aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/mm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r--arch/powerpc/mm/gup.c13
-rw-r--r--arch/powerpc/mm/hash_low_64.S44
-rw-r--r--arch/powerpc/mm/hash_native_64.c38
-rw-r--r--arch/powerpc/mm/hash_utils_64.c132
-rw-r--r--arch/powerpc/mm/hugetlbpage.c10
-rw-r--r--arch/powerpc/mm/mem.c7
-rw-r--r--arch/powerpc/mm/mmu_context_nohash.c12
-rw-r--r--arch/powerpc/mm/numa.c16
-rw-r--r--arch/powerpc/mm/pgtable_64.c17
-rw-r--r--arch/powerpc/mm/slb.c14
-rw-r--r--arch/powerpc/mm/slb_low.S14
-rw-r--r--arch/powerpc/mm/subpage-prot.c2
-rw-r--r--arch/powerpc/mm/tlb_low_64e.S66
-rw-r--r--arch/powerpc/mm/tlb_nohash.c18
14 files changed, 255 insertions, 148 deletions
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index c5f734e20b0..d8746684f60 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -36,6 +36,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
do {
pte_t pte = ACCESS_ONCE(*ptep);
struct page *page;
+ /*
+ * Similar to the PMD case, NUMA hinting must take slow path
+ */
+ if (pte_numa(pte))
+ return 0;
if ((pte_val(pte) & mask) != result)
return 0;
@@ -75,6 +80,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
if (pmd_huge(pmd) || pmd_large(pmd)) {
+ /*
+ * NUMA hinting faults need to be handled in the GUP
+ * slowpath for accounting purposes and so that they
+ * can be serialised against THP migration.
+ */
+ if (pmd_numa(pmd))
+ return 0;
+
if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
write, pages, nr))
return 0;
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 1136d26a95a..057cbbb4c57 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -159,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -201,7 +201,8 @@ htab_insert_pte:
li r8,MMU_PAGE_4K /* page size */
li r9,MMU_PAGE_4K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
bge htab_pte_insert_ok /* Insertion successful */
@@ -225,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1)
li r8,MMU_PAGE_4K /* page size */
li r9,MMU_PAGE_4K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
bl . /* Patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ htab_pte_insert_ok /* Insertion successful */
@@ -242,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
bl . /* Patched by htab_finish_init() */
/* Try all again */
@@ -296,7 +299,8 @@ htab_modify_pte:
li r7,MMU_PAGE_4K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
ld r9,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
bl . /* Patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here
@@ -471,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -526,7 +530,8 @@ htab_special_pfn:
li r8,MMU_PAGE_4K /* page size */
li r9,MMU_PAGE_4K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge htab_pte_insert_ok /* Insertion successful */
@@ -554,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1)
li r8,MMU_PAGE_4K /* page size */
li r9,MMU_PAGE_4K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ htab_pte_insert_ok /* Insertion successful */
@@ -571,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
bl . /* patched by htab_finish_init() */
/* Try all again */
@@ -588,7 +595,7 @@ htab_inval_old_hpte:
li r6,MMU_PAGE_64K /* psize */
ld r7,STK_PARAM(R9)(r1) /* ssize */
ld r8,STK_PARAM(R8)(r1) /* local */
- bl .flush_hash_page
+ bl flush_hash_page
/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
lis r0,_PAGE_HPTE_SUB@h
ori r0,r0,_PAGE_HPTE_SUB@l
@@ -660,7 +667,8 @@ htab_modify_pte:
li r7,MMU_PAGE_4K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
ld r9,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here
@@ -812,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
BEGIN_FTR_SECTION
mr r4,r30
