* [RFC PATCH 1/5] powerpc/64s/hash: convert SLB miss handlers to C
2018-08-20 9:41 [RFC PATCH 0/5] rewriting SLB miss handler in C Nicholas Piggin
@ 2018-08-20 9:41 ` Nicholas Piggin
2018-08-20 10:08 ` Nicholas Piggin
2018-08-21 6:46 ` Michael Ellerman
2018-08-20 9:41 ` [RFC PATCH 2/5] powerpc/64s/hash: remove user SLB data from the paca Nicholas Piggin
` (3 subsequent siblings)
4 siblings, 2 replies; 10+ messages in thread
From: Nicholas Piggin @ 2018-08-20 9:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Aneesh Kumar K . V
This patch moves SLB miss handlers completely to C, using the standard
exception handler macros to set up the stack and branch to C.
This can be done because the segment containing the kernel stack is
always bolted, so accessing it with relocation on will not cause an
SLB exception.
Arbitrary kernel memory may not be accessed when handling kernel space
SLB misses, so care should be taken there. However user SLB misses can
access any kernel memory, which can be used to move some fields out of
the paca (in later patches).
User SLB misses could quite easily reconcile IRQs and set up a first
class kernel environment and exit via ret_from_except, however that
doesn't seem to be necessary at the moment, so we only do that if a
bad fault is encountered.
[ Credit to Aneesh for bug fixes and improvements to bad address
handling ]
---
arch/powerpc/include/asm/asm-prototypes.h | 2 +
arch/powerpc/kernel/exceptions-64s.S | 200 +++----------
arch/powerpc/mm/Makefile | 2 +-
arch/powerpc/mm/slb.c | 237 +++++++--------
arch/powerpc/mm/slb_low.S | 338 ----------------------
5 files changed, 166 insertions(+), 613 deletions(-)
delete mode 100644 arch/powerpc/mm/slb_low.S
diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 1f4691ce4126..c330ed10074a 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -78,6 +78,8 @@ void kernel_bad_stack(struct pt_regs *regs);
void system_reset_exception(struct pt_regs *regs);
void machine_check_exception(struct pt_regs *regs);
void emulation_assist_interrupt(struct pt_regs *regs);
+long do_slb_fault(struct pt_regs *regs, unsigned long ea);
+void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, unsigned long err);
/* signals, syscalls and interrupts */
long sys_swapcontext(struct ucontext __user *old_ctx,
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9dad73722d1a..f22ddb301661 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -567,28 +567,35 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
- mr r12,r3 /* save r3 */
- mfspr r3,SPRN_DAR
- mfspr r11,SPRN_SRR1
- crset 4*cr6+eq
- BRANCH_TO_COMMON(r10, slb_miss_common)
+EXCEPTION_PROLOG(PACA_EXSLB, data_access_slb_common, EXC_STD, KVMTEST_PR, 0x380);
EXC_REAL_END(data_access_slb, 0x380, 0x80)
EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380)
- mr r12,r3 /* save r3 */
- mfspr r3,SPRN_DAR
- mfspr r11,SPRN_SRR1
- crset 4*cr6+eq
- BRANCH_TO_COMMON(r10, slb_miss_common)
+EXCEPTION_RELON_PROLOG(PACA_EXSLB, data_access_slb_common, EXC_STD, NOTEST, 0x380);
EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
+
TRAMP_KVM_SKIP(PACA_EXSLB, 0x380)
+EXC_COMMON_BEGIN(data_access_slb_common)
+ mfspr r10,SPRN_DAR
+ std r10,PACA_EXSLB+EX_DAR(r13)
+ EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
+ ld r4,PACA_EXSLB+EX_DAR(r13)
+ std r4,_DAR(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_slb_fault
+ cmpdi r3,0
+ bne- 1f
+ b fast_exception_return
+1: /* Error case */
+ bl save_nvgprs
+ RECONCILE_IRQ_STATE(r10, r11)
+ ld r4,_DAR(r1)
+ mr r5,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_bad_slb_fault
+ b ret_from_except
+
EXC_REAL(instruction_access, 0x400, 0x80)
EXC_VIRT(instruction_access, 0x4400, 0x80, 0x400)
@@ -611,160 +618,33 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
- mr r12,r3 /* save r3 */
- mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
- mfspr r11,SPRN_SRR1
- crclr 4*cr6+eq
- BRANCH_TO_COMMON(r10, slb_miss_common)
+EXCEPTION_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, KVMTEST_PR, 0x480);
EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480)
- mr r12,r3 /* save r3 */
- mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
- mfspr r11,SPRN_SRR1
- crclr 4*cr6+eq
- BRANCH_TO_COMMON(r10, slb_miss_common)
+EXCEPTION_RELON_PROLOG(PACA_EXSLB, instruction_access_slb_common, EXC_STD, NOTEST, 0x480);
EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
-TRAMP_KVM(PACA_EXSLB, 0x480)
-
-
-/*
- * This handler is used by the 0x380 and 0x480 SLB miss interrupts, as well as
- * the virtual mode 0x4380 and 0x4480 interrupts if AIL is enabled.
- */
-EXC_COMMON_BEGIN(slb_miss_common)
- /*
- * r13 points to the PACA, r9 contains the saved CR,
- * r12 contains the saved r3,
- * r11 contain the saved SRR1, SRR0 is still ready for return
- * r3 has the faulting address
- * r9 - r13 are saved in paca->exslb.
- * cr6.eq is set for a D-SLB miss, clear for a I-SLB miss
- * We assume we aren't going to take any exceptions during this
- * procedure.
