summaryrefslogtreecommitdiff
path: root/arch/sparc/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/sparc/mm')
-rw-r--r--arch/sparc/mm/fault_64.c6
-rw-r--r--arch/sparc/mm/hugetlbpage.c6
-rw-r--r--arch/sparc/mm/init_32.c2
-rw-r--r--arch/sparc/mm/init_64.c171
-rw-r--r--arch/sparc/mm/tlb.c4
-rw-r--r--arch/sparc/mm/tsb.c38
-rw-r--r--arch/sparc/mm/ultra.S379
7 files changed, 473 insertions, 133 deletions
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index dbabe5713a15..e15f33715103 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -479,14 +479,14 @@ good_area:
up_read(&mm->mmap_sem);
mm_rss = get_mm_rss(mm);
-#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE));
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
#endif
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit))
tsb_grow(mm, MM_TSB_BASE, mm_rss);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- mm_rss = mm->context.huge_pte_count;
+ mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
if (unlikely(mm_rss >
mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 364d093f46c6..ffa842b4d7d4 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
addr = ALIGN(addr, HPAGE_SIZE);
vma = find_vma(mm, addr);
if (task_size - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
if (mm->get_unmapped_area == arch_get_unmapped_area)
@@ -180,7 +180,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
unsigned long nptes;
if (!pte_present(*ptep) && pte_present(entry))
- mm->context.huge_pte_count++;
+ mm->context.hugetlb_pte_count++;
addr &= HPAGE_MASK;
@@ -212,7 +212,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
entry = *ptep;
if (pte_present(entry))
- mm->context.huge_pte_count--;
+ mm->context.hugetlb_pte_count--;
addr &= HPAGE_MASK;
nptes = 1 << HUGETLB_PAGE_ORDER;
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index eb8287155279..3b7092d9ea8f 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -301,7 +301,7 @@ void __init mem_init(void)
/* Saves us work later. */
- memset((void *)&empty_zero_page, 0, PAGE_SIZE);
+ memset((void *)empty_zero_page, 0, PAGE_SIZE);
i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5);
i += 1;
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3c4b8975fa76..c2f376ce443b 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -346,7 +346,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
spin_lock_irqsave(&mm->context.lock, flags);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (mm->context.huge_pte_count && is_hugetlb_pte(pte))
+ if ((mm->context.hugetlb_pte_count || mm->context.thp_pte_count) &&
+ is_hugetlb_pte(pte))
__update_mmu_tsb_insert(mm, MM_TSB_HUGE, REAL_HPAGE_SHIFT,
address, pte_val(pte));
else
@@ -655,10 +656,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
/* get_new_mmu_context() uses "cache + 1". */
DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
#define MAX_CTX_NR (1UL << CTX_NR_BITS)
#define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR)
DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+ unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+ unsigned long new_ver, new_ctx, old_ctx;
+ struct mm_struct *mm;
+ int cpu;
+
+ bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+ /* Reserve kernel context */
+ set_bit(0, mmu_context_bmap);
+
+ new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+ if (unlikely(new_ver == 0))
+ new_ver = CTX_FIRST_VERSION;
+ tlb_context_cache = new_ver;
+
+ /*
+ * Make sure that any new mm that are added into per_cpu_secondary_mm,
+ * are going to go through get_new_mmu_context() path.
+ */
+ mb();
+
+ /*
+ * Updated versions to current on those CPUs that had valid secondary
+ * contexts
+ */
+ for_each_online_cpu(cpu) {
+ /*
+ * If a new mm is stored after we took this mm from the array,
+ * it will go into get_new_mmu_context() path, because we
+ * already bumped the version in tlb_context_cache.
+ */
+ mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+ if (unlikely(!mm || mm == &init_mm))
+ continue;
+
+ old_ctx = mm->context.sparc64_ctx_val;
+ if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+ new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+ set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+ mm->context.sparc64_ctx_val = new_ctx;
+ }
+ }
+}
/* Caller does TLB context flushing on local CPU if necessary.