mr r5,r7
- bl .hash_page_do_lazy_icache
+ bl hash_page_do_lazy_icache
END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
/* At this point, r3 contains new PP bits, save them in
@@ -857,7 +865,8 @@ ht64_insert_pte:
li r8,MMU_PAGE_64K
li r9,MMU_PAGE_64K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(ht64_call_hpte_insert1)
+.globl ht64_call_hpte_insert1
+ht64_call_hpte_insert1:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge ht64_pte_insert_ok /* Insertion successful */
@@ -881,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1)
li r8,MMU_PAGE_64K
li r9,MMU_PAGE_64K /* actual page size */
ld r10,STK_PARAM(R9)(r1) /* segment size */
-_GLOBAL(ht64_call_hpte_insert2)
+.globl ht64_call_hpte_insert2
+ht64_call_hpte_insert2:
bl . /* patched by htab_finish_init() */
cmpdi 0,r3,0
bge+ ht64_pte_insert_ok /* Insertion successful */
@@ -898,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2)
2: and r0,r5,r27
rldicr r3,r0,3,63-3 /* r0 = (hash & mask) << 3 */
/* Call ppc_md.hpte_remove */
-_GLOBAL(ht64_call_hpte_remove)
+.globl ht64_call_hpte_remove
+ht64_call_hpte_remove:
bl . /* patched by htab_finish_init() */
/* Try all again */
@@ -952,7 +963,8 @@ ht64_modify_pte:
li r7,MMU_PAGE_64K /* actual page size */
ld r8,STK_PARAM(R9)(r1) /* segment size */
ld r9,STK_PARAM(R8)(r1) /* get "local" param */
-_GLOBAL(ht64_call_hpte_updatepp)
+.globl ht64_call_hpte_updatepp
+ht64_call_hpte_updatepp:
bl . /* patched by htab_finish_init() */
/* if we failed because typically the HPTE wasn't really here
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3ea26c25590..cf1d325eae8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -82,17 +82,14 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
- /* Add AVAL part */
- if (psize != apsize) {
- /*
- * MPSS, 64K base page size and 16MB parge page size
- * We don't need all the bits, but rest of the bits
- * must be ignored by the processor.
- * vpn cover upto 65 bits of va. (0...65) and we need
- * 58..64 bits of va.
- */
- va |= (vpn & 0xfe);
- }
+ /*
+ * AVAL bits:
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe); /* AVAL */
va |= 1; /* L */
asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
: : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -133,17 +130,14 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
- /* Add AVAL part */
- if (psize != apsize) {
- /*
- * MPSS, 64K base page size and 16MB parge page size
- * We don't need all the bits, but rest of the bits
- * must be ignored by the processor.
- * vpn cover upto 65 bits of va. (0...65) and we need
- * 58..64 bits of va.
- */
- va |= (vpn & 0xfe);
- }
+ /*
+ * AVAL bits:
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe);
va |= 1; /* L */
asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
: : "r"(va) : "memory");
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index de6881259ae..88fdd9d2507 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,24 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
if (overlaps_kernel_text(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
+ /* Make kvm guest trampolines executable */
+ if (overlaps_kvm_tmp(vaddr, vaddr + step))
+ tprot &= ~HPTE_R_N;
+
+ /*
+ * If relocatable, check if it overlaps interrupt vectors that
+ * are copied down to real 0. For relocatable kernel
+ * (e.g. kdump case) we copy interrupt vectors down to real
+ * address 0. Mark that region as executable. This is
+ * because on p8 system with relocation on exception feature
+ * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence
+ * in order to execute the interrupt handlers in virtual
+ * mode the vector region need to be marked as executable.