- */
- mflr r10
- stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */
- std r10,PACA_EXSLB+EX_LR(r13) /* save LR */
-
- andi. r9,r11,MSR_PR // Check for exception from userspace
- cmpdi cr4,r9,MSR_PR // And save the result in CR4 for later
-
- /*
- * Test MSR_RI before calling slb_allocate_realmode, because the
- * MSR in r11 gets clobbered. However we still want to allocate
- * SLB in case MSR_RI=0, to minimise the risk of getting stuck in
- * recursive SLB faults. So use cr5 for this, which is preserved.
- */
- andi. r11,r11,MSR_RI /* check for unrecoverable exception */
- cmpdi cr5,r11,MSR_RI
-
- crset 4*cr0+eq
-#ifdef CONFIG_PPC_BOOK3S_64
-BEGIN_MMU_FTR_SECTION
- bl slb_allocate
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
-#endif
-
- ld r10,PACA_EXSLB+EX_LR(r13)
- lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */
- mtlr r10
-
- /*
- * Large address, check whether we have to allocate new contexts.
- */
- beq- 8f
-
- bne- cr5,2f /* if unrecoverable exception, oops */
-
- /* All done -- return from exception. */
-
- bne cr4,1f /* returning to kernel */
-
- mtcrf 0x80,r9
- mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */
- mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */
- mtcrf 0x02,r9 /* I/D indication is in cr6 */
- mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
-
- RESTORE_CTR(r9, PACA_EXSLB)
- RESTORE_PPR_PACA(PACA_EXSLB, r9)
- mr r3,r12
- ld r9,PACA_EXSLB+EX_R9(r13)
- ld r10,PACA_EXSLB+EX_R10(r13)
- ld r11,PACA_EXSLB+EX_R11(r13)
- ld r12,PACA_EXSLB+EX_R12(r13)
- ld r13,PACA_EXSLB+EX_R13(r13)
- RFI_TO_USER
- b . /* prevent speculative execution */
-1:
- mtcrf 0x80,r9
- mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */
- mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */
- mtcrf 0x02,r9 /* I/D indication is in cr6 */
- mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */
-
- RESTORE_CTR(r9, PACA_EXSLB)
- RESTORE_PPR_PACA(PACA_EXSLB, r9)
- mr r3,r12
- ld r9,PACA_EXSLB+EX_R9(r13)
- ld r10,PACA_EXSLB+EX_R10(r13)
- ld r11,PACA_EXSLB+EX_R11(r13)
- ld r12,PACA_EXSLB+EX_R12(r13)
- ld r13,PACA_EXSLB+EX_R13(r13)
- RFI_TO_KERNEL
- b . /* prevent speculative execution */
-
-
-2: std r3,PACA_EXSLB+EX_DAR(r13)
- mr r3,r12
- mfspr r11,SPRN_SRR0
- mfspr r12,SPRN_SRR1
- LOAD_HANDLER(r10,unrecov_slb)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- RFI_TO_KERNEL
- b .
-8: std r3,PACA_EXSLB+EX_DAR(r13)
- mr r3,r12
- mfspr r11,SPRN_SRR0
- mfspr r12,SPRN_SRR1
- LOAD_HANDLER(r10, large_addr_slb)
- mtspr SPRN_SRR0,r10
- ld r10,PACAKMSR(r13)
- mtspr SPRN_SRR1,r10
- RFI_TO_KERNEL
- b .
+TRAMP_KVM(PACA_EXSLB, 0x480)
-EXC_COMMON_BEGIN(unrecov_slb)
- EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
- RECONCILE_IRQ_STATE(r10, r11)
+EXC_COMMON_BEGIN(instruction_access_slb_common)
+ EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
+ ld r4,_NIP(r1)
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_slb_fault
+ cmpdi r3,0
+ bne- 1f
+ b fast_exception_return
+1: /* Error case */
bl save_nvgprs
-1: addi r3,r1,STACK_FRAME_OVERHEAD
- bl unrecoverable_exception
- b 1b
-
-EXC_COMMON_BEGIN(large_addr_slb)
- EXCEPTION_PROLOG_COMMON(0x380, PACA_EXSLB)
RECONCILE_IRQ_STATE(r10, r11)
- ld r3, PACA_EXSLB+EX_DAR(r13)
- std r3, _DAR(r1)
- beq cr6, 2f
- li r10, 0x481 /* fix trap number for I-SLB miss */
- std r10, _TRAP(r1)
-2: bl save_nvgprs
- addi r3, r1, STACK_FRAME_OVERHEAD
- bl slb_miss_large_addr
+ ld r4,_NIP(r1)
+ mr r5,r3
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl do_bad_slb_fault
b ret_from_except
+
EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
.globl hardware_interrupt_hv;
hardware_interrupt_hv:
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index cdf6a9960046..892d4e061d62 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -15,7 +15,7 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \
obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o
hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o
-obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb_low.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o
+obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o
obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o
obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o
obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index a3a6e04296cd..5643879fa2b1 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -34,7 +34,7 @@ enum slb_index {
KSTACK_INDEX = 2, /* Kernel stack map */
};
-extern void slb_allocate(unsigned long ea);
+static long slb_allocate_user(struct mm_struct *mm, unsigned long ea);
#define slb_esid_mask(ssize) \
(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
@@ -287,49 +287,19 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
is_kernel_addr(exec_base))
return;
- slb_allocate(pc);
+ slb_allocate_user(mm, pc);
if (!esids_match(pc, stack))
- slb_allocate(stack);
+ slb_allocate_user(mm, stack);
if (!esids_match(pc, exec_base) &&
!esids_match(stack, exec_base))
- slb_allocate(exec_base);
+ slb_allocate_user(mm, exec_base);
}
-static inline void patch_slb_encoding(unsigned int *insn_addr,
- unsigned int immed)
-{
-
- /*
- * This function patches either an li or a cmpldi instruction with
- * a new immediate value. This relies on the fact that both li
- * (which is actually addi) and cmpldi both take a 16-bit immediate
- * value, and it is situated in the same location in the instruction,
- * ie. bits 16-31 (Big endian bit order) or the lower 16 bits.
