summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-08-07 10:33:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-08-07 10:33:50 -0700
commit25d8d4eecace9de5a6a2193e4df1917afbdd3052 (patch)
tree1f1bbde6423745251c41fb4d1842e70b9f7bca07 /arch/powerpc/mm
parent60e76bb8a4e4c5398ea9053535e1fd0c9d6bb06e (diff)
parenta7aaa2f26bfd932a654706b19859e7adf802bee2 (diff)
downloadlinux-25d8d4eecace9de5a6a2193e4df1917afbdd3052.tar.bz2
Merge tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman: - Add support for (optionally) using queued spinlocks & rwlocks. - Support for a new faster system call ABI using the scv instruction on Power9 or later. - Drop support for the PROT_SAO mmap/mprotect flag as it will be unsupported on Power10 and future processors, leaving us with no way to implement the functionality it requests. This risks breaking userspace, though we believe it is unused in practice. - A bug fix for, and then the removal of, our custom stack expansion checking. We now allow stack expansion up to the rlimit, like other architectures. - Remove the remnants of our (previously disabled) topology update code, which tried to react to NUMA layout changes on virtualised systems, but was prone to crashes and other problems. - Add PMU support for Power10 CPUs. - A change to our signal trampoline so that we don't unbalance the link stack (branch return predictor) in the signal delivery path. - Lots of other cleanups, refactorings, smaller features and so on as usual. Thanks to: Abhishek Goel, Alastair D'Silva, Alexander A. Klimov, Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Balamuruhan S, Bharata B Rao, Bill Wendling, Bin Meng, Cédric Le Goater, Chris Packham, Christophe Leroy, Christoph Hellwig, Daniel Axtens, Dan Williams, David Lamparter, Desnes A. Nunes do Rosario, Erhard F., Finn Thain, Frederic Barrat, Ganesh Goudar, Gautham R. Shenoy, Geoff Levand, Greg Kurz, Gustavo A. R. Silva, Hari Bathini, Harish, Imre Kaloz, Joel Stanley, Joe Perches, John Crispin, Jordan Niethe, Kajol Jain, Kamalesh Babulal, Kees Cook, Laurent Dufour, Leonardo Bras, Li RongQing, Madhavan Srinivasan, Mahesh Salgaonkar, Mark Cave-Ayland, Michal Suchanek, Milton Miller, Mimi Zohar, Murilo Opsfelder Araujo, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nayna Jain, Nicholas Piggin, Oliver O'Halloran, Palmer Dabbelt, Pedro Miraglia Franco de Carvalho, Philippe Bergheaud, Pingfan Liu, Pratik Rajesh Sampat, Qian Cai, Qinglang Miao, Randy Dunlap, Ravi Bangoria, Sachin Sant, Sam Bobroff, Sandipan Das, Santosh Sivaraj, Satheesh Rajendran, Shirisha Ganta, Sourabh Jain, Srikar Dronamraju, Stan Johnson, Stephen Rothwell, Thadeu Lima de Souza Cascardo, Thiago Jung Bauermann, Tom Lane, Vaibhav Jain, Vladis Dronov, Wei Yongjun, Wen Xiong, YueHaibing. * tag 'powerpc-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (337 commits) selftests/powerpc: Fix pkey syscall redefinitions powerpc: Fix circular dependency between percpu.h and mmu.h powerpc/powernv/sriov: Fix use of uninitialised variable selftests/powerpc: Skip vmx/vsx/tar/etc tests on older CPUs powerpc/40x: Fix assembler warning about r0 powerpc/papr_scm: Add support for fetching nvdimm 'fuel-gauge' metric powerpc/papr_scm: Fetch nvdimm performance stats from PHYP cpuidle: pseries: Fixup exit latency for CEDE(0) cpuidle: pseries: Add function to parse extended CEDE records cpuidle: pseries: Set the latency-hint before entering CEDE selftests/powerpc: Fix online CPU selection powerpc/perf: Consolidate perf_callchain_user_[64|32]() powerpc/pseries/hotplug-cpu: Remove double free in error path powerpc/pseries/mobility: Add pr_debug() for device tree changes powerpc/pseries/mobility: Set pr_fmt() powerpc/cacheinfo: Warn if cache object chain becomes unordered powerpc/cacheinfo: Improve diagnostics about malformed cache lists powerpc/cacheinfo: Use name@unit instead of full DT path in debug messages powerpc/cacheinfo: Set pr_fmt() powerpc: fix function annotations to avoid section mismatch warnings with gcc-10 ...
Diffstat (limited to 'arch/powerpc/mm')
-rw-r--r--arch/powerpc/mm/book3s32/hash_low.S2
-rw-r--r--arch/powerpc/mm/book3s32/mmu.c17
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c25
-rw-r--r--arch/powerpc/mm/book3s64/pgtable.c8
-rw-r--r--arch/powerpc/mm/book3s64/pkeys.c300
-rw-r--r--arch/powerpc/mm/book3s64/radix_pgtable.c219
-rw-r--r--arch/powerpc/mm/book3s64/radix_tlb.c82
-rw-r--r--arch/powerpc/mm/drmem.c87
-rw-r--r--arch/powerpc/mm/fault.c106
-rw-r--r--arch/powerpc/mm/hugetlbpage.c18
-rw-r--r--arch/powerpc/mm/init_32.c2
-rw-r--r--arch/powerpc/mm/init_64.c6
-rw-r--r--arch/powerpc/mm/kasan/kasan_init_32.c35
-rw-r--r--arch/powerpc/mm/mem.c5
-rw-r--r--arch/powerpc/mm/nohash/tlb_low_64e.S47
-rw-r--r--arch/powerpc/mm/numa.c506
-rw-r--r--arch/powerpc/mm/pgtable-frag.c3
-rw-r--r--arch/powerpc/mm/ptdump/hashpagetable.c2
-rw-r--r--arch/powerpc/mm/ptdump/ptdump.c55
19 files changed, 572 insertions, 953 deletions
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 923ad8f374eb..1690d369688b 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -62,7 +62,7 @@ _GLOBAL(hash_page)
isync
#endif
/* Get PTE (linux-style) and check access */
- lis r0,KERNELBASE@h /* check if kernel address */
+ lis r0, TASK_SIZE@h /* check if kernel address */
cmplw 0,r4,r0
ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 03b6ba54460e..c0162911f6cb 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -187,6 +187,17 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return __mmu_mapin_ram(border, top);
}
+static bool is_module_segment(unsigned long addr)
+{
+ if (!IS_ENABLED(CONFIG_MODULES))
+ return false;
+ if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
+ return false;
+ if (addr >= ALIGN(VMALLOC_END, SZ_256M))
+ return false;
+ return true;
+}
+
void mmu_mark_initmem_nx(void)
{
int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
@@ -223,9 +234,9 @@ void mmu_mark_initmem_nx(void)
for (i = TASK_SIZE >> 28; i < 16; i++) {
/* Do not set NX on VM space for modules */
- if (IS_ENABLED(CONFIG_MODULES) &&
- (VMALLOC_START & 0xf0000000) == i << 28)
- break;
+ if (is_module_segment(i << 28))
+ continue;
+
mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
}
}
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 9b9f92ad0e7a..1478fceeb683 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -232,8 +232,6 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
rflags |= HPTE_R_I;
else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
rflags |= (HPTE_R_I | HPTE_R_G);
- else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
- rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
else
/*
* Add memory coherence if cache inhibited is not set
@@ -596,7 +594,7 @@ static void __init htab_scan_page_sizes(void)
}
#ifdef CONFIG_HUGETLB_PAGE
- if (!hugetlb_disabled) {
+ if (!hugetlb_disabled && !early_radix_enabled() ) {
/* Reserve 16G huge page memory sections for huge pages */
of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
}
@@ -663,11 +661,10 @@ static void __init htab_init_page_sizes(void)
* Pick a size for the linear mapping. Currently, we only
* support 16M, 1M and 4K which is the default
*/
- if (IS_ENABLED(STRICT_KERNEL_RWX) &&
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) &&
(unsigned long)_stext % 0x1000000) {
if (mmu_psize_defs[MMU_PAGE_16M].shift)
- pr_warn("Kernel not 16M aligned, "
- "disabling 16M linear map alignment");
+ pr_warn("Kernel not 16M aligned, disabling 16M linear map alignment\n");
aligned = false;
}
@@ -788,7 +785,7 @@ static unsigned long __init htab_get_table_size(void)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-int resize_hpt_for_hotplug(unsigned long new_mem_size)
+static int resize_hpt_for_hotplug(unsigned long new_mem_size)
{
unsigned target_hpt_shift;
@@ -822,6 +819,8 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
return -1;
}
+ resize_hpt_for_hotplug(memblock_phys_mem_size());
+
rc = htab_bolt_mapping(start, end, __pa(start),
pgprot_val(prot), mmu_linear_psize,
mmu_kernel_ssize);
@@ -839,6 +838,10 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end)
int rc = htab_remove_mapping(start, end, mmu_linear_psize,
mmu_kernel_ssize);
WARN_ON(rc < 0);
+
+ if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
+ pr_warn("Hash collision while resizing HPT\n");
+
return rc;
}
#endif /* CONFIG_MEMORY_HOTPLUG */
@@ -1111,6 +1114,10 @@ void hash__early_init_mmu_secondary(void)
if (cpu_has_feature(CPU_FTR_ARCH_206)
&& cpu_has_feature(CPU_FTR_HVMODE))
tlbiel_all();
+
+#ifdef CONFIG_PPC_MEM_KEYS
+ mtspr(SPRN_UAMOR, default_uamor);
+#endif
}
#endif /* CONFIG_SMP */
@@ -1731,10 +1738,6 @@ unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
return gslot;
}
-/*
- * WARNING: This is called from hash_low_64.S, if you change this prototype,
- * do not forget to update the assembly call site !