+ */
+ if ((PHYSICAL_START > MEMORY_START) &&
+ overlaps_interrupt_vector_text(vaddr, vaddr + step))
+ tprot &= ~HPTE_R_N;
+
hash = hpt_hash(vpn, shift, ssize);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
@@ -251,9 +269,9 @@ static int __init htab_dt_scan_seg_sizes(unsigned long node,
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- __be32 *prop;
- unsigned long size = 0;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
@@ -306,9 +324,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- __be32 *prop;
- unsigned long size = 0;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
@@ -388,9 +406,9 @@ static int __init htab_dt_scan_page_sizes(unsigned long node,
static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
const char *uname, int depth,
void *data) {
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- __be64 *addr_prop;
- __be32 *page_count_prop;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be64 *addr_prop;
+ const __be32 *page_count_prop;
unsigned int expected_pages;
long unsigned int phys_addr;
long unsigned int block_size;
@@ -431,6 +449,24 @@ static void mmu_psize_set_default_penc(void)
mmu_psize_defs[bpsize].penc[apsize] = -1;
}
+#ifdef CONFIG_PPC_64K_PAGES
+
+static bool might_have_hea(void)
+{
+ /*
+ * The HEA ethernet adapter requires awareness of the
+ * GX bus. Without that awareness we can easily assume
+ * we will never see an HEA ethernet device.
+ */
+#ifdef CONFIG_IBMEBUS
+ return !cpu_has_feature(CPU_FTR_ARCH_207S);
+#else
+ return false;
+#endif
+}
+
+#endif /* #ifdef CONFIG_PPC_64K_PAGES */
+
static void __init htab_init_page_sizes(void)
{
int rc;
@@ -485,10 +521,11 @@ static void __init htab_init_page_sizes(void)
mmu_linear_psize = MMU_PAGE_64K;
if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
/*
- * Don't use 64k pages for ioremap on pSeries, since
- * that would stop us accessing the HEA ethernet.
+ * When running on pSeries using 64k pages for ioremap
+ * would stop us accessing the HEA ethernet. So if we
+ * have the chance of ever seeing one, stay at 4k.
*/
- if (!machine_is(pseries))
+ if (!might_have_hea() || !machine_is(pseries))
mmu_io_psize = MMU_PAGE_64K;
} else
mmu_ci_restrictions = 1;
@@ -532,8 +569,8 @@ static int __init htab_dt_scan_pftsize(unsigned long node,
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- __be32 *prop;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
@@ -589,47 +626,43 @@ int remove_section_mapping(unsigned long start, unsigned long end)
}
#endif /* CONFIG_MEMORY_HOTPLUG */
-#define FUNCTION_TEXT(A) ((*(unsigned long *)(A)))
+extern u32 htab_call_hpte_insert1[];
+extern u32 htab_call_hpte_insert2[];
+extern u32 htab_call_hpte_remove[];
+extern u32 htab_call_hpte_updatepp[];
+extern u32 ht64_call_hpte_insert1[];
+extern u32 ht64_call_hpte_insert2[];
+extern u32 ht64_call_hpte_remove[];
+extern u32 ht64_call_hpte_updatepp[];
static void __init htab_finish_init(void)
{
- extern unsigned int *htab_call_hpte_insert1;
- extern unsigned int *htab_call_hpte_insert2;
- extern unsigned int *htab_call_hpte_remove;
- extern unsigned int *htab_call_hpte_updatepp;
-
#ifdef CONFIG_PPC_HAS_HASH_64K
- extern unsigned int *ht64_call_hpte_insert1;
- extern unsigned int *ht64_call_hpte_insert2;
- extern unsigned int *ht64_call_hpte_remove;
- extern unsigned int *ht64_call_hpte_updatepp;
-
patch_branch(ht64_call_hpte_insert1,
- FUNCTION_TEXT(ppc_md.hpte_insert),
+ ppc_function_entry(ppc_md.hpte_insert),
BRANCH_SET_LINK);
patch_branch(ht64_call_hpte_insert2,
- FUNCTION_TEXT(ppc_md.hpte_insert),
+ ppc_function_entry(ppc_md.hpte_insert),
BRANCH_SET_LINK);
patch_branch(ht64_call_hpte_remove,
- FUNCTION_TEXT(ppc_md.hpte_remove),
+ ppc_function_entry(ppc_md.hpte_remove),
BRANCH_SET_LINK);
patch_branch(ht64_call_hpte_updatepp,