- * The signedness of the immediate operand differs between the two
- * instructions however this code is only ever patching a small value,
- * much less than 1 << 15, so we can get away with it.
- * To patch the value we read the existing instruction, clear the
- * immediate value, and or in our new value, then write the instruction
- * back.
- */
- unsigned int insn = (*insn_addr & 0xffff0000) | immed;
- patch_instruction(insn_addr, insn);
-}
-
-extern u32 slb_miss_kernel_load_linear[];
-extern u32 slb_miss_kernel_load_io[];
-extern u32 slb_compare_rr_to_size[];
-extern u32 slb_miss_kernel_load_vmemmap[];
-
void slb_set_size(u16 size)
{
- if (mmu_slb_size == size)
- return;
-
mmu_slb_size = size;
- patch_slb_encoding(slb_compare_rr_to_size, mmu_slb_size);
}
void slb_initialize(void)
@@ -351,19 +321,9 @@ void slb_initialize(void)
#endif
if (!slb_encoding_inited) {
slb_encoding_inited = 1;
- patch_slb_encoding(slb_miss_kernel_load_linear,
- SLB_VSID_KERNEL | linear_llp);
- patch_slb_encoding(slb_miss_kernel_load_io,
- SLB_VSID_KERNEL | io_llp);
- patch_slb_encoding(slb_compare_rr_to_size,
- mmu_slb_size);
-
pr_devel("SLB: linear LLP = %04lx\n", linear_llp);
pr_devel("SLB: io LLP = %04lx\n", io_llp);
-
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- patch_slb_encoding(slb_miss_kernel_load_vmemmap,
- SLB_VSID_KERNEL | vmemmap_llp);
pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
#endif
}
@@ -394,49 +354,10 @@ void slb_initialize(void)
asm volatile("isync":::"memory");
}
-static void insert_slb_entry(unsigned long vsid, unsigned long ea,
- int bpsize, int ssize)
+static void slb_cache_update(unsigned long esid_data)
{
- unsigned long flags, vsid_data, esid_data;
- enum slb_index index;
int slb_cache_index;
- /*
- * We are irq disabled, hence should be safe to access PACA.
- */
- VM_WARN_ON(!irqs_disabled());
-
- /*
- * We can't take a PMU exception in the following code, so hard
- * disable interrupts.
- */
- hard_irq_disable();
-
- index = get_paca()->stab_rr;
-
- /*
- * simple round-robin replacement of slb starting at SLB_NUM_BOLTED.
- */
- if (index < (mmu_slb_size - 1))
- index++;
- else
- index = SLB_NUM_BOLTED;
-
- get_paca()->stab_rr = index;
-
- flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
- vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
- ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
- esid_data = mk_esid_data(ea, ssize, index);
-
- /*
- * No need for an isync before or after this slbmte. The exception
- * we enter with and the rfid we exit with are context synchronizing.
- * Also we only handle user segments here.
- */
- asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data)
- : "memory");
-
if (cpu_has_feature(CPU_FTR_ARCH_300))
return; /* ISAv3.0B and later does not use slb_cache */
@@ -461,58 +382,146 @@ static void insert_slb_entry(unsigned long vsid, unsigned long ea,
}
}
-static void handle_multi_context_slb_miss(int context_id, unsigned long ea)
+static enum slb_index alloc_slb_index(void)
+{
+ enum slb_index index;
+
+ /* round-robin replacement of slb starting at SLB_NUM_BOLTED. */
+ index = get_paca()->stab_rr;
+ if (index < (mmu_slb_size - 1))
+ index++;
+ else
+ index = SLB_NUM_BOLTED;
+ get_paca()->stab_rr = index;
+
+ return index;
+}
+
+static void slb_insert_entry(unsigned long ea, unsigned long context,
+ unsigned long flags, int ssize)
{
- struct mm_struct *mm = current->mm;
unsigned long vsid;
- int bpsize;
+ unsigned long vsid_data, esid_data;
+ enum slb_index index = alloc_slb_index();
+
+ vsid = get_vsid(context, ea, ssize);
+ vsid_data = (vsid << slb_vsid_shift(ssize)) | flags |
+ ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
+ esid_data = mk_esid_data(ea, ssize, index);
/*
- * We are always above 1TB, hence use high user segment size.
+ * No need for an isync before or after this slbmte. The exception
+ * we enter with and the rfid we exit with are context synchronizing.
+ * Also we only handle user segments here.
*/
- vsid = get_vsid(context_id, ea, mmu_highuser_ssize);
- bpsize = get_slice_psize(mm, ea);
- insert_slb_entry(vsid, ea, bpsize, mmu_highuser_ssize);
+ asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data));
+
+ slb_cache_update(esid_data);
}
-void slb_miss_large_addr(struct pt_regs *regs)
+static long slb_allocate_kernel(unsigned long ea, unsigned long id)
{
- enum ctx_state prev_state = exception_enter();
- unsigned long ea = regs->dar;
- int context;
+ unsigned long context;
+ unsigned long flags;
+ int ssize;
- if (REGION_ID(ea) != USER_REGION_ID)
- goto slb_bad_addr;
+ if ((ea & ~REGION_MASK) >= (1ULL << MAX_EA_BITS_PER_CONTEXT))
+ return -EFAULT;
- /*
- * Are we beyound what the page table layout supports ?