- */
void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
unsigned long flags)
{
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index c58ad1049909..e18ae50a275c 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -15,6 +15,7 @@
#include <asm/powernv.h>
#include <asm/firmware.h>
#include <asm/ultravisor.h>
+#include <asm/kexec.h>
#include <mm/mmu_decl.h>
#include <trace/events/thp.h>
@@ -165,6 +166,8 @@ void mmu_cleanup_all(void)
radix__mmu_cleanup_all();
else if (mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
+
+ reset_sprs();
}
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -339,6 +342,9 @@ void pmd_fragment_free(unsigned long *pmd)
{
struct page *page = virt_to_page(pmd);
+ if (PageReserved(page))
+ return free_reserved_page(page);
+
BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
if (atomic_dec_and_test(&page->pt_frag_refcount)) {
pgtable_pmd_page_dtor(page);
@@ -356,7 +362,7 @@ static inline void pgtable_free(void *table, int index)
pmd_fragment_free(table);
break;
case PUD_INDEX:
- kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
+ __pud_free(table);
break;
#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
/* 16M hugepd directory at pud level */
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index d174106bab67..69a6b87f2bb4 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -10,58 +10,103 @@
#include <asm/mmu.h>
#include <asm/setup.h>
#include <linux/pkeys.h>
-#include <linux/of_device.h>
+#include <linux/of_fdt.h>
-DEFINE_STATIC_KEY_TRUE(pkey_disabled);
-int pkeys_total; /* Total pkeys as per device tree */
-u32 initial_allocation_mask; /* Bits set for the initially allocated keys */
-u32 reserved_allocation_mask; /* Bits set for reserved keys */
-static bool pkey_execute_disable_supported;
-static bool pkeys_devtree_defined; /* property exported by device tree */
-static u64 pkey_amr_mask; /* Bits in AMR not to be touched */
-static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */
-static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */
+int num_pkey; /* Max number of pkeys supported */
+/*
+ * Keys marked in the reservation list cannot be allocated by userspace
+ */
+u32 reserved_allocation_mask __ro_after_init;
+
+/* Bits set for the initially allocated keys */
+static u32 initial_allocation_mask __ro_after_init;
+
+/*
+ * Even if we allocate keys with sys_pkey_alloc(), we need to make sure
+ * other thread still find the access denied using the same keys.
+ */
+static u64 default_amr = ~0x0UL;
+static u64 default_iamr = 0x5555555555555555UL;
+u64 default_uamor __ro_after_init;
+/*
+ * Key used to implement PROT_EXEC mmap. Denies READ/WRITE
+ * We pick key 2 because 0 is special key and 1 is reserved as per ISA.
+ */
static int execute_only_key = 2;
+static bool pkey_execute_disable_supported;
+
#define AMR_BITS_PER_PKEY 2
#define AMR_RD_BIT 0x1UL
#define AMR_WR_BIT 0x2UL
#define IAMR_EX_BIT 0x1UL
-#define PKEY_REG_BITS (sizeof(u64)*8)
+#define PKEY_REG_BITS (sizeof(u64) * 8)
#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey+1) * AMR_BITS_PER_PKEY))
-static void scan_pkey_feature(void)
+static int __init dt_scan_storage_keys(unsigned long node,
+ const char *uname, int depth,
+ void *data)
{
- u32 vals[2];
- struct device_node *cpu;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int *pkeys_total = (int *) data;
- cpu = of_find_node_by_type(NULL, "cpu");
- if (!cpu)
- return;
+ /* We are scanning "cpu" nodes only */
+ if (type == NULL || strcmp(type, "cpu") != 0)
+ return 0;
- if (of_property_read_u32_array(cpu,
- "ibm,processor-storage-keys", vals, 2))
- return;
+ prop = of_get_flat_dt_prop(node, "ibm,processor-storage-keys", NULL);
+ if (!prop)
+ return 0;
+ *pkeys_total = be32_to_cpu(prop[0]);
+ return 1;
+}
+
+static int scan_pkey_feature(void)
+{
+ int ret;
+ int pkeys_total = 0;
/*
- * Since any pkey can be used for data or execute, we will just treat
- * all keys as equal and track them as one entity.
+ * Pkey is not supported with Radix translation.
*/
- pkeys_total = vals[0];
- pkeys_devtree_defined = true;
-}
+ if (early_radix_enabled())
+ return 0;
-static inline bool pkey_mmu_enabled(void)
-{
- if (firmware_has_feature(FW_FEATURE_LPAR))
- return pkeys_total;
- else
- return cpu_has_feature(CPU_FTR_PKEY);
+ /*
+ * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1
+ */
+ if (!early_cpu_has_feature(CPU_FTR_ARCH_206))
+ return 0;
+
+ ret = of_scan_flat_dt(dt_scan_storage_keys, &pkeys_total);
+ if (ret == 0) {
+ /*
+ * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device
+ * tree. We make this exception since some version of skiboot forgot to
+ * expose this property on power8/9.
+ */
+ if (!firmware_has_feature(FW_FEATURE_LPAR)) {
+ unsigned long pvr = mfspr(SPRN_PVR);
+
+ if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E ||
+ PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9)
+ pkeys_total = 32;
+ }
+ }
+
+ /*
+ * Adjust the upper limit, based on the number of bits supported by
+ * arch-neutral code.
+ */
+ pkeys_total = min_t(int, pkeys_total,
+ ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) + 1));
+ return pkeys_total;
}
-static int pkey_initialize(void)
+void __init pkey_early_init_devtree(void)
{
- int os_reserved, i;
+ int pkeys_total, i;
/*
* We define PKEY_DISABLE_EXECUTE in addition to the arch-neutral
@@ -80,31 +125,14 @@ static int pkey_initialize(void)
!= (sizeof(u64) * BITS_PER_BYTE));
/* scan the device tree for pkey feature */
- scan_pkey_feature();
-
- /*
- * Let's assume 32 pkeys on P8 bare metal, if its not defined by device
- * tree. We make this exception since skiboot forgot to expose this
- * property on power8.
- */
- if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) &&
- cpu_has_feature(CPU_FTRS_POWER8))
- pkeys_total = 32;
-
- /*
- * Adjust the upper limit, based on the number of bits supported by
- * arch-neutral code.
- */
- pkeys_total = min_t(int, pkeys_total,
- ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)+1));
+ pkeys_total = scan_pkey_feature();
+ if (!pkeys_total)
+ goto out;
- if (!pkey_mmu_enabled() || radix_enabled() || !pkeys_total)
- static_branch_enable(&pkey_disabled);
- else
- static_branch_disable(&pkey_disabled);
+ /* Allow all keys to be modified by default */
+ default_uamor = ~0x0UL;
- if (static_branch_likely(&pkey_disabled))
- return 0;
+ cur_cpu_spec->mmu_features |= MMU_FTR_PKEY;
/*
* The device tree cannot be relied to indicate support for
@@ -118,53 +146,86 @@ static int pkey_initialize(void)
#ifdef CONFIG_PPC_4K_PAGES
/*
* The OS can manage only 8 pkeys due to its inability to represent them
- * in the Linux 4K PTE.
+ * in the Linux 4K PTE. Mark all other keys reserved.
*/
- os_reserved = pkeys_total - 8;
+ num_pkey = min(8, pkeys_total);
#else
- os_reserved = 0;
+ num_pkey = pkeys_total;
#endif
- /* Bits are in LE format. */
- reserved_allocation_mask = (0x1 << 1) | (0x1 << execute_only_key);
-
- /* register mask is in BE format */
- pkey_amr_mask = ~0x0ul;
- pkey_amr_mask &= ~(0x3ul << pkeyshift(0));
-
- pkey_iamr_mask = ~0x0ul;
- pkey_iamr_mask &= ~(0x3ul << pkeyshift(0));
- pkey_iamr_mask &= ~(0x3ul << pkeyshift(execute_only_key));
- pkey_uamor_mask = ~0x0ul;
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(0));
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(execute_only_key));
-
- /* mark the rest of the keys as reserved and hence unavailable */
- for (i = (pkeys_total - os_reserved); i < pkeys_total; i++) {
- reserved_allocation_mask |= (0x1 << i);
- pkey_uamor_mask &= ~(0x3ul << pkeyshift(i));
- }
- initial_allocation_mask = reserved_allocation_mask | (0x1 << 0);
-
- if (unlikely((pkeys_total - os_reserved) <= execute_only_key)) {
+ if (unlikely(num_pkey <= execute_only_key) || !pkey_execute_disable_supported) {
/*
* Insufficient number of keys to support
* execute only key. Mark it unavailable.
- * Any AMR, UAMOR, IAMR bit set for
- * this key is irrelevant since this key
- * can never be allocated.
*/
execute_only_key = -1;
+ } else {
+ /*
+ * Mark the execute_only_pkey as not available for
+ * user allocation via pkey_alloc.
+ */
+ reserved_allocation_mask |= (0x1 << execute_only_key);
+
+ /*
+ * Deny READ/WRITE for execute_only_key.
+ * Allow execute in IAMR.
+ */
+ default_amr |= (0x3ul << pkeyshift(execute_only_key));
+ default_iamr &= ~(0x1ul << pkeyshift(execute_only_key));
+
+ /*
+ * Clear the uamor bits for this key.
+ */
+ default_uamor &= ~(0x3ul << pkeyshift(execute_only_key));
}
- return 0;
-}
+ /*
+ * Allow access for only key 0. And prevent any other modification.
+ */
+ default_amr &= ~(0x3ul << pkeyshift(0));
+ default_iamr &= ~(0x1ul << pkeyshift(0));
+ default_uamor &= ~(0x3ul << pkeyshift(0));
+ /*
+ * key 0 is special in that we want to consider it an allocated
+ * key which is preallocated. We don't allow changing AMR bits
+ * w.r.t key 0. But one can pkey_free(key0)
+ */
+ initial_allocation_mask |= (0x1 << 0);
-arch_initcall(pkey_initialize);
+ /*
+ * key 1 is recommended not to be used. PowerISA(3.0) page 1015,
+ * programming note.
+ */
+ reserved_allocation_mask |= (0x1 << 1);
+ default_uamor &= ~(0x3ul << pkeyshift(1));
+
+ /*
+ * Prevent the usage of OS reserved keys. Update UAMOR
+ * for those keys. Also mark the rest of the bits in the
+ * 32 bit mask as reserved.