- FUNCTION_TEXT(ppc_md.hpte_updatepp),
+ ppc_function_entry(ppc_md.hpte_updatepp),
BRANCH_SET_LINK);
-
#endif /* CONFIG_PPC_HAS_HASH_64K */
patch_branch(htab_call_hpte_insert1,
- FUNCTION_TEXT(ppc_md.hpte_insert),
+ ppc_function_entry(ppc_md.hpte_insert),
BRANCH_SET_LINK);
patch_branch(htab_call_hpte_insert2,
- FUNCTION_TEXT(ppc_md.hpte_insert),
+ ppc_function_entry(ppc_md.hpte_insert),
BRANCH_SET_LINK);
patch_branch(htab_call_hpte_remove,
- FUNCTION_TEXT(ppc_md.hpte_remove),
+ ppc_function_entry(ppc_md.hpte_remove),
BRANCH_SET_LINK);
patch_branch(htab_call_hpte_updatepp,
- FUNCTION_TEXT(ppc_md.hpte_updatepp),
+ ppc_function_entry(ppc_md.hpte_updatepp),
BRANCH_SET_LINK);
}
@@ -946,6 +979,22 @@ 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)) {
+ get_paca()->context = mm->context;
+ 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
@@ -1067,6 +1116,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
WARN_ON(1);
}
#endif
+ check_paca_psize(ea, mm, psize, user_region);
+
goto bail;
}
@@ -1107,17 +1158,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
#endif
}
}
- if (user_region) {
- if (psize != get_paca_psize(ea)) {
- get_paca()->context = mm->context;
- 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();
- }
+
+ check_paca_psize(ea, mm, psize, user_region);
#endif /* CONFIG_PPC_64K_PAGES */
#ifdef CONFIG_PPC_HAS_HASH_64K
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index eb923654ba8..7e70ae968e5 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -86,11 +86,6 @@ int pgd_huge(pgd_t pgd)
*/
return ((pgd_val(pgd) & 0x3) != 0x0);
}
-
-int pmd_huge_support(void)
-{
- return 1;
-}
#else
int pmd_huge(pmd_t pmd)
{
@@ -106,11 +101,6 @@ int pgd_huge(pgd_t pgd)
{
return 0;
}
-
-int pmd_huge_support(void)
-{
- return 0;
-}
#endif
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 4b5cd5c2594..2c8e90f5789 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -139,9 +139,14 @@ int arch_remove_memory(u64 start, u64 size)
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
struct zone *zone;
+ int ret;
zone = page_zone(pfn_to_page(start_pfn));
- return __remove_pages(zone, start_pfn, nr_pages);
+ ret = __remove_pages(zone, start_pfn, nr_pages);
+ if (!ret && (ppc_md.remove_memory))
+ ret = ppc_md.remove_memory(start, size);
+
+ return ret;
}
#endif
#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index af3d78e1930..928ebe79668 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -410,17 +410,7 @@ void __init mmu_context_init(void)
} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
first_context = 1;
last_context = 65535;
- } else
-#ifdef CONFIG_PPC_BOOK3E_MMU
- if (mmu_has_feature(MMU_FTR_TYPE_3E)) {
- u32 mmucfg = mfspr(SPRN_MMUCFG);
- u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK)
- >> MMUCFG_PIDSIZE_SHIFT;
- first_context = 1;
- last_context = (1UL << (pid_bits + 1)) - 1;
- } else
-#endif
- {
+ } else {
first_context = 1;
last_context = 255;
}
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 30a42e24bf1..3b181b22cd4 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -232,6 +232,7 @@ int __node_distance(int a, int b)
return distance;
}
+EXPORT_SYMBOL(__node_distance);
static void initialize_distance_lookup_table(int nid,
const __be32 *associativity)
@@ -1591,6 +1592,20 @@ int arch_update_cpu_topology(void)
cpu = cpu_last_thread_sibling(cpu);
}
+ /*
+ * In cases where we have nothing to update (because the updates list
+ * is too short or because the new topology is same as the old one),
+ * skip invoking update_cpu_topology() via stop-machine(). This is
+ * necessary (and not just a fast-path optimization) since stop-machine
+ * can end up electing a random CPU to run update_cpu_topology(), and
+ * thus trick us into setting up incorrect cpu-node mappings (since
+ * 'updates' is kzalloc()'ed).