- */
- if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
- goto slb_bad_addr;
+ if (id == KERNEL_REGION_ID) {
+ flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+ } else if (id == VMEMMAP_REGION_ID) {
+ flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp;
+#endif
+ } else {
+ if (ea < H_VMALLOC_END)
+ flags = get_paca()->vmalloc_sllp;
+ else
+ flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
+ }
+ ssize = MMU_SEGSIZE_1T;
+ if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
+ ssize = MMU_SEGSIZE_256M;
+
+ context = id - KERNEL_REGION_CONTEXT_OFFSET;
- /* Lower address should have been handled by asm code */
- if (ea < (1UL << MAX_EA_BITS_PER_CONTEXT))
- goto slb_bad_addr;
+ slb_insert_entry(ea, context, flags, ssize);
+
+ return 0;
+}
+
+static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
+{
+ unsigned long context;
+ unsigned long flags;
+ int bpsize;
+ int ssize;
/*
* consider this as bad access if we take a SLB miss
* on an address above addr limit.
*/
- if (ea >= current->mm->context.slb_addr_limit)
- goto slb_bad_addr;
+ if (ea >= mm->context.slb_addr_limit)
+ return -EFAULT;
- context = get_ea_context(¤t->mm->context, ea);
+ context = get_ea_context(&mm->context, ea);
if (!context)
- goto slb_bad_addr;
+ return -EFAULT;
+
+ if (unlikely(ea >= H_PGTABLE_RANGE)) {
+ WARN_ON(1);
+ return -EFAULT;
+ }
+
+ ssize = user_segment_size(ea);
+
+ bpsize = get_slice_psize(mm, ea);
+ flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
+
+ slb_insert_entry(ea, context, flags, ssize);
+
+ return 0;
+}
+
+long do_slb_fault(struct pt_regs *regs, unsigned long ea)
+{
+ unsigned long id = REGION_ID(ea);
+
+ /* IRQs are not reconciled here, so can't check irqs_disabled */
+ VM_WARN_ON(mfmsr() & MSR_EE);
+
+ /*
+ * SLB kernel faults must be very careful not to touch anything
+ * that is not bolted. E.g., PACA and global variables are okay,
+ * mm->context stuff is not.
+ *
+ * SLB user faults can access all of kernel memory, but must be
+ * careful not to touch things like IRQ state because it is not
+ * "reconciled" here. The difficulty is that we must use
+ * fast_exception_return to return from kernel SLB faults without
+ * looking at possible non-bolted memory. We could test user vs
+ * kernel faults in the interrupt handler asm and do a full fault,
+ * reconcile, ret_from_except for user faults which would make them
+ * first class kernel code. But for performance it's probably nicer
+ * if they go via fast_exception_return too.
+ */
+ if (id >= KERNEL_REGION_ID) {
+ return slb_allocate_kernel(ea, id);
+ } else {
+ struct mm_struct *mm = current->mm;
+
+ if (unlikely(!mm))
+ return -EFAULT;
- handle_multi_context_slb_miss(context, ea);
- exception_exit(prev_state);
- return;
+ return slb_allocate_user(mm, ea);
+ }
+}
-slb_bad_addr:
+void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err)
+{
if (user_mode(regs))
_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
else
bad_page_fault(regs, ea, SIGSEGV);
- exception_exit(prev_state);
}
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
deleted file mode 100644
index dbbb7a59eaf8..000000000000
--- a/arch/powerpc/mm/slb_low.S
+++ /dev/null
@@ -1,338 +0,0 @@
-/*
- * Low-level SLB routines
- *
- * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
- *
- * Based on earlier C version:
- * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
- * Copyright (c) 2001 Dave Engebretsen
- * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <asm/processor.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/cputable.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/pgtable.h>
-#include <asm/firmware.h>
-#include <asm/feature-fixups.h>
-
-/*
- * This macro generates asm code to compute the VSID scramble
- * function. Used in slb_allocate() and do_stab_bolted. The function
- * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
- *
- * rt = register containing the proto-VSID and into which the
- * VSID will be stored
- * rx = scratch register (clobbered)
- * rf = flags
- *
- * - rt and rx must be different registers
- * - The answer will end up in the low VSID_BITS bits of rt. The higher
- * bits may contain other garbage, so you may need to mask the
- * result.
- */
-#define ASM_VSID_SCRAMBLE(rt, rx, rf, size) \
- lis rx,VSID_MULTIPLIER_##size@h; \
- ori rx,rx,VSID_MULTIPLIER_##size@l; \
- mulld rt,rt,rx; /* rt = rt * MULTIPLIER */ \
-/* \
- * powermac get slb fault before feature fixup, so make 65 bit part \
- * the default part of feature fixup \
- */ \
-BEGIN_MMU_FTR_SECTION \
- srdi rx,rt,VSID_BITS_65_##size; \
- clrldi rt,rt,(64-VSID_BITS_65_##size); \
- add rt,rt,rx; \
- addi rx,rt,1; \
- srdi rx,rx,VSID_BITS_65_##size; \
- add rt,rt,rx; \
- rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_65_##size)); \
-MMU_FTR_SECTION_ELSE \
- srdi rx,rt,VSID_BITS_##size; \
- clrldi rt,rt,(64-VSID_BITS_##size); \
- add rt,rt,rx; /* add high and low bits */ \
- addi rx,rt,1; \
- srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \
- add rt,rt,rx; \
- rldimi rf,rt,SLB_VSID_SHIFT_##size,(64 - (SLB_VSID_SHIFT_##size + VSID_BITS_##size)); \
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_68_BIT_VA)
-
-
-/* void slb_allocate(unsigned long ea);
- *
- * Create an SLB entry for the given EA (user or kernel).