+ */
+ for (i = num_pkey; i < 32 ; i++) {
+ reserved_allocation_mask |= (0x1 << i);
+ default_uamor &= ~(0x3ul << pkeyshift(i));
+ }
+ /*
+ * Prevent the allocation of reserved keys too.
+ */
+ initial_allocation_mask |= reserved_allocation_mask;
+
+ pr_info("Enabling pkeys with max key count %d\n", num_pkey);
+out:
+ /*
+ * Setup uamor on boot cpu
+ */
+ mtspr(SPRN_UAMOR, default_uamor);
+
+ return;
+}
void pkey_mm_init(struct mm_struct *mm)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
mm_pkey_allocation_map(mm) = initial_allocation_mask;
mm->context.execute_only_pkey = execute_only_key;
@@ -196,30 +257,6 @@ static inline void write_iamr(u64 value)
mtspr(SPRN_IAMR, value);
}
-static inline u64 read_uamor(void)
-{
- return mfspr(SPRN_UAMOR);
-}
-
-static inline void write_uamor(u64 value)
-{
- mtspr(SPRN_UAMOR, value);
-}
-
-static bool is_pkey_enabled(int pkey)
-{
- u64 uamor = read_uamor();
- u64 pkey_bits = 0x3ul << pkeyshift(pkey);
- u64 uamor_pkey_bits = (uamor & pkey_bits);
-
- /*
- * Both the bits in UAMOR corresponding to the key should be set or
- * reset.
- */
- WARN_ON(uamor_pkey_bits && (uamor_pkey_bits != pkey_bits));
- return !!(uamor_pkey_bits);
-}
-
static inline void init_amr(int pkey, u8 init_bits)
{
u64 new_amr_bits = (((u64)init_bits & 0x3UL) << pkeyshift(pkey));
@@ -245,8 +282,18 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
{
u64 new_amr_bits = 0x0ul;
u64 new_iamr_bits = 0x0ul;
+ u64 pkey_bits, uamor_pkey_bits;
+
+ /*
+ * Check whether the key is disabled by UAMOR.
+ */
+ pkey_bits = 0x3ul << pkeyshift(pkey);
+ uamor_pkey_bits = (default_uamor & pkey_bits);
- if (!is_pkey_enabled(pkey))
+ /*
+ * Both the bits in UAMOR corresponding to the key should be set
+ */
+ if (uamor_pkey_bits != pkey_bits)
return -EINVAL;
if (init_val & PKEY_DISABLE_EXECUTE) {
@@ -268,7 +315,7 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
void thread_pkey_regs_save(struct thread_struct *thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
/*
@@ -276,38 +323,33 @@ void thread_pkey_regs_save(struct thread_struct *thread)
*/
thread->amr = read_amr();
thread->iamr = read_iamr();
- thread->uamor = read_uamor();
}
void thread_pkey_regs_restore(struct thread_struct *new_thread,
struct thread_struct *old_thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
if (old_thread->amr != new_thread->amr)
write_amr(new_thread->amr);
if (old_thread->iamr != new_thread->iamr)
write_iamr(new_thread->iamr);
- if (old_thread->uamor != new_thread->uamor)
- write_uamor(new_thread->uamor);
}
void thread_pkey_regs_init(struct thread_struct *thread)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
- thread->amr = pkey_amr_mask;
- thread->iamr = pkey_iamr_mask;
- thread->uamor = pkey_uamor_mask;
+ thread->amr = default_amr;
+ thread->iamr = default_iamr;
- write_uamor(pkey_uamor_mask);
- write_amr(pkey_amr_mask);
- write_iamr(pkey_iamr_mask);
+ write_amr(default_amr);
+ write_iamr(default_iamr);
}
-int __execute_only_pkey(struct mm_struct *mm)
+int execute_only_pkey(struct mm_struct *mm)
{
return mm->context.execute_only_pkey;
}
@@ -366,7 +408,7 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute)
bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return true;
return pkey_access_permitted(pte_to_pkey_bits(pte), write, execute);
@@ -383,7 +425,7 @@ bool arch_pte_access_permitted(u64 pte, bool write, bool execute)
bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
bool execute, bool foreign)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return true;
/*
* Do not enforce our key-permissions on a foreign vma.
@@ -396,7 +438,7 @@ bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm)
{
- if (static_branch_likely(&pkey_disabled))
+ if (!mmu_has_feature(MMU_FTR_PKEY))
return;
/* Duplicate the oldmm pkey state in mm: */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index bb00e0cba119..28c784976bed 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -15,7 +15,7 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/string_helpers.h>
-#include <linux/stop_machine.h>
+#include <linux/memory.h>
#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
@@ -34,6 +34,7 @@
unsigned int mmu_pid_bits;
unsigned int mmu_base_pid;
+unsigned int radix_mem_block_size __ro_after_init;
static __ref void *early_alloc_pgtable(unsigned long size, int nid,
unsigned long region_start, unsigned long region_end)
@@ -56,6 +57,13 @@ static __ref void *early_alloc_pgtable(unsigned long size, int nid,
return ptr;
}
+/*
+ * When allocating pud or pmd pointers, we allocate a complete page
+ * of PAGE_SIZE rather than PUD_TABLE_SIZE or PMD_TABLE_SIZE. This
+ * is to ensure that the page obtained from the memblock allocator
+ * can be completely used as page table page and can be freed
+ * correctly when the page table entries are removed.
+ */
static int early_map_kernel_page(unsigned long ea, unsigned long pa,
pgprot_t flags,
unsigned int map_page_size,
@@ -72,8 +80,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
pgdp = pgd_offset_k(ea);
p4dp = p4d_offset(pgdp, ea);
if (p4d_none(*p4dp)) {
- pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid,
- region_start, region_end);
+ pudp = early_alloc_pgtable(PAGE_SIZE, nid,
+ region_start, region_end);
p4d_populate(&init_mm, p4dp, pudp);
}
pudp = pud_offset(p4dp, ea);
@@ -82,8 +90,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa,
goto set_the_pte;
}
if (pud_none(*pudp)) {
- pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid,
- region_start, region_end);
+ pmdp = early_alloc_pgtable(PAGE_SIZE, nid, region_start,
+ region_end);
pud_populate(&init_mm, pudp, pmdp);
}
pmdp = pmd_offset(pudp, ea);
@@ -259,6 +267,7 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end)
static int __meminit create_physical_mapping(unsigned long start,
unsigned long end,
+ unsigned long max_mapping_size,
int nid, pgprot_t _prot)
{
unsigned long vaddr, addr, mapping_size = 0;
@@ -272,6 +281,8 @@ static int __meminit create_physical_mapping(unsigned long start,
int rc;
gap = next_boundary(addr, end) - addr;
+ if (gap > max_mapping_size)
+ gap = max_mapping_size;
previous_size = mapping_size;
prev_exec = exec;
@@ -322,8 +333,9 @@ static void __init radix_init_pgtable(void)
/* We don't support slb for radix */
mmu_slb_size = 0;
+
/*
- * Create the linear mapping, using standard page size for now
+ * Create the linear mapping
*/
for_each_memblock(memory, reg) {
/*
@@ -339,6 +351,7 @@ static void __init radix_init_pgtable(void)
WARN_ON(create_physical_mapping(reg->base,
reg->base + reg->size,
+ radix_mem_block_size,
-1, PAGE_KERNEL));
}
@@ -479,6 +492,57 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
return 1;
}
+#ifdef CONFIG_MEMORY_HOTPLUG
+static int __init probe_memory_block_size(unsigned long node, const char *uname, int
+ depth, void *data)
+{
+ unsigned long *mem_block_size = (unsigned long *)data;
+ const __be64 *prop;
+ int len;
+
+ if (depth != 1)
+ return 0;
+
+ if (strcmp(uname, "ibm,dynamic-reconfiguration-memory"))
+ return 0;
+
+ prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
+ if (!prop || len < sizeof(__be64))
+ /*
+ * Nothing in the device tree
+ */
+ *mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+ else
+ *mem_block_size = be64_to_cpup(prop);
+ return 1;
+}
+
+static unsigned long radix_memory_block_size(void)
+{
+ unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE;
+
+ /*
+ * OPAL firmware feature is set by now. Hence we are ok
+ * to test OPAL feature.
+ */
+ if (firmware_has_feature(FW_FEATURE_OPAL))
+ mem_block_size = 1UL * 1024 * 1024 * 1024;
+ else
+ of_scan_flat_dt(probe_memory_block_size, &mem_block_size);
+
+ return mem_block_size;
+}
+
+#else /* CONFIG_MEMORY_HOTPLUG */
+
+static unsigned long radix_memory_block_size(void)
+{
+ return 1UL * 1024 * 1024 * 1024;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+
void __init radix__early_init_devtree(void)
{
int rc;
@@ -487,17 +551,27 @@ void __init radix__early_init_devtree(void)
* Try to find the available page sizes in the device-tree
*/
rc = of_scan_flat_dt(radix_dt_scan_page_sizes, NULL);
- if (rc != 0) /* Found */
- goto found;
+ if (!rc) {
+ /*
+ * No page size details found in device tree.
+ * Let's assume we have page 4k and 64k support
+ */
+ mmu_psize_defs[MMU_PAGE_4K].shift = 12;
+ mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
+
+ mmu_psize_defs[MMU_PAGE_64K].shift = 16;
+ mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
+ }
+
/*
- * let's assume we have page 4k and 64k support
+ * Max mapping size used when mapping pages. We don't use
+ * ppc_md.memory_block_size() here because this get called
+ * early and we don't have machine probe called yet. Also
+ * the pseries implementation only check for ibm,lmb-size.
+ * All hypervisor supporting radix do expose that device
+ * tree node.
*/
- mmu_psize_defs[MMU_PAGE_4K].shift = 12;
- mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
-
- mmu_psize_defs[MMU_PAGE_64K].shift = 16;
- mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
-found:
+ radix_mem_block_size = radix_memory_block_size();
return;
}
@@ -519,8 +593,10 @@ void setup_kuep(bool disabled)
if (disabled || !early_radix_enabled())
return;
- if (smp_processor_id() == boot_cpuid)
+ if (smp_processor_id() == boot_cpuid) {
pr_info("Activating Kernel Userspace Execution Prevention\n");
+ cur_cpu_spec->mmu_features |= MMU_FTR_KUEP;
+ }
/*
* Radix always uses key0 of the IAMR to determine if an access is
@@ -544,6 +620,10 @@ void setup_kuap(bool disabled)
/* Make sure userspace can't change the AMR */
mtspr(SPRN_UAMOR, 0);
+
+ /*
+ * Set the default kernel AMR values on all cpus.