* The caller also ensures that CTX_VALID(mm->context) is false.
@@ -674,48 +723,30 @@ void get_new_mmu_context(struct mm_struct *mm)
{
unsigned long ctx, new_ctx;
unsigned long orig_pgsz_bits;
- int new_version;
spin_lock(&ctx_alloc_lock);
+retry:
+ /* wrap might have happened, test again if our context became valid */
+ if (unlikely(CTX_VALID(mm->context)))
+ goto out;
orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
- new_version = 0;
if (new_ctx >= (1 << CTX_NR_BITS)) {
new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
if (new_ctx >= ctx) {
- int i;
- new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
- CTX_FIRST_VERSION;
- if (new_ctx == 1)
- new_ctx = CTX_FIRST_VERSION;
-
- /* Don't call memset, for 16 entries that's just
- * plain silly...
- */
- mmu_context_bmap[0] = 3;
- mmu_context_bmap[1] = 0;
- mmu_context_bmap[2] = 0;
- mmu_context_bmap[3] = 0;
- for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
- mmu_context_bmap[i + 0] = 0;
- mmu_context_bmap[i + 1] = 0;
- mmu_context_bmap[i + 2] = 0;
- mmu_context_bmap[i + 3] = 0;
- }
- new_version = 1;
- goto out;
+ mmu_context_wrap();
+ goto retry;
}
}
+ if (mm->context.sparc64_ctx_val)
+ cpumask_clear(mm_cpumask(mm));
mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
tlb_context_cache = new_ctx;
mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
spin_unlock(&ctx_alloc_lock);
-
- if (unlikely(new_version))
- smp_new_mmu_context_version();
}
static int numa_enabled = 1;
@@ -799,8 +830,10 @@ struct mdesc_mblock {
};
static struct mdesc_mblock *mblocks;
static int num_mblocks;
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask);
-static unsigned long ra_to_pa(unsigned long addr)
+static unsigned long __init ra_to_pa(unsigned long addr)
{
int i;
@@ -816,8 +849,11 @@ static unsigned long ra_to_pa(unsigned long addr)
return addr;
}
-static int find_node(unsigned long addr)
+static int __init find_node(unsigned long addr)
{
+ static bool search_mdesc = true;
+ static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL };
+ static int last_index;
int i;
addr = ra_to_pa(addr);
@@ -827,13 +863,30 @@ static int find_node(unsigned long addr)
if ((addr & p->mask) == p->val)
return i;
}
- /* The following condition has been observed on LDOM guests.*/
- WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
- " rule. Some physical memory will be owned by node 0.");
- return 0;
+ /* The following condition has been observed on LDOM guests because
+ * node_masks only contains the best latency mask and value.
+ * LDOM guest's mdesc can contain a single latency group to
+ * cover multiple address range. Print warning message only if the
+ * address cannot be found in node_masks nor mdesc.