+ *
+ * And for the similar reason, we will skip all the following updating.
+ */
+ if (!cpumask_weight(&updated_cpus))
+ goto out;
+
stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
/*
@@ -1612,6 +1627,7 @@ int arch_update_cpu_topology(void)
changed = 1;
}
+out:
kfree(updates);
return changed;
}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 65b7b65e870..f6ce1f111f5 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
}
unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp, unsigned long clr)
+ pmd_t *pmdp, unsigned long clr,
+ unsigned long set)
{
unsigned long old, tmp;
@@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
+ or %1,%1,%7\n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
- : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+ : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set)
: "cc" );
#else
old = pmd_val(*pmdp);
- *pmdp = __pmd(old & ~clr);
+ *pmdp = __pmd((old & ~clr) | set);
#endif
if (old & _PAGE_HASHPTE)
hpte_do_hugepage_flush(mm, addr, pmdp);
@@ -645,6 +647,11 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
if (old & _PAGE_HASHPTE)
hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
}
+ /*
+ * This ensures that generic code that rely on IRQ disabling
+ * to prevent a parallel THP split work as expected.
+ */
+ kick_all_cpus_sync();
}
/*
@@ -708,7 +715,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
- pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+ pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
}
/*
@@ -835,7 +842,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
unsigned long old;
pgtable_t *pgtable_slot;
- old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+ old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
old_pmd = __pmd(old);
/*
* We have pmd == none and we are holding page_table_lock.
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 9d1d33cd2be..0399a670295 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -97,7 +97,7 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
static void __slb_flush_and_rebolt(void)
{
/* If you change this make sure you change SLB_NUM_BOLTED
- * appropriately too. */
+ * and PR KVM appropriately too. */
unsigned long linear_llp, vmalloc_llp, lflags, vflags;
unsigned long ksp_esid_data, ksp_vsid_data;
@@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
patch_instruction(insn_addr, insn);
}
+extern u32 slb_compare_rr_to_size[];
+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)
{
- extern unsigned int *slb_compare_rr_to_size;
-
if (mmu_slb_size == size)
return;
@@ -272,11 +276,7 @@ void slb_initialize(void)
unsigned long linear_llp, vmalloc_llp, io_llp;
unsigned long lflags, vflags;
static int slb_encoding_inited;
- extern unsigned int *slb_miss_kernel_load_linear;
- extern unsigned int *slb_miss_kernel_load_io;
- extern unsigned int *slb_compare_rr_to_size;
#ifdef CONFIG_SPARSEMEM_VMEMMAP
- extern unsigned int *slb_miss_kernel_load_vmemmap;
unsigned long vmemmap_llp;
#endif
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 17aa6dfceb3..736d18b3cef 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -35,7 +35,7 @@ _GLOBAL(slb_allocate_realmode)