+ */
mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
isync();
}
@@ -700,30 +780,19 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud)
pud_clear(pud);
}
-struct change_mapping_params {
- pte_t *pte;
- unsigned long start;
- unsigned long end;
- unsigned long aligned_start;
- unsigned long aligned_end;
-};
-
-static int __meminit stop_machine_change_mapping(void *data)
+static void free_pud_table(pud_t *pud_start, p4d_t *p4d)
{
- struct change_mapping_params *params =
- (struct change_mapping_params *)data;
+ pud_t *pud;
+ int i;
- if (!data)
- return -1;
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ pud = pud_start + i;
+ if (!pud_none(*pud))
+ return;
+ }
- spin_unlock(&init_mm.page_table_lock);
- pte_clear(&init_mm, params->aligned_start, params->pte);
- create_physical_mapping(__pa(params->aligned_start),
- __pa(params->start), -1, PAGE_KERNEL);
- create_physical_mapping(__pa(params->end), __pa(params->aligned_end),
- -1, PAGE_KERNEL);
- spin_lock(&init_mm.page_table_lock);
- return 0;
+ pud_free(&init_mm, pud_start);
+ p4d_clear(p4d);
}
static void remove_pte_table(pte_t *pte_start, unsigned long addr,
@@ -754,53 +823,7 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr,
}
}
-/*
- * clear the pte and potentially split the mapping helper
- */
-static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end,
- unsigned long size, pte_t *pte)
-{
- unsigned long mask = ~(size - 1);
- unsigned long aligned_start = addr & mask;
- unsigned long aligned_end = addr + size;
- struct change_mapping_params params;
- bool split_region = false;
-
- if ((end - addr) < size) {
- /*
- * We're going to clear the PTE, but not flushed
- * the mapping, time to remap and flush. The
- * effects if visible outside the processor or
- * if we are running in code close to the
- * mapping we cleared, we are in trouble.
- */
- if (overlaps_kernel_text(aligned_start, addr) ||
- overlaps_kernel_text(end, aligned_end)) {
- /*
- * Hack, just return, don't pte_clear
- */
- WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel "
- "text, not splitting\n", addr, end);
- return;
- }
- split_region = true;
- }
-
- if (split_region) {
- params.pte = pte;
- params.start = addr;
- params.end = end;
- params.aligned_start = addr & ~(size - 1);
- params.aligned_end = min_t(unsigned long, aligned_end,
- (unsigned long)__va(memblock_end_of_DRAM()));
- stop_machine(stop_machine_change_mapping, &params, NULL);
- return;
- }
-
- pte_clear(&init_mm, addr, pte);
-}
-
-static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
+static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
unsigned long end)
{
unsigned long next;
@@ -815,7 +838,12 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
continue;
if (pmd_is_leaf(*pmd)) {
- split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd);
+ if (!IS_ALIGNED(addr, PMD_SIZE) ||
+ !IS_ALIGNED(next, PMD_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+ pte_clear(&init_mm, addr, (pte_t *)pmd);
continue;
}
@@ -825,7 +853,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
}
}
-static void remove_pud_table(pud_t *pud_start, unsigned long addr,
+static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr,
unsigned long end)
{
unsigned long next;
@@ -840,7 +868,12 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr,
continue;
if (pud_is_leaf(*pud)) {
- split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud);
+ if (!IS_ALIGNED(addr, PUD_SIZE) ||
+ !IS_ALIGNED(next, PUD_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+ pte_clear(&init_mm, addr, (pte_t *)pud);
continue;
}
@@ -868,12 +901,19 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end)
continue;
if (p4d_is_leaf(*p4d)) {
- split_kernel_mapping(addr, end, P4D_SIZE, (pte_t *)p4d);
+ if (!IS_ALIGNED(addr, P4D_SIZE) ||
+ !IS_ALIGNED(next, P4D_SIZE)) {
+ WARN_ONCE(1, "%s: unaligned range\n", __func__);
+ continue;
+ }
+
+ pte_clear(&init_mm, addr, (pte_t *)pgd);
continue;
}
pud_base = (pud_t *)p4d_page_vaddr(*p4d);
remove_pud_table(pud_base, addr, next);
+ free_pud_table(pud_base, p4d);
}
spin_unlock(&init_mm.page_table_lock);
@@ -889,7 +929,8 @@ int __meminit radix__create_section_mapping(unsigned long start,
return -1;
}
- return create_physical_mapping(__pa(start), __pa(end), nid, prot);
+ return create_physical_mapping(__pa(start), __pa(end),
+ radix_mem_block_size, nid, prot);
}
int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index b5cc9b23cf02..0d233763441f 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -16,6 +16,7 @@
#include <asm/tlbflush.h>
#include <asm/trace.h>
#include <asm/cputhreads.h>
+#include <asm/plpar_wrappers.h>
#define RIC_FLUSH_TLB 0
#define RIC_FLUSH_PWC 1
@@ -694,7 +695,14 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
goto local;
}
- if (cputlb_use_tlbie()) {
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB,
+ H_RPTI_PAGE_ALL, 0, -1UL);
+ } else if (cputlb_use_tlbie()) {
if (mm_needs_flush_escalation(mm))
_tlbie_pid(pid, RIC_FLUSH_ALL);
else
@@ -727,7 +735,16 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
goto local;
}
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type,
+ H_RPTI_PAGE_ALL, 0, -1UL);
+ } else if (cputlb_use_tlbie())
_tlbie_pid(pid, RIC_FLUSH_ALL);
else
_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
@@ -760,7 +777,19 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
exit_flush_lazy_tlbs(mm);
goto local;
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt, pg_sizes, size;
+
+ tgt = H_RPTI_TARGET_CMMU;
+ pg_sizes = psize_to_rpti_pgsize(psize);
+ size = 1UL << mmu_psize_to_shift(psize);
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB,
+ pg_sizes, vmaddr,
+ vmaddr + size);
+ } else if (cputlb_use_tlbie())
_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
else
_tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB);
@@ -810,7 +839,14 @@ static inline void _tlbiel_kernel_broadcast(void)
*/
void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU | H_RPTI_TARGET_NMMU;
+ unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+
+ pseries_rpt_invalidate(0, tgt, type, H_RPTI_PAGE_ALL,
+ start, end);
+ } else if (cputlb_use_tlbie())
_tlbie_pid(0, RIC_FLUSH_ALL);
else
_tlbiel_kernel_broadcast();
@@ -864,7 +900,17 @@ is_local:
nr_pages > tlb_local_single_page_flush_ceiling);
}
- if (full) {
+ if (!mmu_has_feature(MMU_FTR_GTSE) && !local) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize);
+
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+ pg_sizes |= psize_to_rpti_pgsize(MMU_PAGE_2M);
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, pg_sizes,
+ start, end);
+ } else if (full) {
if (local) {
_tlbiel_pid(pid, RIC_FLUSH_TLB);
} else {
@@ -1046,7 +1092,17 @@ is_local:
nr_pages > tlb_local_single_page_flush_ceiling);
}
- if (full) {
+ if (!mmu_has_feature(MMU_FTR_GTSE) && !local) {
+ unsigned long tgt = H_RPTI_TARGET_CMMU;
+ unsigned long type = H_RPTI_TYPE_TLB;
+ unsigned long pg_sizes = psize_to_rpti_pgsize(psize);
+
+ if (also_pwc)
+ type |= H_RPTI_TYPE_PWC;
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type, pg_sizes, start, end);
+ } else if (full) {
if (local) {
_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
} else {
@@ -1111,7 +1167,19 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
exit_flush_lazy_tlbs(mm);
goto local;
}
- if (cputlb_use_tlbie())
+ if (!mmu_has_feature(MMU_FTR_GTSE)) {
+ unsigned long tgt, type, pg_sizes;
+
+ tgt = H_RPTI_TARGET_CMMU;
+ type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+ H_RPTI_TYPE_PRT;
+ pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize);
+
+ if (atomic_read(&mm->context.copros) > 0)
+ tgt |= H_RPTI_TARGET_NMMU;
+ pseries_rpt_invalidate(pid, tgt, type, pg_sizes,
+ addr, end);
+ } else if (cputlb_use_tlbie())
_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
else
_tlbiel_va_range_multicast(mm,
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 59327cefbc6a..b2eeea39684c 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -14,6 +14,8 @@
#include <asm/prom.h>
#include <asm/drmem.h>
+static int n_root_addr_cells, n_root_size_cells;
+
static struct drmem_lmb_info __drmem_info;
struct drmem_lmb_info *drmem_info = &__drmem_info;
@@ -189,12 +191,13 @@ int drmem_update_dt(void)
return rc;
}
-static void __init read_drconf_v1_cell(struct drmem_lmb *lmb,
+static void read_drconf_v1_cell(struct drmem_lmb *lmb,
const __be32 **prop)
{
const __be32 *p = *prop;
- lmb->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p);
+ lmb->base_addr = of_read_number(p, n_root_addr_cells);
+ p += n_root_addr_cells;
lmb->drc_index = of_read_number(p++, 1);
p++; /* skip reserved field */
@@ -205,29 +208,33 @@ static void __init read_drconf_v1_cell(struct drmem_lmb *lmb,
*prop = p;
}
-static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm,
- void (*func)(struct drmem_lmb *, const __be32 **))
+static int
+__walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, void *data,
+ int (*func)(struct drmem_lmb *, const __be32 **, void *))
{
struct drmem_lmb lmb;
u32 i, n_lmbs;
+ int ret = 0;
n_lmbs = of_read_number(prop++, 1);