+ */
+ if ((search_mdesc) &&
+ ((addr & last_mem_mask.mask) != last_mem_mask.val)) {
+ /* find the available node in the mdesc */
+ last_index = find_numa_node_for_addr(addr, &last_mem_mask);
+ numadbg("find_node: latency group for address 0x%lx is %d\n",
+ addr, last_index);
+ if ((last_index < 0) || (last_index >= num_node_masks)) {
+ /* WARN_ONCE() and use default group 0 */
+ WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.");
+ search_mdesc = false;
+ last_index = 0;
+ }
+ }
+
+ return last_index;
}
-static u64 memblock_nid_range(u64 start, u64 end, int *nid)
+static u64 __init memblock_nid_range(u64 start, u64 end, int *nid)
{
*nid = find_node(start);
start += PAGE_SIZE;
@@ -1157,6 +1210,41 @@ int __node_distance(int from, int to)
return numa_latency[from][to];
}
+static int find_numa_node_for_addr(unsigned long pa,
+ struct node_mem_mask *pnode_mask)
+{
+ struct mdesc_handle *md = mdesc_grab();
+ u64 node, arc;
+ int i = 0;
+
+ node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
+ if (node == MDESC_NODE_NULL)
+ goto out;
+
+ mdesc_for_each_node_by_name(md, node, "group") {
+ mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) {
+ u64 target = mdesc_arc_target(md, arc);
+ struct mdesc_mlgroup *m = find_mlgroup(target);
+
+ if (!m)
+ continue;
+ if ((pa & m->mask) == m->match) {
+ if (pnode_mask) {
+ pnode_mask->mask = m->mask;
+ pnode_mask->val = m->match;
+ }
+ mdesc_release(md);
+ return i;
+ }
+ }
+ i++;
+ }
+
+out:
+ mdesc_release(md);
+ return -1;
+}
+
static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp)
{
int i;
@@ -1435,7 +1523,7 @@ bool kern_addr_valid(unsigned long addr)
if ((long)addr < 0L) {
unsigned long pa = __pa(addr);
- if ((addr >> max_phys_bits) != 0UL)
+ if ((pa >> max_phys_bits) != 0UL)
return false;
return pfn_valid(pa >> PAGE_SHIFT);
@@ -2314,10 +2402,17 @@ void __init mem_init(void)
{
high_memory = __va(last_valid_pfn << PAGE_SHIFT);
- register_page_bootmem_info();
free_all_bootmem();
/*
+ * Must be done after boot memory is put on freelist, because here we
+ * might set fields in deferred struct pages that have not yet been
+ * initialized, and free_all_bootmem() initializes all the reserved
+ * deferred pages for us.
+ */
+ register_page_bootmem_info();
+
+ /*
* Set up the zero page, mark it reserved, so that page count
* is not manipulated when freeing the page from user ptes.
*/
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index f81cd9736700..3659d37b4d81 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -175,9 +175,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
if (pmd_val(pmd) & _PAGE_PMD_HUGE)
- mm->context.huge_pte_count++;
+ mm->context.thp_pte_count++;
else
- mm->context.huge_pte_count--;
+ mm->context.thp_pte_count--;
/* Do not try to allocate the TSB hash table if we
* don't have one already. We have various locks held
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a0604a493a36..266411291634 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -27,6 +27,20 @@ static inline int tag_compare(unsigned long tag, unsigned long vaddr)
return (tag == (vaddr >> 22));
}
+static void flush_tsb_kernel_range_scan(unsigned long start, unsigned long end)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx < KERNEL_TSB_NENTRIES; idx++) {
+ struct tsb *ent = &swapper_tsb[idx];
+ unsigned long match = idx << 13;
+
+ match |= (ent->tag << 22);
+ if (match >= start && match < end)
+ ent->tag = (1UL << TSB_TAG_INVALID_BIT);
+ }
+}
+
/* TSB flushes need only occur on the processor initiating the address
* space modification, not on each cpu the address space has run on.
* Only the TLB flush needs that treatment.
@@ -36,6 +50,9 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
{
unsigned long v;
+ if ((end - start) >> PAGE_SHIFT >= 2 * KERNEL_TSB_NENTRIES)
+ return flush_tsb_kernel_range_scan(start, end);
+
for (v = start; v < end; v += PAGE_SIZE) {
unsigned long hash = tsb_hash(v, PAGE_SHIFT,
KERNEL_TSB_NENTRIES);
@@ -434,7 +451,8 @@ retry_tsb_alloc:
extern void copy_tsb(unsigned long old_tsb_base,
unsigned long old_tsb_size,
unsigned long new_tsb_base,
- unsigned long new_tsb_size);
+ unsigned long new_tsb_size,
+ unsigned long page_size_shift);
unsigned long old_tsb_base = (unsigned long) old_tsb;
unsigned long new_tsb_base = (unsigned long) new_tsb;
@@ -442,7 +460,9 @@ retry_tsb_alloc:
old_tsb_base = __pa(old_tsb_base);
new_tsb_base = __pa(new_tsb_base);
}
- copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+ copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+ tsb_index == MM_TSB_BASE ?