- * r3 = faulting address, r13 = PACA
- * r9, r10, r11 are clobbered by this function
- * r3 is preserved.
- * No other registers are examined or changed.
- */
-_GLOBAL(slb_allocate)
- /*
- * Check if the address falls within the range of the first context, or
- * if we may need to handle multi context. For the first context we
- * allocate the slb entry via the fast path below. For large address we
- * branch out to C-code and see if additional contexts have been
- * allocated.
- * The test here is:
- * (ea & ~REGION_MASK) >= (1ull << MAX_EA_BITS_PER_CONTEXT)
- */
- rldicr. r9,r3,4,(63 - MAX_EA_BITS_PER_CONTEXT - 4)
- bne- 8f
-
- srdi r9,r3,60 /* get region */
- srdi r10,r3,SID_SHIFT /* get esid */
- cmpldi cr7,r9,0xc /* cmp PAGE_OFFSET for later use */
-
- /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
- blt cr7,0f /* user or kernel? */
-
- /* Check if hitting the linear mapping or some other kernel space
- */
- bne cr7,1f
-
- /* Linear mapping encoding bits, the "li" instruction below will
- * be patched by the kernel at boot
- */
-.globl slb_miss_kernel_load_linear
-slb_miss_kernel_load_linear:
- li r11,0
- /*
- * context = (ea >> 60) - (0xc - 1)
- * r9 = region id.
- */
- subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
-
-BEGIN_FTR_SECTION
- b .Lslb_finish_load
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
- b .Lslb_finish_load_1T
-
-1:
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
- cmpldi cr0,r9,0xf
- bne 1f
-/* Check virtual memmap region. To be patched at kernel boot */
-.globl slb_miss_kernel_load_vmemmap
-slb_miss_kernel_load_vmemmap:
- li r11,0
- b 6f
-1:
-#endif /* CONFIG_SPARSEMEM_VMEMMAP */
-
- /*
- * r10 contains the ESID, which is the original faulting EA shifted
- * right by 28 bits. We need to compare that with (H_VMALLOC_END >> 28)
- * which is 0xd00038000. That can't be used as an immediate, even if we
- * ignored the 0xd, so we have to load it into a register, and we only
- * have one register free. So we must load all of (H_VMALLOC_END >> 28)
- * into a register and compare ESID against that.
- */
- lis r11,(H_VMALLOC_END >> 32)@h // r11 = 0xffffffffd0000000
- ori r11,r11,(H_VMALLOC_END >> 32)@l // r11 = 0xffffffffd0003800
- // Rotate left 4, then mask with 0xffffffff0
- rldic r11,r11,4,28 // r11 = 0xd00038000
- cmpld r10,r11 // if r10 >= r11
- bge 5f // goto io_mapping
-
- /*
- * vmalloc mapping gets the encoding from the PACA as the mapping
- * can be demoted from 64K -> 4K dynamically on some machines.
- */
- lhz r11,PACAVMALLOCSLLP(r13)
- b 6f
-5:
- /* IO mapping */
-.globl slb_miss_kernel_load_io
-slb_miss_kernel_load_io:
- li r11,0
-6:
- /*
- * context = (ea >> 60) - (0xc - 1)
- * r9 = region id.
- */
- subi r9,r9,KERNEL_REGION_CONTEXT_OFFSET
-
-BEGIN_FTR_SECTION
- b .Lslb_finish_load
-END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
- b .Lslb_finish_load_1T
-
-0: /*
- * For userspace addresses, make sure this is region 0.
- */
- cmpdi r9, 0
- bne- 8f
- /*
- * user space make sure we are within the allowed limit
- */
- ld r11,PACA_SLB_ADDR_LIMIT(r13)
- cmpld r3,r11
- bge- 8f
-
- /* when using slices, we extract the psize off the slice bitmaps
- * and then we need to get the sllp encoding off the mmu_psize_defs
- * array.
- *
- * XXX This is a bit inefficient especially for the normal case,
- * so we should try to implement a fast path for the standard page
- * size using the old sllp value so we avoid the array. We cannot
- * really do dynamic patching unfortunately as processes might flip
- * between 4k and 64k standard page size
- */
-#ifdef CONFIG_PPC_MM_SLICES
- /* r10 have esid */
- cmpldi r10,16
- /* below SLICE_LOW_TOP */
- blt 5f
- /*
- * Handle hpsizes,
- * r9 is get_paca()->context.high_slices_psize[index], r11 is mask_index
- */
- srdi r11,r10,(SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT + 1) /* index */
- addi r9,r11,PACAHIGHSLICEPSIZE
- lbzx r9,r13,r9 /* r9 is hpsizes[r11] */
- /* r11 = (r10 >> (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)) & 0x1 */
- rldicl r11,r10,(64 - (SLICE_HIGH_SHIFT - SLICE_LOW_SHIFT)),63
- b 6f
-
-5:
- /*
- * Handle lpsizes
- * r9 is get_paca()->context.low_slices_psize[index], r11 is mask_index
- */
- srdi r11,r10,1 /* index */
- addi r9,r11,PACALOWSLICESPSIZE
- lbzx r9,r13,r9 /* r9 is lpsizes[r11] */
- rldicl r11,r10,0,63 /* r11 = r10 & 0x1 */
-6:
- sldi r11,r11,2 /* index * 4 */
- /* Extract the psize and multiply to get an array offset */
- srd r9,r9,r11
- andi. r9,r9,0xf
- mulli r9,r9,MMUPSIZEDEFSIZE
-
- /* Now get to the array and obtain the sllp
- */
- ld r11,PACATOC(r13)
- ld r11,mmu_psize_defs@got(r11)
- add r11,r11,r9
- ld r11,MMUPSIZESLLP(r11)
- ori r11,r11,SLB_VSID_USER
-#else
- /* paca context sllp already contains the SLB_VSID_USER bits */
- lhz r11,PACACONTEXTSLLP(r13)
-#endif /* CONFIG_PPC_MM_SLICES */
-
- ld r9,PACACONTEXTID(r13)
-BEGIN_FTR_SECTION
- cmpldi r10,0x1000
- bge .Lslb_finish_load_1T
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- b .Lslb_finish_load
-
-8: /* invalid EA - return an error indication */
- crset 4*cr0+eq /* indicate failure */
- blr
-
-/*
- * Finish loading of an SLB entry and return
- *
- * r3 = EA, r9 = context, r10 = ESID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET
- */
-.Lslb_finish_load:
- rldimi r10,r9,ESID_BITS,0
- ASM_VSID_SCRAMBLE(r10,r9,r11,256M)
- /* r3 = EA, r11 = VSID data */
- /*
- * Find a slot, round robin. Previously we tried to find a
- * free slot first but that took too long. Unfortunately we
- * dont have any LRU information to help us choose a slot.