- if (n_lmbs == 0)
- return;
-
for (i = 0; i < n_lmbs; i++) {
read_drconf_v1_cell(&lmb, &prop);
- func(&lmb, &usm);
+ ret = func(&lmb, &usm, data);
+ if (ret)
+ break;
}
+
+ return ret;
}
-static void __init read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell,
+static void read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell,
const __be32 **prop)
{
const __be32 *p = *prop;
dr_cell->seq_lmbs = of_read_number(p++, 1);
- dr_cell->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p);
+ dr_cell->base_addr = of_read_number(p, n_root_addr_cells);
+ p += n_root_addr_cells;
dr_cell->drc_index = of_read_number(p++, 1);
dr_cell->aa_index = of_read_number(p++, 1);
dr_cell->flags = of_read_number(p++, 1);
@@ -235,17 +242,16 @@ static void __init read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell,
*prop = p;
}
-static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm,
- void (*func)(struct drmem_lmb *, const __be32 **))
+static int
+__walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, void *data,
+ int (*func)(struct drmem_lmb *, const __be32 **, void *))
{
struct of_drconf_cell_v2 dr_cell;
struct drmem_lmb lmb;
u32 i, j, lmb_sets;
+ int ret = 0;
lmb_sets = of_read_number(prop++, 1);
- if (lmb_sets == 0)
- return;
-
for (i = 0; i < lmb_sets; i++) {
read_drconf_v2_cell(&dr_cell, &prop);
@@ -259,21 +265,29 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm,
lmb.aa_index = dr_cell.aa_index;
lmb.flags = dr_cell.flags;
- func(&lmb, &usm);
+ ret = func(&lmb, &usm, data);
+ if (ret)
+ break;
}
}
+
+ return ret;
}
#ifdef CONFIG_PPC_PSERIES
-void __init walk_drmem_lmbs_early(unsigned long node,
- void (*func)(struct drmem_lmb *, const __be32 **))
+int __init walk_drmem_lmbs_early(unsigned long node, void *data,
+ int (*func)(struct drmem_lmb *, const __be32 **, void *))
{
const __be32 *prop, *usm;
- int len;
+ int len, ret = -ENODEV;
prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);
if (!prop || len < dt_root_size_cells * sizeof(__be32))
- return;
+ return ret;
+
+ /* Get the address & size cells */
+ n_root_addr_cells = dt_root_addr_cells;
+ n_root_size_cells = dt_root_size_cells;
drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop);
@@ -281,20 +295,21 @@ void __init walk_drmem_lmbs_early(unsigned long node,
prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &len);
if (prop) {
- __walk_drmem_v1_lmbs(prop, usm, func);
+ ret = __walk_drmem_v1_lmbs(prop, usm, data, func);
} else {
prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory-v2",
&len);
if (prop)
- __walk_drmem_v2_lmbs(prop, usm, func);
+ ret = __walk_drmem_v2_lmbs(prop, usm, data, func);
}
memblock_dump_all();
+ return ret;
}
#endif
-static int __init init_drmem_lmb_size(struct device_node *dn)
+static int init_drmem_lmb_size(struct device_node *dn)
{
const __be32 *prop;
int len;
@@ -303,12 +318,12 @@ static int __init init_drmem_lmb_size(struct device_node *dn)
return 0;
prop = of_get_property(dn, "ibm,lmb-size", &len);
- if (!prop || len < dt_root_size_cells * sizeof(__be32)) {
+ if (!prop || len < n_root_size_cells * sizeof(__be32)) {
pr_info("Could not determine LMB size\n");
return -1;
}
- drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop);
+ drmem_info->lmb_size = of_read_number(prop, n_root_size_cells);
return 0;
}
@@ -329,24 +344,36 @@ static const __be32 *of_get_usable_memory(struct device_node *dn)
return prop;
}
-void __init walk_drmem_lmbs(struct device_node *dn,
- void (*func)(struct drmem_lmb *, const __be32 **))
+int walk_drmem_lmbs(struct device_node *dn, void *data,
+ int (*func)(struct drmem_lmb *, const __be32 **, void *))
{
const __be32 *prop, *usm;
+ int ret = -ENODEV;
+
+ if (!of_root)
+ return ret;
+
+ /* Get the address & size cells */
+ of_node_get(of_root);
+ n_root_addr_cells = of_n_addr_cells(of_root);
+ n_root_size_cells = of_n_size_cells(of_root);
+ of_node_put(of_root);
if (init_drmem_lmb_size(dn))
- return;
+ return ret;
usm = of_get_usable_memory(dn);
prop = of_get_property(dn, "ibm,dynamic-memory", NULL);
if (prop) {
- __walk_drmem_v1_lmbs(prop, usm, func);
+ ret = __walk_drmem_v1_lmbs(prop, usm, data, func);
} else {
prop = of_get_property(dn, "ibm,dynamic-memory-v2", NULL);
if (prop)
- __walk_drmem_v2_lmbs(prop, usm, func);
+ ret = __walk_drmem_v2_lmbs(prop, usm, data, func);
}
+
+ return ret;
}
static void __init init_drmem_v1_lmbs(const __be32 *prop)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 641fc5f3d7dd..925a7231abb3 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -42,39 +42,7 @@
#include <asm/kup.h>
#include <asm/inst.h>
-/*
- * Check whether the instruction inst is a store using
- * an update addressing form which will update r1.
- */
-static bool store_updates_sp(struct ppc_inst inst)
-{
- /* check for 1 in the rA field */
- if (((ppc_inst_val(inst) >> 16) & 0x1f) != 1)
- return false;
- /* check major opcode */
- switch (ppc_inst_primary_opcode(inst)) {
- case OP_STWU:
- case OP_STBU:
- case OP_STHU:
- case OP_STFSU:
- case OP_STFDU:
- return true;
- case OP_STD: /* std or stdu */
- return (ppc_inst_val(inst) & 3) == 1;
- case OP_31:
- /* check minor opcode */
- switch ((ppc_inst_val(inst) >> 1) & 0x3ff) {
- case OP_31_XOP_STDUX:
- case OP_31_XOP_STWUX:
- case OP_31_XOP_STBUX:
- case OP_31_XOP_STHUX:
- case OP_31_XOP_STFSUX:
- case OP_31_XOP_STFDUX:
- return true;
- }
- }
- return false;
-}
+
/*
* do_page_fault error handling helpers
*/
@@ -267,54 +235,6 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
return false;
}
-static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
- struct vm_area_struct *vma, unsigned int flags,
- bool *must_retry)
-{
- /*
- * N.B. The POWER/Open ABI allows programs to access up to
- * 288 bytes below the stack pointer.
- * The kernel signal delivery code writes up to about 1.5kB
- * below the stack pointer (r1) before decrementing it.
- * The exec code can write slightly over 640kB to the stack
- * before setting the user r1. Thus we allow the stack to
- * expand to 1MB without further checks.
- */
- if (address + 0x100000 < vma->vm_end) {
- struct ppc_inst __user *nip = (struct ppc_inst __user *)regs->nip;
- /* get user regs even if this fault is in kernel mode */
- struct pt_regs *uregs = current->thread.regs;
- if (uregs == NULL)
- return true;
-
- /*
- * A user-mode access to an address a long way below
- * the stack pointer is only valid if the instruction
- * is one which would update the stack pointer to the
- * address accessed if the instruction completed,
- * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
- * (or the byte, halfword, float or double forms).
- *
- * If we don't check this then any write to the area
- * between the last mapped region and the stack will
- * expand the stack rather than segfaulting.
- */
- if (address + 2048 >= uregs->gpr[1])
- return false;
-
- if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
- access_ok(nip, sizeof(*nip))) {
- struct ppc_inst inst;
-
- if (!probe_user_read_inst(&inst, nip))
- return !store_updates_sp(inst);
- *must_retry = true;
- }
- return true;
- }
- return false;
-}
-
#ifdef CONFIG_PPC_MEM_KEYS
static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey,
struct vm_area_struct *vma)
@@ -480,7 +400,6 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
int is_user = user_mode(regs);
int is_write = page_fault_is_write(error_code);
vm_fault_t fault, major = 0;
- bool must_retry = false;
bool kprobe_fault = kprobe_page_fault(regs, 11);
if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
@@ -569,30 +488,15 @@ retry:
vma = find_vma(mm, address);
if (unlikely(!vma))
return bad_area(regs, address);
- if (likely(vma->vm_start <= address))
- goto good_area;
- if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
- return bad_area(regs, address);
- /* The stack is being expanded, check if it's valid */
- if (unlikely(bad_stack_expansion(regs, address, vma, flags,
- &must_retry))) {
- if (!must_retry)
+ if (unlikely(vma->vm_start > address)) {
+ if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
return bad_area(regs, address);
- mmap_read_unlock(mm);
- if (fault_in_pages_readable((const char __user *)regs->nip,
- sizeof(unsigned int)))
- return bad_area_nosemaphore(regs, address);
- goto retry;
+ if (unlikely(expand_stack(vma, address)))
+ return bad_area(regs, address);
}
- /* Try to expand it */
- if (unlikely(expand_stack(vma, address)))
- return bad_area(regs, address);
-
-good_area:
-
#ifdef CONFIG_PPC_MEM_KEYS
if (unlikely(access_pkey_error(is_write, is_exec,
(error_code & DSISR_KEYFAULT), vma)))
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index e9bfbccd975d..26292544630f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -684,3 +684,21 @@ void flush_dcache_icache_hugepage(struct page *page)
}
}
}
+
+void __init gigantic_hugetlb_cma_reserve(void)
+{
+ unsigned long order = 0;
+
+ if (radix_enabled())
+ order = PUD_SHIFT - PAGE_SHIFT;
+ else if (!firmware_has_feature(FW_FEATURE_LPAR) && mmu_psize_defs[MMU_PAGE_16G].shift)
+ /*
+ * For pseries we do use ibm,expected#pages for reserving 16G pages.