+ PAGE_SHIFT : REAL_HPAGE_SHIFT);
}
mm->context.tsb_block[tsb_index].tsb = new_tsb;
@@ -470,7 +490,7 @@ retry_tsb_alloc:
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- unsigned long huge_pte_count;
+ unsigned long total_huge_pte_count;
#endif
unsigned int i;
@@ -479,12 +499,14 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
mm->context.sparc64_ctx_val = 0UL;
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- /* We reset it to zero because the fork() page copying
+ /* We reset them to zero because the fork() page copying
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
*/
- huge_pte_count = mm->context.huge_pte_count;
- mm->context.huge_pte_count = 0;
+ total_huge_pte_count = mm->context.hugetlb_pte_count +
+ mm->context.thp_pte_count;
+ mm->context.hugetlb_pte_count = 0;
+ mm->context.thp_pte_count = 0;
#endif
/* copy_mm() copies over the parent's mm_struct before calling
@@ -500,8 +522,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
- if (unlikely(huge_pte_count))
- tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
+ if (unlikely(total_huge_pte_count))
+ tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
#endif
if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S
index b4f4733abc6e..fcf4d27a38fb 100644
--- a/arch/sparc/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -30,7 +30,7 @@
.text
.align 32
.globl __flush_tlb_mm
-__flush_tlb_mm: /* 18 insns */
+__flush_tlb_mm: /* 19 insns */
/* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */
ldxa [%o1] ASI_DMMU, %g2
cmp %g2, %o0
@@ -81,7 +81,7 @@ __flush_tlb_page: /* 22 insns */
.align 32
.globl __flush_tlb_pending
-__flush_tlb_pending: /* 26 insns */
+__flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
rdpr %pstate, %g7
sllx %o1, 3, %o1
@@ -113,12 +113,14 @@ __flush_tlb_pending: /* 26 insns */
.align 32
.globl __flush_tlb_kernel_range
-__flush_tlb_kernel_range: /* 16 insns */
+__flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, __spitfire_flush_tlb_kernel_range_slow
sethi %hi(PAGE_SIZE), %o4
- sub %o1, %o0, %o3
sub %o3, %o4, %o3
or %o0, 0x20, %o0 ! Nucleus
1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
@@ -131,6 +133,41 @@ __flush_tlb_kernel_range: /* 16 insns */
retl
nop
nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
+__spitfire_flush_tlb_kernel_range_slow:
+ mov 63 * 8, %o4
+1: ldxa [%o4] ASI_ITLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_IMMU
+ stxa %g0, [%o4] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%o4] ASI_DTLB_DATA_ACCESS, %o3
+ andcc %o3, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %o3
+ stxa %g0, [%o3] ASI_DMMU
+ stxa %g0, [%o4] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %o4, 8, %o4
+ brgez,pt %o4, 1b
+ nop
+ retl
+ nop
__spitfire_flush_tlb_mm_slow:
rdpr %pstate, %g1
@@ -285,6 +322,40 @@ __cheetah_flush_tlb_pending: /* 27 insns */
retl
wrpr %g7, 0x0, %pstate
+__cheetah_flush_tlb_kernel_range: /* 31 insns */
+ /* %o0=start, %o1=end */
+ cmp %o0, %o1
+ be,pn %xcc, 2f
+ sub %o1, %o0, %o3
+ srlx %o3, 18, %o4
+ brnz,pn %o4, 3f
+ sethi %hi(PAGE_SIZE), %o4
+ sub %o3, %o4, %o3
+ or %o0, 0x20, %o0 ! Nucleus
+1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP
+ stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %o3, 1b
+ sub %o3, %o4, %o3
+2: sethi %hi(KERNBASE), %o3
+ flush %o3
+ retl
+ nop
+3: mov 0x80, %o4
+ stxa %g0, [%o4] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%o4] ASI_IMMU_DEMAP