- */
-
- mr r9,r3
-
- /* slb_finish_load_1T continues here. r9=EA with non-ESID bits clear */
-7: ld r10,PACASTABRR(r13)
- addi r10,r10,1
- /* This gets soft patched on boot. */
-.globl slb_compare_rr_to_size
-slb_compare_rr_to_size:
- cmpldi r10,0
-
- blt+ 4f
- li r10,SLB_NUM_BOLTED
-
-4:
- std r10,PACASTABRR(r13)
-
-3:
- rldimi r9,r10,0,36 /* r9 = EA[0:35] | entry */
- oris r10,r9,SLB_ESID_V@h /* r10 = r9 | SLB_ESID_V */
-
- /* r9 = ESID data, r11 = VSID data */
-
- /*
- * No need for an isync before or after this slbmte. The exception
- * we enter with and the rfid we exit with are context synchronizing.
- */
- slbmte r11,r10
-
- crclr 4*cr0+eq /* set result to "success" */
-BEGIN_FTR_SECTION
- blr /* No SLB cache, see switch_slb */
-FTR_SECTION_ELSE
- bgelr cr7 /* we're done for kernel addresses */
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300)
-
- /* Update the slb cache for user addresses */
- lhz r9,PACASLBCACHEPTR(r13) /* offset = paca->slb_cache_ptr */
- cmpldi r9,SLB_CACHE_ENTRIES
- bge 1f
-
- /* still room in the slb cache */
- sldi r11,r9,2 /* r11 = offset * sizeof(u32) */
- srdi r10,r10,28 /* get the 36 bits of the ESID */
- add r11,r11,r13 /* r11 = (u32 *)paca + offset */
- stw r10,PACASLBCACHE(r11) /* paca->slb_cache[offset] = esid */
- addi r9,r9,1 /* offset++ */
- b 2f
-1: /* offset >= SLB_CACHE_ENTRIES */
- li r9,SLB_CACHE_ENTRIES+1
-2:
- sth r9,PACASLBCACHEPTR(r13) /* paca->slb_cache_ptr = offset */
- crclr 4*cr0+eq /* set result to "success" */
- blr
-
-/*
- * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
- *
- * r3 = EA, r9 = context, r10 = ESID(256MB), r11 = flags, clobbers r9
- */
-.Lslb_finish_load_1T:
- srdi r10,r10,(SID_SHIFT_1T - SID_SHIFT) /* get 1T ESID */
- rldimi r10,r9,ESID_BITS_1T,0
- ASM_VSID_SCRAMBLE(r10,r9,r11,1T)
-
- li r10,MMU_SEGSIZE_1T
- rldimi r11,r10,SLB_VSID_SSIZE_SHIFT,0 /* insert segment size */
-
- /* r3 = EA, r11 = VSID data */
- clrrdi r9,r3,SID_SHIFT_1T /* clear out non-ESID bits */
- b 7b
-
-
-_ASM_NOKPROBE_SYMBOL(slb_allocate)
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_linear)
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_io)
-_ASM_NOKPROBE_SYMBOL(slb_compare_rr_to_size)
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-_ASM_NOKPROBE_SYMBOL(slb_miss_kernel_load_vmemmap)
-#endif
--
2.17.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [RFC PATCH 2/5] powerpc/64s/hash: remove user SLB data from the paca
2018-08-20 9:41 [RFC PATCH 0/5] rewriting SLB miss handler in C Nicholas Piggin
2018-08-20 9:41 ` [RFC PATCH 1/5] powerpc/64s/hash: convert SLB miss handlers to C Nicholas Piggin
@ 2018-08-20 9:41 ` Nicholas Piggin
2018-08-20 9:41 ` [RFC PATCH 3/5] powerpc/64s/hash: remove the first vmalloc segment from the bolted SLB Nicholas Piggin
` (2 subsequent siblings)
4 siblings, 0 replies; 10+ messages in thread
From: Nicholas Piggin @ 2018-08-20 9:41 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nicholas Piggin, Aneesh Kumar K . V
User SLB mappig data is copied into the PACA from the mm->context
so it can be accessed by the SLB miss handlers.
After the previous patch, SLB miss handlers now run with relocation
on, and user SLB misses are able to take recursive kernel SLB misses,
so the user SLB mapping data can be removed from the paca and
accessed directly.