+ */
+ order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT;
+
+ if (order) {
+ VM_WARN_ON(order < MAX_ORDER);
+ hugetlb_cma_reserve(order);
+ }
+}
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 5a5469eb3174..bf1717f8d5f4 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -171,6 +171,8 @@ void __init MMU_init(void)
btext_unmap();
#endif
+ kasan_mmu_init();
+
setup_kup();
/* Shortly after that, the entire linear mapping will be available */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index bc73abf0bc25..4ae5fc0ceb30 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -406,13 +406,15 @@ static void __init early_check_vec5(void)
}
if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
OV5_FEAT(OV5_RADIX_GTSE))) {
- pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
- }
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE;
+ } else
+ cur_cpu_spec->mmu_features |= MMU_FTR_GTSE;
/* Do radix anyway - the hypervisor said we had to */
cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
/* Hypervisor only supports hash - disable radix */
cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+ cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE;
}
}
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 0760e1e754e4..fb294046e00e 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -115,16 +115,35 @@ static void __init kasan_unmap_early_shadow_vmalloc(void)
unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
kasan_update_early_region(k_start, k_end, __pte(0));
+
+#ifdef MODULES_VADDR
+ k_start = (unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR);
+ k_end = (unsigned long)kasan_mem_to_shadow((void *)MODULES_END);
+ kasan_update_early_region(k_start, k_end, __pte(0));
+#endif
}
-static void __init kasan_mmu_init(void)
+void __init kasan_mmu_init(void)
{
int ret;
+
+ if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
+ IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+ ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+ if (ret)
+ panic("kasan: kasan_init_shadow_page_tables() failed");
+ }
+}
+
+void __init kasan_init(void)
+{
struct memblock_region *reg;
for_each_memblock(memory, reg) {
phys_addr_t base = reg->base;
phys_addr_t top = min(base + reg->size, total_lowmem);
+ int ret;
if (base >= top)
continue;
@@ -134,20 +153,6 @@ static void __init kasan_mmu_init(void)
panic("kasan: kasan_init_region() failed");
}
- if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ||
- IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
- ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END);
-
- if (ret)
- panic("kasan: kasan_init_shadow_page_tables() failed");
- }
-
-}
-
-void __init kasan_init(void)
-{
- kasan_mmu_init();
-
kasan_remap_early_shadow_ro();
clear_page(kasan_early_shadow_page);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index c2c11eb8dcfc..9dafc636588f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -127,8 +127,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
unsigned long nr_pages = size >> PAGE_SHIFT;
int rc;
- resize_hpt_for_hotplug(memblock_phys_mem_size());
-
start = (unsigned long)__va(start);
rc = create_section_mapping(start, start + size, nid,
params->pgprot);
@@ -161,9 +159,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
* hit that section of memory
*/
vm_unmap_aliases();
-
- if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
- pr_warn("Hash collision while resizing HPT\n");
}
#endif
diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
index d5e2704d0096..bf24451f3e71 100644
--- a/arch/powerpc/mm/nohash/tlb_low_64e.S
+++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
@@ -71,7 +71,6 @@ START_BTB_FLUSH_SECTION
END_BTB_FLUSH_SECTION
std r7,EX_TLB_R7(r12)
#endif
- TLB_MISS_PROLOG_STATS
.endm
.macro tlb_epilog_bolted
@@ -85,7 +84,6 @@ END_BTB_FLUSH_SECTION
mtcr r14
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
@@ -128,7 +126,6 @@ END_BTB_FLUSH_SECTION
ori r10,r10,_PAGE_PRESENT
oris r11,r10,_PAGE_ACCESSED@h
- TLB_MISS_STATS_SAVE_INFO_BOLTED
bne tlb_miss_kernel_bolted
tlb_miss_common_bolted:
@@ -209,7 +206,6 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV)
tlbwe
tlb_miss_done_bolted:
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
tlb_epilog_bolted
rfi
@@ -229,11 +225,9 @@ tlb_miss_fault_bolted:
andi. r10,r11,_PAGE_EXEC|_PAGE_BAP_SX
bne itlb_miss_fault_bolted
dtlb_miss_fault_bolted:
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
tlb_epilog_bolted
b exc_data_storage_book3e
itlb_miss_fault_bolted:
- TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
tlb_epilog_bolted
b exc_instruction_storage_book3e
@@ -243,7 +237,6 @@ itlb_miss_fault_bolted:
rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
srdi r15,r16,60 /* get region */
- TLB_MISS_STATS_SAVE_INFO_BOLTED
bne- itlb_miss_fault_bolted
li r11,_PAGE_PRESENT|_PAGE_EXEC /* Base perm */
@@ -276,7 +269,6 @@ itlb_miss_fault_bolted:
srdi. r15,r16,60 /* get region */
ori r16,r16,1
- TLB_MISS_STATS_SAVE_INFO_BOLTED
bne tlb_miss_kernel_e6500 /* user/kernel test */
b tlb_miss_common_e6500
@@ -288,7 +280,6 @@ itlb_miss_fault_bolted:
srdi. r15,r16,60 /* get region */
rldicr r16,r16,0,62
- TLB_MISS_STATS_SAVE_INFO_BOLTED
bne tlb_miss_kernel_e6500 /* user vs kernel check */
/*
@@ -460,7 +451,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT)
.endm
tlb_unlock_e6500
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
tlb_epilog_bolted
rfi
@@ -519,11 +509,9 @@ tlb_miss_fault_e6500:
andi. r16,r16,1
bne itlb_miss_fault_e6500
dtlb_miss_fault_e6500:
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
tlb_epilog_bolted
b exc_data_storage_book3e
itlb_miss_fault_e6500:
- TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
tlb_epilog_bolted
b exc_instruction_storage_book3e
#endif /* CONFIG_PPC_FSL_BOOK3E */
@@ -548,7 +536,6 @@ itlb_miss_fault_e6500:
mfspr r16,SPRN_DEAR /* get faulting address */
srdi r15,r16,60 /* get region */
cmpldi cr0,r15,0xc /* linear mapping ? */
- TLB_MISS_STATS_SAVE_INFO
beq tlb_load_linear /* yes -> go to linear map load */
/* The page tables are mapped virtually linear. At this point, though,
@@ -600,7 +587,6 @@ itlb_miss_fault_e6500:
/* We got a crappy address, just fault with whatever DEAR and ESR
* are here
*/
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
@@ -624,7 +610,6 @@ itlb_miss_fault_e6500:
*/
srdi r15,r16,60 /* get region */
cmpldi cr0,r15,0xc /* linear mapping ? */
- TLB_MISS_STATS_SAVE_INFO
beq tlb_load_linear /* yes -> go to linear map load */
/* We do the user/kernel test for the PID here along with the RW test
@@ -646,7 +631,6 @@ itlb_miss_fault_e6500:
beq+ normal_tlb_miss
/* We got a crappy address, just fault */
- TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_instruction_storage_book3e
@@ -745,7 +729,6 @@ normal_tlb_miss_done:
* level 0 and just going back to userland. They are only needed
* if you are going to take an access fault
*/
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
TLB_MISS_EPILOG_SUCCESS
rfi
@@ -757,11 +740,9 @@ normal_tlb_miss_access_fault:
ld r15,EX_TLB_ESR(r12)
mtspr SPRN_DEAR,r14
mtspr SPRN_ESR,r15
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
-1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
- TLB_MISS_EPILOG_ERROR
+1: TLB_MISS_EPILOG_ERROR
b exc_instruction_storage_book3e
@@ -899,7 +880,6 @@ virt_page_table_tlb_miss_done:
1:
END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV)
/* Return to caller, normal case */
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK);
TLB_MISS_EPILOG_SUCCESS
rfi
@@ -935,18 +915,15 @@ virt_page_table_tlb_miss_fault:
beq 1f
mtspr SPRN_DEAR,r15
mtspr SPRN_ESR,r16
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT);
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
-1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT);
- TLB_MISS_EPILOG_ERROR
+1: TLB_MISS_EPILOG_ERROR
b exc_instruction_storage_book3e
virt_page_table_tlb_miss_whacko_fault:
/* The linear fault will restart everything so ESR and DEAR will
* not have been clobbered, let's just fault with what we have
*/
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_FAULT);
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
@@ -971,7 +948,6 @@ virt_page_table_tlb_miss_whacko_fault:
mfspr r16,SPRN_DEAR /* get faulting address */
srdi r11,r16,60 /* get region */
cmpldi cr0,r11,0xc /* linear mapping ? */
- TLB_MISS_STATS_SAVE_INFO
beq tlb_load_linear /* yes -> go to linear map load */
/* We do the user/kernel test for the PID here along with the RW test
@@ -991,7 +967,6 @@ virt_page_table_tlb_miss_whacko_fault:
/* We got a crappy address, just fault with whatever DEAR and ESR
* are here
*/
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
@@ -1015,7 +990,6 @@ virt_page_table_tlb_miss_whacko_fault:
*/
srdi r11,r16,60 /* get region */
cmpldi cr0,r11,0xc /* linear mapping ? */
- TLB_MISS_STATS_SAVE_INFO
beq tlb_load_linear /* yes -> go to linear map load */
/* We do the user/kernel test for the PID here along with the RW test
@@ -1033,7 +1007,6 @@ virt_page_table_tlb_miss_whacko_fault:
beq+ htw_tlb_miss
/* We got a crappy address, just fault */
- TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_instruction_storage_book3e
@@ -1130,7 +1103,6 @@ htw_tlb_miss_done:
* level 0 and just going back to userland. They are only needed
* if you are going to take an access fault
*/
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK)
TLB_MISS_EPILOG_SUCCESS
rfi
@@ -1142,11 +1114,9 @@ htw_tlb_miss_fault:
beq 1f
mtspr SPRN_DEAR,r16
mtspr SPRN_ESR,r14
- TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT)
TLB_MISS_EPILOG_ERROR
b exc_data_storage_book3e
-1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT)
- TLB_MISS_EPILOG_ERROR
+1: TLB_MISS_EPILOG_ERROR
b exc_instruction_storage_book3e
/*
@@ -1221,7 +1191,6 @@ tlb_load_linear_done:
* We do that because we can't resume a fault within a TLB
* miss handler, due to MAS and TLB reservation being clobbered.
*/
- TLB_MISS_STATS_X(MMSTAT_TLB_MISS_LINEAR)
TLB_MISS_EPILOG_ERROR
rfi
@@ -1233,13 +1202,3 @@ tlb_load_linear_fault:
b exc_data_storage_book3e
1: TLB_MISS_EPILOG_ERROR_SPECIAL
b exc_instruction_storage_book3e
-
-
-#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
-.tlb_stat_inc:
-1: ldarx r8,0,r9
- addi r8,r8,1
- stdcx. r8,0,r9
- bne- 1b
- blr
-#endif
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9fcf2d195830..058fee9a0835 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -221,7 +221,8 @@ static void initialize_distance_lookup_table(int nid,
}
}
-/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
* info is found.