+ membar #Sync
+ retl
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
__cheetah_flush_dcache_page: /* 11 insns */
sethi %hi(PAGE_OFFSET), %g1
@@ -309,19 +380,28 @@ __hypervisor_tlb_tl0_error:
ret
restore
-__hypervisor_flush_tlb_mm: /* 10 insns */
+__hypervisor_flush_tlb_mm: /* 19 insns */
mov %o0, %o2 /* ARG2: mmu context */
mov 0, %o0 /* ARG0: CPU lists unimplemented */
mov 0, %o1 /* ARG1: CPU lists unimplemented */
mov HV_MMU_ALL, %o3 /* ARG3: flags */
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_FAST_MMU_DEMAP_CTX, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o5
+ jmpl %o5 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_page: /* 11 insns */
+__hypervisor_flush_tlb_page: /* 22 insns */
/* %o0 = context, %o1 = vaddr */
mov %o0, %g2
mov %o1, %o0 /* ARG0: vaddr + IMMU-bit */
@@ -330,12 +410,23 @@ __hypervisor_flush_tlb_page: /* 11 insns */
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_pending: /* 16 insns */
+__hypervisor_flush_tlb_pending: /* 27 insns */
/* %o0 = context, %o1 = nr, %o2 = vaddrs[] */
sllx %o1, 3, %g1
mov %o2, %g2
@@ -347,31 +438,57 @@ __hypervisor_flush_tlb_pending: /* 16 insns */
srlx %o0, PAGE_SHIFT, %o0
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 1f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g1, 1b
nop
retl
nop
+1: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
-__hypervisor_flush_tlb_kernel_range: /* 16 insns */
+__hypervisor_flush_tlb_kernel_range: /* 31 insns */
/* %o0=start, %o1=end */
cmp %o0, %o1
be,pn %xcc, 2f
- sethi %hi(PAGE_SIZE), %g3
- mov %o0, %g1
- sub %o1, %g1, %g2
+ sub %o1, %o0, %g2
+ srlx %g2, 18, %g3
+ brnz,pn %g3, 4f
+ mov %o0, %g1
+ sethi %hi(PAGE_SIZE), %g3
sub %g2, %g3, %g2
1: add %g1, %g2, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
- brnz,pn %o0, __hypervisor_tlb_tl0_error
+ brnz,pn %o0, 3f
mov HV_MMU_UNMAP_ADDR_TRAP, %o1
brnz,pt %g2, 1b
sub %g2, %g3, %g2
2: retl
nop
+3: sethi %hi(__hypervisor_tlb_tl0_error), %o2
+ jmpl %o2 + %lo(__hypervisor_tlb_tl0_error), %g0
+ nop
+4: mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ brnz,pn %o0, 3b
+ mov HV_FAST_MMU_DEMAP_CTX, %o1
+ retl
+ nop
#ifdef DCACHE_ALIASING_POSSIBLE
/* XXX Niagara and friends have an 8K cache, so no aliasing is
@@ -394,43 +511,6 @@ tlb_patch_one:
retl
nop
- .globl cheetah_patch_cachetlbops
-cheetah_patch_cachetlbops:
- save %sp, -128, %sp
-
- sethi %hi(__flush_tlb_mm), %o0
- or %o0, %lo(__flush_tlb_mm), %o0
- sethi %hi(__cheetah_flush_tlb_mm), %o1
- or %o1, %lo(__cheetah_flush_tlb_mm), %o1
- call tlb_patch_one
- mov 19, %o2
-
- sethi %hi(__flush_tlb_page), %o0
- or %o0, %lo(__flush_tlb_page), %o0
- sethi %hi(__cheetah_flush_tlb_page), %o1
- or %o1, %lo(__cheetah_flush_tlb_page), %o1
- call tlb_patch_one
- mov 22, %o2
-
- sethi %hi(__flush_tlb_pending), %o0
- or %o0, %lo(__flush_tlb_pending), %o0
- sethi %hi(__cheetah_flush_tlb_pending), %o1
- or %o1, %lo(__cheetah_flush_tlb_pending), %o1
- call tlb_patch_one
- mov 27, %o2
-
-#ifdef DCACHE_ALIASING_POSSIBLE
- sethi %hi(__flush_dcache_page), %o0
- or %o0, %lo(__flush_dcache_page), %o0
- sethi %hi(__cheetah_flush_dcache_page), %o1
- or %o1, %lo(__cheetah_flush_dcache_page), %o1
- call tlb_patch_one
- mov 11, %o2
-#endif /* DCACHE_ALIASING_POSSIBLE */
-
- ret
- restore
-
#ifdef CONFIG_SMP
/* These are all called by the slaves of a cross call, at
* trap level 1, with interrupts fully disabled.