---
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
arch/powerpc/include/asm/paca.h | 13 ------
arch/powerpc/kernel/asm-offsets.c | 9 ----
arch/powerpc/kernel/paca.c | 21 ---------
arch/powerpc/mm/hash_utils_64.c | 46 +++++--------------
arch/powerpc/mm/mmu_context.c | 3 +-
arch/powerpc/mm/slb.c | 20 +++++++-
arch/powerpc/mm/slice.c | 29 ++++--------
8 files changed, 40 insertions(+), 102 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index b3520b549cba..39764214aef5 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -496,6 +496,7 @@ static inline void hpte_init_pseries(void) { }
extern void hpte_init_native(void);
extern void slb_initialize(void);
+extern void core_flush_all_slbs(struct mm_struct *mm);
extern void slb_flush_and_rebolt(void);
void slb_flush_all_realmode(void);
void __slb_restore_bolted_realmode(void);
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 4331295db0f7..8c258a057207 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -143,18 +143,6 @@ struct paca_struct {
struct tlb_core_data tcd;
#endif /* CONFIG_PPC_BOOK3E */
-#ifdef CONFIG_PPC_BOOK3S
- mm_context_id_t mm_ctx_id;
-#ifdef CONFIG_PPC_MM_SLICES
- unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
- unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
- unsigned long mm_ctx_slb_addr_limit;
-#else
- u16 mm_ctx_user_psize;
- u16 mm_ctx_sllp;
-#endif
-#endif
-
/*
* then miscellaneous read-write fields
*/
@@ -256,7 +244,6 @@ struct paca_struct {
#endif /* CONFIG_PPC_PSERIES */
} ____cacheline_aligned;
-extern void copy_mm_to_paca(struct mm_struct *mm);
extern struct paca_struct **paca_ptrs;
extern void initialise_paca(struct paca_struct *new_paca, int cpu);
extern void setup_paca(struct paca_struct *new_paca);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7834256585f1..43b67ead5b97 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -181,15 +181,6 @@ int main(void)
OFFSET(PACAIRQSOFTMASK, paca_struct, irq_soft_mask);
OFFSET(PACAIRQHAPPENED, paca_struct, irq_happened);
OFFSET(PACA_FTRACE_ENABLED, paca_struct, ftrace_enabled);
-#ifdef CONFIG_PPC_BOOK3S
- OFFSET(PACACONTEXTID, paca_struct, mm_ctx_id);
-#ifdef CONFIG_PPC_MM_SLICES
- OFFSET(PACALOWSLICESPSIZE, paca_struct, mm_ctx_low_slices_psize);
- OFFSET(PACAHIGHSLICEPSIZE, paca_struct, mm_ctx_high_slices_psize);
- OFFSET(PACA_SLB_ADDR_LIMIT, paca_struct, mm_ctx_slb_addr_limit);
- DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
-#endif /* CONFIG_PPC_MM_SLICES */
-#endif
#ifdef CONFIG_PPC_BOOK3E
OFFSET(PACAPGD, paca_struct, pgd);
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 0ee3e6d50f28..6752e17f0281 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -259,24 +259,3 @@ void __init free_unused_pacas(void)
paca_ptrs_size + paca_struct_size, nr_cpu_ids);
}
-void copy_mm_to_paca(struct mm_struct *mm)
-{
-#ifdef CONFIG_PPC_BOOK3S
- mm_context_t *context = &mm->context;
-
- get_paca()->mm_ctx_id = context->id;
-#ifdef CONFIG_PPC_MM_SLICES
- VM_BUG_ON(!mm->context.slb_addr_limit);
- get_paca()->mm_ctx_slb_addr_limit = mm->context.slb_addr_limit;
- memcpy(&get_paca()->mm_ctx_low_slices_psize,
- &context->low_slices_psize, sizeof(context->low_slices_psize));
- memcpy(&get_paca()->mm_ctx_high_slices_psize,
- &context->high_slices_psize, TASK_SLICE_ARRAY_SZ(mm));
-#else /* CONFIG_PPC_MM_SLICES */
- get_paca()->mm_ctx_user_psize = context->user_psize;
- get_paca()->mm_ctx_sllp = context->sllp;
-#endif
-#else /* !CONFIG_PPC_BOOK3S */
- return;
-#endif
-}
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index f23a89d8e4ce..88c95dc8b141 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1088,16 +1088,16 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
}
#ifdef CONFIG_PPC_MM_SLICES
-static unsigned int get_paca_psize(unsigned long addr)
+static unsigned int get_psize(struct mm_struct *mm, unsigned long addr)
{
unsigned char *psizes;
unsigned long index, mask_index;
if (addr < SLICE_LOW_TOP) {
- psizes = get_paca()->mm_ctx_low_slices_psize;
+ psizes = mm->context.low_slices_psize;
index = GET_LOW_SLICE_INDEX(addr);
} else {
- psizes = get_paca()->mm_ctx_high_slices_psize;
+ psizes = mm->context.high_slices_psize;
index = GET_HIGH_SLICE_INDEX(addr);
}
mask_index = index & 0x1;
@@ -1105,9 +1105,9 @@ static unsigned int get_paca_psize(unsigned long addr)
}
#else
-unsigned int get_paca_psize(unsigned long addr)
+unsigned int get_psize(struct mm_struct *mm, unsigned long addr)
{
- return get_paca()->mm_ctx_user_psize;
+ return mm->context.user_psize;
}
#endif
@@ -1118,15 +1118,11 @@ unsigned int get_paca_psize(unsigned long addr)
#ifdef CONFIG_PPC_64K_PAGES
void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
{
- if (get_slice_psize(mm, addr) == MMU_PAGE_4K)
+ if (get_psize(mm, addr) == MMU_PAGE_4K)
return;
slice_set_range_psize(mm, addr, 1, MMU_PAGE_4K);
copro_flush_all_slbs(mm);
- if ((get_paca_psize(addr) != MMU_PAGE_4K) && (current->mm == mm)) {