*/
static int associativity_to_nid(const __be32 *associativity)
@@ -235,7 +236,7 @@ static int associativity_to_nid(const __be32 *associativity)
nid = of_read_number(&associativity[min_common_depth], 1);
/* POWER4 LPAR uses 0xffff as invalid node */
- if (nid == 0xffff || nid >= MAX_NUMNODES)
+ if (nid == 0xffff || nid >= nr_node_ids)
nid = NUMA_NO_NODE;
if (nid > 0 &&
@@ -448,7 +449,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
nid = of_read_number(&aa.arrays[index], 1);
- if (nid == 0xffff || nid >= MAX_NUMNODES)
+ if (nid == 0xffff || nid >= nr_node_ids)
nid = default_nid;
if (nid > 0) {
@@ -644,8 +645,9 @@ static inline int __init read_usm_ranges(const __be32 **usm)
* Extract NUMA information from the ibm,dynamic-reconfiguration-memory
* node. This assumes n_mem_{addr,size}_cells have been set.
*/
-static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
- const __be32 **usm)
+static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
+ const __be32 **usm,
+ void *data)
{
unsigned int ranges, is_kexec_kdump = 0;
unsigned long base, size, sz;
@@ -657,7 +659,7 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
*/
if ((lmb->flags & DRCONF_MEM_RESERVED)
|| !(lmb->flags & DRCONF_MEM_ASSIGNED))
- return;
+ return 0;
if (*usm)
is_kexec_kdump = 1;
@@ -669,7 +671,7 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
if (is_kexec_kdump) {
ranges = read_usm_ranges(usm);
if (!ranges) /* there are no (base, size) duple */
- return;
+ return 0;
}
do {
@@ -686,6 +688,8 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
if (sz)
memblock_set_node(base, sz, &memblock.memory, nid);
} while (--ranges);
+
+ return 0;
}
static int __init parse_numa_properties(void)
@@ -787,7 +791,7 @@ new_range:
*/
memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
if (memory) {
- walk_drmem_lmbs(memory, numa_setup_drmem_lmb);
+ walk_drmem_lmbs(memory, NULL, numa_setup_drmem_lmb);
of_node_put(memory);
}
@@ -984,28 +988,6 @@ static int __init early_numa(char *p)
}
early_param("numa", early_numa);
-/*
- * The platform can inform us through one of several mechanisms
- * (post-migration device tree updates, PRRN or VPHN) that the NUMA
- * assignment of a resource has changed. This controls whether we act
- * on that. Disabled by default.
- */
-static bool topology_updates_enabled;
-
-static int __init early_topology_updates(char *p)
-{
- if (!p)
- return 0;
-
- if (!strcmp(p, "on")) {
- pr_warn("Caution: enabling topology updates\n");
- topology_updates_enabled = true;
- }
-
- return 0;
-}
-early_param("topology_updates", early_topology_updates);
-
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Find the node associated with a hot added memory section for
@@ -1144,98 +1126,9 @@ u64 memory_hotplug_max(void)
/* Virtual Processor Home Node (VPHN) support */
#ifdef CONFIG_PPC_SPLPAR
-struct topology_update_data {
- struct topology_update_data *next;
- unsigned int cpu;
- int old_nid;
- int new_nid;
-};
-
-#define TOPOLOGY_DEF_TIMER_SECS 60
-
-static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
-static cpumask_t cpu_associativity_changes_mask;
-static int vphn_enabled;
-static int prrn_enabled;
-static void reset_topology_timer(void);
-static int topology_timer_secs = 1;
static int topology_inited;
/*
- * Change polling interval for associativity changes.
- */
-int timed_topology_update(int nsecs)
-{
- if (vphn_enabled) {
- if (nsecs > 0)
- topology_timer_secs = nsecs;
- else
- topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS;
-
- reset_topology_timer();
- }
-
- return 0;
-}
-
-/*
- * Store the current values of the associativity change counters in the
- * hypervisor.
- */
-static void setup_cpu_associativity_change_counters(void)
-{
- int cpu;
-
- /* The VPHN feature supports a maximum of 8 reference points */
- BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
-
- for_each_possible_cpu(cpu) {
- int i;
- u8 *counts = vphn_cpu_change_counts[cpu];
- volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
-
- for (i = 0; i < distance_ref_points_depth; i++)
- counts[i] = hypervisor_counts[i];
- }
-}
-
-/*
- * The hypervisor maintains a set of 8 associativity change counters in
- * the VPA of each cpu that correspond to the associativity levels in the
- * ibm,associativity-reference-points property. When an associativity
- * level changes, the corresponding counter is incremented.
- *
- * Set a bit in cpu_associativity_changes_mask for each cpu whose home
- * node associativity levels have changed.
- *
- * Returns the number of cpus with unhandled associativity changes.
- */
-static int update_cpu_associativity_changes_mask(void)
-{
- int cpu;
- cpumask_t *changes = &cpu_associativity_changes_mask;
-
- for_each_possible_cpu(cpu) {
- int i, changed = 0;
- u8 *counts = vphn_cpu_change_counts[cpu];
- volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts;
-
- for (i = 0; i < distance_ref_points_depth; i++) {
- if (hypervisor_counts[i] != counts[i]) {
- counts[i] = hypervisor_counts[i];
- changed = 1;
- }
- }
- if (changed) {
- cpumask_or(changes, changes, cpu_sibling_mask(cpu));
- cpu = cpu_last_thread_sibling(cpu);
- }
- }
-
- return cpumask_weight(changes);
-}
-
-/*
* Retrieve the new associativity information for a virtual processor's
* home node.
*/
@@ -1250,7 +1143,6 @@ static long vphn_get_associativity(unsigned long cpu,
switch (rc) {
case H_SUCCESS:
dbg("VPHN hcall succeeded. Reset polling...\n");
- timed_topology_update(0);
goto out;
case H_FUNCTION:
@@ -1269,8 +1161,6 @@ static long vphn_get_associativity(unsigned long cpu,
, rc);
break;
}
-
- stop_topology_update();
out:
return rc;
}
@@ -1314,380 +1204,8 @@ int find_and_online_cpu_nid(int cpu)
return new_nid;
}
-/*
- * Update the CPU maps and sysfs entries for a single CPU when its NUMA
- * characteristics change. This function doesn't perform any locking and is
- * only safe to call from stop_machine().
- */
-static int update_cpu_topology(void *data)
-{
- struct topology_update_data *update;
- unsigned long cpu;
-
- if (!data)
- return -EINVAL;
-
- cpu = smp_processor_id();
-
- for (update = data; update; update = update->next) {
- int new_nid = update->new_nid;
- if (cpu != update->cpu)
- continue;
-
- unmap_cpu_from_node(cpu);
- map_cpu_to_node(cpu, new_nid);
- set_cpu_numa_node(cpu, new_nid);
- set_cpu_numa_mem(cpu, local_memory_node(new_nid));
- vdso_getcpu_init();
- }
-
- return 0;
-}
-
-static int update_lookup_table(void *data)
-{
- struct topology_update_data *update;
-
- if (!data)
- return -EINVAL;
-
- /*
- * Upon topology update, the numa-cpu lookup table needs to be updated
- * for all threads in the core, including offline CPUs, to ensure that
- * future hotplug operations respect the cpu-to-node associativity
- * properly.
- */
- for (update = data; update; update = update->next) {
- int nid, base, j;
-
- nid = update->new_nid;
- base = cpu_first_thread_sibling(update->cpu);
-
- for (j = 0; j < threads_per_core; j++) {
- update_numa_cpu_lookup_table(base + j, nid);
- }
- }
-
- return 0;
-}
-
-/*
- * Update the node maps and sysfs entries for each cpu whose home node
- * has changed. Returns 1 when the topology has changed, and 0 otherwise.
- *
- * cpus_locked says whether we already hold cpu_hotplug_lock.
- */
-int numa_update_cpu_topology(bool cpus_locked)
-{
- unsigned int cpu, sibling, changed = 0;
- struct topology_update_data *updates, *ud;
- cpumask_t updated_cpus;
- struct device *dev;
- int weight, new_nid, i = 0;
-
- if (!prrn_enabled && !vphn_enabled && topology_inited)
- return 0;
-
- weight = cpumask_weight(&cpu_associativity_changes_mask);
- if (!weight)
- return 0;
-
- updates = kcalloc(weight, sizeof(*updates), GFP_KERNEL);
- if (!updates)
- return 0;
-
- cpumask_clear(&updated_cpus);
-
- for_each_cpu(cpu, &cpu_associativity_changes_mask) {
- /*
- * If siblings aren't flagged for changes, updates list
- * will be too short. Skip on this update and set for next
- * update.
- */
- if (!cpumask_subset(cpu_sibling_mask(cpu),
- &cpu_associativity_changes_mask)) {
- pr_info("Sibling bits not set for associativity "
- "change, cpu%d\n", cpu);
- cpumask_or(&cpu_associativity_changes_mask,
- &cpu_associativity_changes_mask,
- cpu_sibling_mask(cpu));
- cpu = cpu_last_thread_sibling(cpu);
- continue;
- }
-
- new_nid = find_and_online_cpu_nid(cpu);
-
- if (new_nid == numa_cpu_lookup_table[cpu]) {
- cpumask_andnot(&cpu_associativity_changes_mask,
- &cpu_associativity_changes_mask,
- cpu_sibling_mask(cpu));
- dbg("Assoc chg gives same node %d for cpu%d\n",
- new_nid, cpu);
- cpu = cpu_last_thread_sibling(cpu);
- continue;
- }
-
- for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
- ud = &updates[i++];
- ud->next = &updates[i];
- ud->cpu = sibling;
- ud->new_nid = new_nid;
- ud->old_nid = numa_cpu_lookup_table[sibling];
- cpumask_set_cpu(sibling, &updated_cpus);
- }
- cpu = cpu_last_thread_sibling(cpu);
- }
-
- /*
- * Prevent processing of 'updates' from overflowing array
- * where last entry filled in a 'next' pointer.