@@ -447,7 +527,7 @@ cheetah_patch_cachetlbops:
*/
.align 32
.globl xcall_flush_tlb_mm
-xcall_flush_tlb_mm: /* 21 insns */
+xcall_flush_tlb_mm: /* 24 insns */
mov PRIMARY_CONTEXT, %g2
ldxa [%g2] ASI_DMMU, %g3
srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4
@@ -469,9 +549,12 @@ xcall_flush_tlb_mm: /* 21 insns */
nop
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_page
-xcall_flush_tlb_page: /* 17 insns */
+xcall_flush_tlb_page: /* 20 insns */
/* %g5=context, %g1=vaddr */
mov PRIMARY_CONTEXT, %g4
ldxa [%g4] ASI_DMMU, %g2
@@ -490,15 +573,20 @@ xcall_flush_tlb_page: /* 17 insns */
retry
nop
nop
+ nop
+ nop
+ nop
.globl xcall_flush_tlb_kernel_range
-xcall_flush_tlb_kernel_range: /* 25 insns */
+xcall_flush_tlb_kernel_range: /* 44 insns */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
- add %g2, 1, %g2
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
sub %g3, %g2, %g3
or %g1, 0x20, %g1 ! Nucleus
1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
@@ -507,8 +595,25 @@ xcall_flush_tlb_kernel_range: /* 25 insns */
brnz,pt %g3, 1b
sub %g3, %g2, %g3
retry
- nop
- nop
+2: mov 63 * 8, %g1
+1: ldxa [%g1] ASI_ITLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0 /* _PAGE_L_4U */
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_IMMU
+ stxa %g0, [%g1] ASI_ITLB_DATA_ACCESS
+ membar #Sync
+2: ldxa [%g1] ASI_DTLB_DATA_ACCESS, %g2
+ andcc %g2, 0x40, %g0
+ bne,pn %xcc, 2f
+ mov TLB_TAG_ACCESS, %g2
+ stxa %g0, [%g2] ASI_DMMU
+ stxa %g0, [%g1] ASI_DTLB_DATA_ACCESS
+ membar #Sync
+2: sub %g1, 8, %g1
+ brgez,pt %g1, 1b
+ nop
+ retry
nop
nop
nop
@@ -637,6 +742,52 @@ xcall_fetch_glob_pmu_n4:
retry
+__cheetah_xcall_flush_tlb_kernel_range: /* 44 insns */
+ sethi %hi(PAGE_SIZE - 1), %g2
+ or %g2, %lo(PAGE_SIZE - 1), %g2
+ andn %g1, %g2, %g1
+ andn %g7, %g2, %g7
+ sub %g7, %g1, %g3
+ srlx %g3, 18, %g2
+ brnz,pn %g2, 2f
+ add %g2, 1, %g2
+ sub %g3, %g2, %g3
+ or %g1, 0x20, %g1 ! Nucleus
+1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP
+ stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP
+ membar #Sync
+ brnz,pt %g3, 1b
+ sub %g3, %g2, %g3
+ retry
+2: mov 0x80, %g2
+ stxa %g0, [%g2] ASI_DMMU_DEMAP
+ membar #Sync
+ stxa %g0, [%g2] ASI_IMMU_DEMAP
+ membar #Sync
+ retry
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+ nop
+
#ifdef DCACHE_ALIASING_POSSIBLE
.align 32
.globl xcall_flush_dcache_page_cheetah
@@ -700,7 +851,7 @@ __hypervisor_tlb_xcall_error:
ba,a,pt %xcc, rtrap
.globl __hypervisor_xcall_flush_tlb_mm
-__hypervisor_xcall_flush_tlb_mm: /* 21 insns */
+__hypervisor_xcall_flush_tlb_mm: /* 24 insns */
/* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */
mov %o0, %g2
mov %o1, %g3
@@ -714,7 +865,7 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
mov HV_FAST_MMU_DEMAP_CTX, %o5
ta HV_FAST_TRAP