* check for bad kernel/user address
* (ea & ~REGION_MASK) >= PGTABLE_RANGE
*/
- rldicr. r9,r3,4,(63 - 46 - 4)
+ rldicr. r9,r3,4,(63 - PGTABLE_EADDR_SIZE - 4)
bne- 8f
srdi r9,r3,60 /* get region */
@@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode)
/* Linear mapping encoding bits, the "li" instruction below will
* be patched by the kernel at boot
*/
-_GLOBAL(slb_miss_kernel_load_linear)
+.globl slb_miss_kernel_load_linear
+slb_miss_kernel_load_linear:
li r11,0
/*
* context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
@@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
/* Check virtual memmap region. To be patches at kernel boot */
cmpldi cr0,r9,0xf
bne 1f
-_GLOBAL(slb_miss_kernel_load_vmemmap)
+.globl slb_miss_kernel_load_vmemmap
+slb_miss_kernel_load_vmemmap:
li r11,0
b 6f
1:
@@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
b 6f
5:
/* IO mapping */
- _GLOBAL(slb_miss_kernel_load_io)
+.globl slb_miss_kernel_load_io
+slb_miss_kernel_load_io:
li r11,0
6:
/*
@@ -250,7 +253,8 @@ slb_finish_load:
7: ld r10,PACASTABRR(r13)
addi r10,r10,1
/* This gets soft patched on boot. */
-_GLOBAL(slb_compare_rr_to_size)
+.globl slb_compare_rr_to_size
+slb_compare_rr_to_size:
cmpldi r10,0
blt+ 4f
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index a770df2dae7..6c0b1f5f8d2 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
for (; npages > 0; --npages) {
- pte_update(mm, addr, pte, 0, 0);
+ pte_update(mm, addr, pte, 0, 0, 0);
addr += PAGE_SIZE;
++pte;
}
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index c95eb323e9a..356e8b41fb0 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -39,37 +39,49 @@
* *
**********************************************************************/
+/*
+ * Note that, unlike non-bolted handlers, TLB_EXFRAME is not
+ * modified by the TLB miss handlers themselves, since the TLB miss
+ * handler code will not itself cause a recursive TLB miss.
+ *
+ * TLB_EXFRAME will be modified when crit/mc/debug exceptions are
+ * entered/exited.
+ */
.macro tlb_prolog_bolted intnum addr
- mtspr SPRN_SPRG_GEN_SCRATCH,r13
+ mtspr SPRN_SPRG_GEN_SCRATCH,r12
+ mfspr r12,SPRN_SPRG_TLB_EXFRAME
+ std r13,EX_TLB_R13(r12)
+ std r10,EX_TLB_R10(r12)
mfspr r13,SPRN_SPRG_PACA
- std r10,PACA_EXTLB+EX_TLB_R10(r13)
+
mfcr r10
- std r11,PACA_EXTLB+EX_TLB_R11(r13)
+ std r11,EX_TLB_R11(r12)
#ifdef CONFIG_KVM_BOOKE_HV
BEGIN_FTR_SECTION
mfspr r11, SPRN_SRR1
END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
#endif
DO_KVM \intnum, SPRN_SRR1
- std r16,PACA_EXTLB+EX_TLB_R16(r13)
+ std r16,EX_TLB_R16(r12)
mfspr r16,\addr /* get faulting address */
- std r14,PACA_EXTLB+EX_TLB_R14(r13)
+ std r14,EX_TLB_R14(r12)
ld r14,PACAPGD(r13)
- std r15,PACA_EXTLB+EX_TLB_R15(r13)
- std r10,PACA_EXTLB+EX_TLB_CR(r13)
- TLB_MISS_PROLOG_STATS_BOLTED
+ std r15,EX_TLB_R15(r12)
+ std r10,EX_TLB_CR(r12)
+ TLB_MISS_PROLOG_STATS
.endm
.macro tlb_epilog_bolted
- ld r14,PACA_EXTLB+EX_TLB_CR(r13)
- ld r10,PACA_EXTLB+EX_TLB_R10(r13)
- ld r11,PACA_EXTLB+EX_TLB_R11(r13)
+ ld r14,EX_TLB_CR(r12)
+ ld r10,EX_TLB_R10(r12)
+ ld r11,EX_TLB_R11(r12)
+ ld r13,EX_TLB_R13(r12)
mtcr r14
- ld r14,PACA_EXTLB+EX_TLB_R14(r13)
- ld r15,PACA_EXTLB+EX_TLB_R15(r13)