- */
- if (i)
- updates[i-1].next = NULL;
-
- pr_debug("Topology update for the following CPUs:\n");
- if (cpumask_weight(&updated_cpus)) {
- for (ud = &updates[0]; ud; ud = ud->next) {
- pr_debug("cpu %d moving from node %d "
- "to %d\n", ud->cpu,
- ud->old_nid, ud->new_nid);
- }
- }
-
- /*
- * 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;
-
- if (cpus_locked)
- stop_machine_cpuslocked(update_cpu_topology, &updates[0],
- &updated_cpus);
- else
- stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
-
- /*
- * Update the numa-cpu lookup table with the new mappings, even for
- * offline CPUs. It is best to perform this update from the stop-
- * machine context.
- */
- if (cpus_locked)
- stop_machine_cpuslocked(update_lookup_table, &updates[0],
- cpumask_of(raw_smp_processor_id()));
- else
- stop_machine(update_lookup_table, &updates[0],
- cpumask_of(raw_smp_processor_id()));
-
- for (ud = &updates[0]; ud; ud = ud->next) {
- unregister_cpu_under_node(ud->cpu, ud->old_nid);
- register_cpu_under_node(ud->cpu, ud->new_nid);
-
- dev = get_cpu_device(ud->cpu);
- if (dev)
- kobject_uevent(&dev->kobj, KOBJ_CHANGE);
- cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
- changed = 1;
- }
-
-out:
- kfree(updates);
- return changed;
-}
-
-int arch_update_cpu_topology(void)
-{
- return numa_update_cpu_topology(true);
-}
-
-static void topology_work_fn(struct work_struct *work)
-{
- rebuild_sched_domains();
-}
-static DECLARE_WORK(topology_work, topology_work_fn);
-
-static void topology_schedule_update(void)
-{
- schedule_work(&topology_work);
-}
-
-static void topology_timer_fn(struct timer_list *unused)
-{
- if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
- topology_schedule_update();
- else if (vphn_enabled) {
- if (update_cpu_associativity_changes_mask() > 0)
- topology_schedule_update();
- reset_topology_timer();
- }
-}
-static struct timer_list topology_timer;
-
-static void reset_topology_timer(void)
-{
- if (vphn_enabled)
- mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ);
-}
-
-#ifdef CONFIG_SMP
-
-static int dt_update_callback(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct of_reconfig_data *update = data;
- int rc = NOTIFY_DONE;
-
- switch (action) {
- case OF_RECONFIG_UPDATE_PROPERTY:
- if (of_node_is_type(update->dn, "cpu") &&
- !of_prop_cmp(update->prop->name, "ibm,associativity")) {
- u32 core_id;
- of_property_read_u32(update->dn, "reg", &core_id);
- rc = dlpar_cpu_readd(core_id);
- rc = NOTIFY_OK;
- }
- break;
- }
-
- return rc;
-}
-
-static struct notifier_block dt_update_nb = {
- .notifier_call = dt_update_callback,
-};
-
-#endif
-
-/*
- * Start polling for associativity changes.
- */
-int start_topology_update(void)
-{
- int rc = 0;
-
- if (!topology_updates_enabled)
- return 0;
-
- if (firmware_has_feature(FW_FEATURE_PRRN)) {
- if (!prrn_enabled) {
- prrn_enabled = 1;
-#ifdef CONFIG_SMP
- rc = of_reconfig_notifier_register(&dt_update_nb);
-#endif
- }
- }
- if (firmware_has_feature(FW_FEATURE_VPHN) &&
- lppaca_shared_proc(get_lppaca())) {
- if (!vphn_enabled) {
- vphn_enabled = 1;
- setup_cpu_associativity_change_counters();
- timer_setup(&topology_timer, topology_timer_fn,
- TIMER_DEFERRABLE);
- reset_topology_timer();
- }
- }
-
- pr_info("Starting topology update%s%s\n",
- (prrn_enabled ? " prrn_enabled" : ""),
- (vphn_enabled ? " vphn_enabled" : ""));
-
- return rc;
-}
-
-/*
- * Disable polling for VPHN associativity changes.
- */
-int stop_topology_update(void)
-{
- int rc = 0;
-
- if (!topology_updates_enabled)
- return 0;
-
- if (prrn_enabled) {
- prrn_enabled = 0;
-#ifdef CONFIG_SMP
- rc = of_reconfig_notifier_unregister(&dt_update_nb);
-#endif
- }
- if (vphn_enabled) {
- vphn_enabled = 0;
- rc = del_timer_sync(&topology_timer);
- }
-
- pr_info("Stopping topology update\n");
-
- return rc;
-}
-
-int prrn_is_enabled(void)
-{
- return prrn_enabled;
-}
-
-static int topology_read(struct seq_file *file, void *v)
-{
- if (vphn_enabled || prrn_enabled)
- seq_puts(file, "on\n");
- else
- seq_puts(file, "off\n");
-
- return 0;
-}
-
-static int topology_open(struct inode *inode, struct file *file)
-{
- return single_open(file, topology_read, NULL);
-}
-
-static ssize_t topology_write(struct file *file, const char __user *buf,
- size_t count, loff_t *off)
-{
- char kbuf[4]; /* "on" or "off" plus null. */
- int read_len;
-
- read_len = count < 3 ? count : 3;
- if (copy_from_user(kbuf, buf, read_len))
- return -EINVAL;
-
- kbuf[read_len] = '\0';
-
- if (!strncmp(kbuf, "on", 2)) {
- topology_updates_enabled = true;
- start_topology_update();
- } else if (!strncmp(kbuf, "off", 3)) {
- stop_topology_update();
- topology_updates_enabled = false;
- } else
- return -EINVAL;
-
- return count;
-}
-
-static const struct proc_ops topology_proc_ops = {
- .proc_read = seq_read,
- .proc_write = topology_write,
- .proc_open = topology_open,
- .proc_release = single_release,
-};
-
static int topology_update_init(void)
{
- start_topology_update();
-
- if (vphn_enabled)
- topology_schedule_update();
-
- if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_proc_ops))
- return -ENOMEM;
-
topology_inited = 1;
return 0;
}
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index ee4bd6d38602..97ae4935da79 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -110,6 +110,9 @@ void pte_fragment_free(unsigned long *table, int kernel)
{
struct page *page = virt_to_page(table);
+ if (PageReserved(page))
+ return free_reserved_page(page);
+
BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
if (atomic_dec_and_test(&page->pt_frag_refcount)) {
if (!kernel)
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index a2c33efc7ce8..5b8bd34cd3a1 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -258,7 +258,7 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *
for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) {
lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes);
- if (lpar_rc != H_SUCCESS)
+ if (lpar_rc)
continue;
for (j = 0; j < 4; j++) {
if (HPTE_V_COMPARE(ptes[j].v, want_v) &&
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index de6e05ef871c..c911cd757f7d 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -74,6 +74,10 @@ struct addr_marker {
static struct addr_marker address_markers[] = {
{ 0, "Start of kernel VM" },
+#ifdef MODULES_VADDR
+ { 0, "modules start" },
+ { 0, "modules end" },
+#endif
{ 0, "vmalloc() Area" },
{ 0, "vmalloc() End" },
#ifdef CONFIG_PPC64
@@ -195,6 +199,24 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
}
+static void note_page_update_state(struct pg_state *st, unsigned long addr,
+ unsigned int level, u64 val, unsigned long page_size)
+{
+ u64 flag = val & pg_level[level].mask;
+ u64 pa = val & PTE_RPN_MASK;
+
+ st->level = level;
+ st->current_flags = flag;
+ st->start_address = addr;
+ st->start_pa = pa;
+ st->page_size = page_size;
+
+ while (addr >= st->marker[1].start_address) {
+ st->marker++;
+ pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ }
+}
+
static void note_page(struct pg_state *st, unsigned long addr,
unsigned int level, u64 val, unsigned long page_size)
{
@@ -203,13 +225,8 @@ static void note_page(struct pg_state *st, unsigned long addr,
/* At first no level is set */
if (!st->level) {
- st->level = level;
- st->current_flags = flag;
- st->start_address = addr;
- st->start_pa = pa;
- st->last_pa = pa;
- st->page_size = page_size;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ note_page_update_state(st, addr, level, val, page_size);
/*
* Dump the section of virtual memory when:
* - the PTE flags from one entry to the next differs.
@@ -241,19 +258,9 @@ static void note_page(struct pg_state *st, unsigned long addr,
* Address indicates we have passed the end of the
* current section of virtual memory
*/
- while (addr >= st->marker[1].start_address) {
- st->marker++;
- pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
- }
- st->start_address = addr;
- st->start_pa = pa;
- st->last_pa = pa;
- st->page_size = page_size;
- st->current_flags = flag;
- st->level = level;
- } else {
- st->last_pa = pa;
+ note_page_update_state(st, addr, level, val, page_size);
}
+ st->last_pa = pa;
}
static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
@@ -348,7 +355,15 @@ static void populate_markers(void)
{
int i = 0;
+#ifdef CONFIG_PPC64
address_markers[i++].start_address = PAGE_OFFSET;
+#else
+ address_markers[i++].start_address = TASK_SIZE;
+#endif
+#ifdef MODULES_VADDR
+ address_markers[i++].start_address = MODULES_VADDR;
+ address_markers[i++].start_address = MODULES_END;
+#endif
address_markers[i++].start_address = VMALLOC_START;
address_markers[i++].start_address = VMALLOC_END;
#ifdef CONFIG_PPC64
@@ -385,7 +400,7 @@ static int ptdump_show(struct seq_file *m, void *v)
struct pg_state st = {
.seq = m,
.marker = address_markers,
- .start_address = PAGE_OFFSET,
+ .start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
};
#ifdef CONFIG_PPC64
@@ -429,7 +444,7 @@ void ptdump_check_wx(void)
.seq = NULL,
.marker = address_markers,
.check_wx = true,
- .start_address = PAGE_OFFSET,
+ .start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
};
#ifdef CONFIG_PPC64
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-14 03:53:12 +0000