mov HV_FAST_MMU_DEMAP_CTX, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
@@ -723,9 +874,12 @@ __hypervisor_xcall_flush_tlb_mm: /* 21 insns */
mov %g7, %o5
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_page
-__hypervisor_xcall_flush_tlb_page: /* 17 insns */
+__hypervisor_xcall_flush_tlb_page: /* 20 insns */
/* %g5=ctx, %g1=vaddr */
mov %o0, %g2
mov %o1, %g3
@@ -737,42 +891,64 @@ __hypervisor_xcall_flush_tlb_page: /* 17 insns */
sllx %o0, PAGE_SHIFT, %o0
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,a,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,a,pn %o0, 1f
mov %o0, %g5
mov %g2, %o0
mov %g3, %o1
mov %g4, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
.globl __hypervisor_xcall_flush_tlb_kernel_range
-__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */
+__hypervisor_xcall_flush_tlb_kernel_range: /* 44 insns */
/* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */
sethi %hi(PAGE_SIZE - 1), %g2
or %g2, %lo(PAGE_SIZE - 1), %g2
andn %g1, %g2, %g1
andn %g7, %g2, %g7
sub %g7, %g1, %g3
+ srlx %g3, 18, %g7
add %g2, 1, %g2
sub %g3, %g2, %g3
mov %o0, %g2
mov %o1, %g4
- mov %o2, %g7
+ brnz,pn %g7, 2f
+ mov %o2, %g7
1: add %g1, %g3, %o0 /* ARG0: virtual address */
mov 0, %o1 /* ARG1: mmu context */
mov HV_MMU_ALL, %o2 /* ARG2: flags */
ta HV_MMU_UNMAP_ADDR_TRAP
mov HV_MMU_UNMAP_ADDR_TRAP, %g6
- brnz,pn %o0, __hypervisor_tlb_xcall_error
+ brnz,pn %o0, 1f
mov %o0, %g5
sethi %hi(PAGE_SIZE), %o2
brnz,pt %g3, 1b
sub %g3, %o2, %g3
- mov %g2, %o0
+5: mov %g2, %o0
mov %g4, %o1
mov %g7, %o2
membar #Sync
retry
+1: sethi %hi(__hypervisor_tlb_xcall_error), %g4
+ jmpl %g4 + %lo(__hypervisor_tlb_xcall_error), %g0
+ nop
+2: mov %o3, %g1
+ mov %o5, %g3
+ mov 0, %o0 /* ARG0: CPU lists unimplemented */
+ mov 0, %o1 /* ARG1: CPU lists unimplemented */
+ mov 0, %o2 /* ARG2: mmu context == nucleus */
+ mov HV_MMU_ALL, %o3 /* ARG3: flags */
+ mov HV_FAST_MMU_DEMAP_CTX, %o5
+ ta HV_FAST_TRAP
+ mov %g1, %o3
+ brz,pt %o0, 5b
+ mov %g3, %o5
+ mov HV_FAST_MMU_DEMAP_CTX, %g6
+ ba,pt %xcc, 1b
+ clr %g5
/* These just get rescheduled to PIL vectors. */
.globl xcall_call_function
@@ -795,11 +971,6 @@ xcall_capture:
wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint
retry
- .globl xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
- wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
- retry
-
#ifdef CONFIG_KGDB
.globl xcall_kgdb_capture
xcall_kgdb_capture:
@@ -809,6 +980,58 @@ xcall_kgdb_capture:
#endif /* CONFIG_SMP */
+ .globl cheetah_patch_cachetlbops
+cheetah_patch_cachetlbops:
+ save %sp, -128, %sp
+
+ sethi %hi(__flush_tlb_mm), %o0
+ or %o0, %lo(__flush_tlb_mm), %o0
+ sethi %hi(__cheetah_flush_tlb_mm), %o1
+ or %o1, %lo(__cheetah_flush_tlb_mm), %o1
+ call tlb_patch_one
+ mov 19, %o2
+
