. */ -_GLOBAL(do_lvx) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - oris r7,r6,MSR_VEC@h - cmpwi cr7,r3,0 - li r8,STKFRM-16 - MTMSRD(r7) - isync - beq cr7,1f - stvx v0,r1,r8 -1: li r9,-EFAULT -2: lvx v0,0,r4 - li r9,0 -3: beq cr7,4f - bl put_vr - lvx v0,r1,r8 -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) +2: MTMSRD(r6) isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Store vector reg N to *p. N is in r3, p in r4. */ -_GLOBAL(do_stvx) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - oris r7,r6,MSR_VEC@h - cmpwi cr7,r3,0 - li r8,STKFRM-16 - MTMSRD(r7) - isync - beq cr7,1f - stvx v0,r1,r8 - bl get_vr -1: li r9,-EFAULT -2: stvx v0,0,r4 - li r9,0 -3: beq cr7,4f - lvx v0,r1,r8 -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX @@ -313,7 +159,7 @@ reg = reg + 1 bctr /* Load VSX reg N from vector doubleword *p. N is in r3, p in r4. */ -_GLOBAL(do_lxvd2x) +_GLOBAL(load_vsrn) PPC_STLU r1,-STKFRM(r1) mflr r0 PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) @@ -325,49 +171,74 @@ _GLOBAL(do_lxvd2x) isync beq cr7,1f STXVD2X(0,R1,R8) -1: li r9,-EFAULT -2: LXVD2X(0,R0,R4) - li r9,0 -3: beq cr7,4f +1: LXVD2X(0,R0,R4) +#ifdef __LITTLE_ENDIAN__ + XXSWAPD(0,0) +#endif + beq cr7,4f bl put_vsr LXVD2X(0,R1,R8) 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) isync - mr r3,r9 addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) /* Store VSX reg N to vector doubleword *p. N is in r3, p in r4. */ -_GLOBAL(do_stxvd2x) +_GLOBAL(store_vsrn) PPC_STLU r1,-STKFRM(r1) mflr r0 PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) mfmsr r6 oris r7,r6,MSR_VSX@h - cmpwi cr7,r3,0 li r8,STKFRM-16 MTMSRD(r7) isync - beq cr7,1f STXVD2X(0,R1,R8) bl get_vsr -1: li r9,-EFAULT -2: STXVD2X(0,R0,R4) - li r9,0 -3: beq cr7,4f +#ifdef __LITTLE_ENDIAN__ + XXSWAPD(0,0) +#endif + STXVD2X(0,R0,R4) LXVD2X(0,R1,R8) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) + PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) isync mr r3,r9 addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) - #endif /* CONFIG_VSX */ +/* Convert single-precision to double, without disturbing FPRs. */ +/* conv_sp_to_dp(float *sp, double *dp) */ +_GLOBAL(conv_sp_to_dp) + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync + stfd fr0, -16(r1) + lfs fr0, 0(r3) + stfd fr0, 0(r4) + lfd fr0, -16(r1) + MTMSRD(r6) + isync + blr + +/* Convert single-precision to double, without disturbing FPRs. */ +/* conv_sp_to_dp(double *dp, float *sp) */ +_GLOBAL(conv_dp_to_sp) + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync + stfd fr0, -16(r1) + lfd fr0, 0(r3) + stfs fr0, 0(r4) + lfd fr0, -16(r1) + MTMSRD(r6) + isync + blr + #endif /* CONFIG_PPC_FPU */ |