- TLB_MISS_RESTORE_STATS_BOLTED
- ld r16,PACA_EXTLB+EX_TLB_R16(r13)
- mfspr r13,SPRN_SPRG_GEN_SCRATCH
+ ld r14,EX_TLB_R14(r12)
+ ld r15,EX_TLB_R15(r12)
+ TLB_MISS_RESTORE_STATS
+ ld r16,EX_TLB_R16(r12)
+ mfspr r12,SPRN_SPRG_GEN_SCRATCH
.endm
/* Data TLB miss */
@@ -284,7 +296,7 @@ itlb_miss_fault_bolted:
* r14 = page table base
* r13 = PACA
* r11 = tlb_per_core ptr
- * r10 = crap (free to use)
+ * r10 = cpu number
*/
tlb_miss_common_e6500:
/*
@@ -293,15 +305,18 @@ tlb_miss_common_e6500:
*
* MAS6:IND should be already set based on MAS4
*/
- addi r10,r11,TCD_LOCK
-1: lbarx r15,0,r10
+1: lbarx r15,0,r11
+ lhz r10,PACAPACAINDEX(r13)
cmpdi r15,0
+ cmpdi cr1,r15,1 /* set cr1.eq = 0 for non-recursive */
bne 2f
- li r15,1
- stbcx. r15,0,r10
+ stbcx. r10,0,r11
bne 1b
+3:
.subsection 1
-2: lbz r15,0(r10)
+2: cmpd cr1,r15,r10 /* recursive lock due to mcheck/crit/etc? */
+ beq cr1,3b /* unlock will happen if cr1.eq = 0 */
+ lbz r15,0(r11)
cmpdi r15,0
bne 2b
b 1b
@@ -379,9 +394,11 @@ tlb_miss_common_e6500:
tlb_miss_done_e6500:
.macro tlb_unlock_e6500
+ beq cr1,1f /* no unlock if lock was recursively grabbed */
li r15,0
isync
- stb r15,TCD_LOCK(r11)
+ stb r15,0(r11)
+1:
.endm
tlb_unlock_e6500
@@ -1091,7 +1108,8 @@ tlb_load_linear:
ld r11,PACATOC(r13)
ld r11,linear_map_top@got(r11)
ld r10,0(r11)
- cmpld cr0,r10,r16
+ tovirt(10,10)
+ cmpld cr0,r16,r10
bge tlb_load_linear_fault
/* MAS1 need whole new setup. */
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index b37a58e1c92..92cb18d52ea 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -144,6 +144,15 @@ int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
unsigned long linear_map_top; /* Top of linear mapping */
+
+/*
+ * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
+ * exceptions. This is used for bolted and e6500 TLB miss handlers which
+ * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
+ * this is set to zero.
+ */
+int extlb_level_exc;
+
#endif /* CONFIG_PPC64 */
#ifdef CONFIG_PPC_FSL_BOOK3E
@@ -559,6 +568,7 @@ static void setup_mmu_htw(void)
break;
#ifdef CONFIG_PPC_FSL_BOOK3E
case PPC_HTW_E6500:
+ extlb_level_exc = EX_TLB_SIZE;
patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
break;
@@ -586,8 +596,13 @@ static void __early_init_mmu(int boot_cpu)
/* XXX This should be decided at runtime based on supported
* page sizes in the TLB, but for now let's assume 16M is
* always there and a good fit (which it probably is)
+ *
+ * Freescale booke only supports 4K pages in TLB0, so use that.
*/
- mmu_vmemmap_psize = MMU_PAGE_16M;
+ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+ mmu_vmemmap_psize = MMU_PAGE_4K;
+ else
+ mmu_vmemmap_psize = MMU_PAGE_16M;
/* XXX This code only checks for TLB 0 capabilities and doesn't
* check what page size combos are supported by the HW. It
@@ -652,6 +667,7 @@ static void __early_init_mmu(int boot_cpu)
memblock_enforce_memory_limit(linear_map_top);
if (book3e_htw_mode == PPC_HTW_NONE) {
+ extlb_level_exc = EX_TLB_SIZE;
patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
patch_exception(0x1e0,
exc_instruction_tlb_miss_bolted_book3e);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 00:52:27 +0000