+ sethi %hi(__flush_tlb_page), %o0
+ or %o0, %lo(__flush_tlb_page), %o0
+ sethi %hi(__cheetah_flush_tlb_page), %o1
+ or %o1, %lo(__cheetah_flush_tlb_page), %o1
+ call tlb_patch_one
+ mov 22, %o2
+
+ sethi %hi(__flush_tlb_pending), %o0
+ or %o0, %lo(__flush_tlb_pending), %o0
+ sethi %hi(__cheetah_flush_tlb_pending), %o1
+ or %o1, %lo(__cheetah_flush_tlb_pending), %o1
+ call tlb_patch_one
+ mov 27, %o2
+
+ sethi %hi(__flush_tlb_kernel_range), %o0
+ or %o0, %lo(__flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 31, %o2
+
+#ifdef DCACHE_ALIASING_POSSIBLE
+ sethi %hi(__flush_dcache_page), %o0
+ or %o0, %lo(__flush_dcache_page), %o0
+ sethi %hi(__cheetah_flush_dcache_page), %o1
+ or %o1, %lo(__cheetah_flush_dcache_page), %o1
+ call tlb_patch_one
+ mov 11, %o2
+#endif /* DCACHE_ALIASING_POSSIBLE */
+
+#ifdef CONFIG_SMP
+ sethi %hi(xcall_flush_tlb_kernel_range), %o0
+ or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
+ sethi %hi(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ or %o1, %lo(__cheetah_xcall_flush_tlb_kernel_range), %o1
+ call tlb_patch_one
+ mov 44, %o2
+#endif /* CONFIG_SMP */
+
+ ret
+ restore
.globl hypervisor_patch_cachetlbops
hypervisor_patch_cachetlbops:
@@ -819,28 +1042,28 @@ hypervisor_patch_cachetlbops:
sethi %hi(__hypervisor_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_flush_tlb_mm), %o1
call tlb_patch_one
- mov 10, %o2
+ mov 19, %o2
sethi %hi(__flush_tlb_page), %o0
or %o0, %lo(__flush_tlb_page), %o0
sethi %hi(__hypervisor_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_flush_tlb_page), %o1
call tlb_patch_one
- mov 11, %o2
+ mov 22, %o2
sethi %hi(__flush_tlb_pending), %o0
or %o0, %lo(__flush_tlb_pending), %o0
sethi %hi(__hypervisor_flush_tlb_pending), %o1
or %o1, %lo(__hypervisor_flush_tlb_pending), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 27, %o2
sethi %hi(__flush_tlb_kernel_range), %o0
or %o0, %lo(__flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 16, %o2
+ mov 31, %o2
#ifdef DCACHE_ALIASING_POSSIBLE
sethi %hi(__flush_dcache_page), %o0
@@ -857,21 +1080,21 @@ hypervisor_patch_cachetlbops:
sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1
call tlb_patch_one
- mov 21, %o2
+ mov 24, %o2
sethi %hi(xcall_flush_tlb_page), %o0
or %o0, %lo(xcall_flush_tlb_page), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_page), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_page), %o1
call tlb_patch_one
- mov 17, %o2
+ mov 20, %o2
sethi %hi(xcall_flush_tlb_kernel_range), %o0
or %o0, %lo(xcall_flush_tlb_kernel_range), %o0
sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1
or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1
call tlb_patch_one
- mov 25, %o2
+ mov 44, %o2
#endif /* CONFIG_SMP */
ret
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-08 16:03:27 +0000