-
- copy_mm_to_paca(mm);
- slb_flush_and_rebolt();
- }
+ core_flush_all_slbs(mm);
}
#endif /* CONFIG_PPC_64K_PAGES */
@@ -1191,22 +1187,6 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
trap, vsid, ssize, psize, lpsize, pte);
}
-static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
- int psize, bool user_region)
-{
- if (user_region) {
- if (psize != get_paca_psize(ea)) {
- copy_mm_to_paca(mm);
- slb_flush_and_rebolt();
- }
- } else if (get_paca()->vmalloc_sllp !=
- mmu_psize_defs[mmu_vmalloc_psize].sllp) {
- get_paca()->vmalloc_sllp =
- mmu_psize_defs[mmu_vmalloc_psize].sllp;
- slb_vmalloc_update();
- }
-}
-
/* Result code is:
* 0 - handled
* 1 - normal page fault
@@ -1239,7 +1219,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
rc = 1;
goto bail;
}
- psize = get_slice_psize(mm, ea);
+ psize = get_psize(mm, ea);
ssize = user_segment_size(ea);
vsid = get_user_vsid(&mm->context, ea, ssize);
break;
@@ -1327,9 +1307,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
WARN_ON(1);
}
#endif
- if (current->mm == mm)
- check_paca_psize(ea, mm, psize, user_region);
-
goto bail;
}
@@ -1364,15 +1341,14 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
"to 4kB pages because of "
"non-cacheable mapping\n");
psize = mmu_vmalloc_psize = MMU_PAGE_4K;
+ slb_vmalloc_update();
copro_flush_all_slbs(mm);
+ core_flush_all_slbs(mm);
}
}
#endif /* CONFIG_PPC_64K_PAGES */
- if (current->mm == mm)
- check_paca_psize(ea, mm, psize, user_region);
-
#ifdef CONFIG_PPC_64K_PAGES
if (psize == MMU_PAGE_64K)
rc = __hash_page_64K(ea, access, vsid, ptep, trap,
@@ -1460,7 +1436,7 @@ int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
#ifdef CONFIG_PPC_MM_SLICES
static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
{
- int psize = get_slice_psize(mm, ea);
+ int psize = get_psize(mm, ea);
/* We only prefault standard pages for now */
if (unlikely(psize != mm->context.user_psize))
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index f84e14f23e50..28ae2835db3d 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -54,8 +54,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
* MMU context id, which is then moved to SPRN_PID.
*
* For the hash MMU it is either the first load from slb_cache
- * in switch_slb(), and/or the store of paca->mm_ctx_id in
- * copy_mm_to_paca().
+ * in switch_slb(), and/or load of MMU context id.
*
* On the other side, the barrier is in mm/tlb-radix.c for
* radix which orders earlier stores to clear the PTEs vs
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 5643879fa2b1..221d94b4f9cf 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -274,8 +274,6 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
get_paca()->slb_cache_ptr = 0;
}
- copy_mm_to_paca(mm);
-
/*
* preload some userspace segments into the SLB.
* Almost all 32 and 64bit PowerPC executables are linked at
@@ -302,6 +300,24 @@ void slb_set_size(u16 size)
mmu_slb_size = size;
}
+static void cpu_flush_slb(void *parm)
+{
+ struct mm_struct *mm = parm;
+ unsigned long flags;
+
+ if (mm != current->active_mm)
+ return;
+
+ local_irq_save(flags);
+ slb_flush_and_rebolt();
+ local_irq_restore(flags);
+}
+
+void core_flush_all_slbs(struct mm_struct *mm)
+{
+ on_each_cpu(cpu_flush_slb, mm, 1);
+}
+
void slb_initialize(void)
{
unsigned long linear_llp, vmalloc_llp, io_llp;
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 205fe557ca10..606f424aac47 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -207,23 +207,6 @@ static bool slice_check_range_fits(struct mm_struct *mm,
return true;
}
-static void slice_flush_segments(void *parm)
-{
-#ifdef CONFIG_PPC64
- struct mm_struct *mm = parm;
- unsigned long flags;
-
- if (mm != current->active_mm)
- return;
-
- copy_mm_to_paca(current->active_mm);
-
- local_irq_save(flags);
- slb_flush_and_rebolt();
- local_irq_restore(flags);
-#endif
-}
-
static void slice_convert(struct mm_struct *mm,
const struct slice_mask *mask, int psize)
{
@@ -289,6 +272,9 @@ static void slice_convert(struct mm_struct *mm,
spin_unlock_irqrestore(&slice_convert_lock, flags);
copro_flush_all_slbs(mm);
+#ifdef CONFIG_PPC64
+ core_flush_all_slbs(mm);
+#endif
}
/*
@@ -502,8 +488,9 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
* be already initialised beyond the old address limit.
*/
mm->context.slb_addr_limit = high_limit;
-
- on_each_cpu(slice_flush_segments, mm, 1);
+#ifdef CONFIG_PPC64
+ core_flush_all_slbs(mm);
+#endif
}
/* Sanity checks */
@@ -665,8 +652,10 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
(SLICE_NUM_HIGH &&
!bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) {
slice_convert(mm, &potential_mask, psize);
+#ifdef CONFIG_PPC64
if (psize > MMU_PAGE_BASE)
- on_each_cpu(slice_flush_segments, mm, 1);
+ core_flush_all_slbs(mm);
+#endif
}
return newaddr;
--
2.17.0
^ permalink raw reply related [flat|nested] 10+ messages in thread