Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 33b3461..36c3800 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -19,7 +19,6 @@
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/kmemleak.h>
-#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/setup.h>
@@ -30,7 +29,8 @@
#define hugepd_none(hpd) (hpd_val(hpd) == 0)
-#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *)))
+#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_basic_t)) - \
+ __builtin_ffs(sizeof(void *)))
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
@@ -53,24 +53,17 @@
if (pshift >= pdshift) {
cachep = PGT_CACHE(PTE_T_ORDER);
num_hugepd = 1 << (pshift - pdshift);
- new = NULL;
- } else if (IS_ENABLED(CONFIG_PPC_8xx)) {
- cachep = NULL;
- num_hugepd = 1;
- new = pte_alloc_one(mm);
} else {
cachep = PGT_CACHE(pdshift - pshift);
num_hugepd = 1;
- new = NULL;
}
- if (!cachep && !new) {
+ if (!cachep) {
WARN_ONCE(1, "No page table cache created for hugetlb tables");
return -ENOMEM;
}
- if (cachep)
- new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+ new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
BUG_ON(pshift > HUGEPD_SHIFT_MASK);
BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -101,10 +94,7 @@
if (i < num_hugepd) {
for (i = i - 1 ; i >= 0; i--, hpdp--)
*hpdp = __hugepd(0);
- if (cachep)
- kmem_cache_free(cachep, new);
- else
- pte_free(mm, new);
+ kmem_cache_free(cachep, new);
} else {
kmemleak_ignore(new);
}
@@ -119,6 +109,7 @@
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
pgd_t *pg;
+ p4d_t *p4;
pud_t *pu;
pmd_t *pm;
hugepd_t *hpdp = NULL;
@@ -128,20 +119,21 @@
addr &= ~(sz-1);
pg = pgd_offset(mm, addr);
+ p4 = p4d_offset(pg, addr);
#ifdef CONFIG_PPC_BOOK3S_64
if (pshift == PGDIR_SHIFT)
/* 16GB huge page */
- return (pte_t *) pg;
+ return (pte_t *) p4;
else if (pshift > PUD_SHIFT) {
/*
* We need to use hugepd table
*/
ptl = &mm->page_table_lock;
- hpdp = (hugepd_t *)pg;
+ hpdp = (hugepd_t *)p4;
} else {
pdshift = PUD_SHIFT;
- pu = pud_alloc(mm, pg, addr);
+ pu = pud_alloc(mm, p4, addr);
if (!pu)
return NULL;
if (pshift == PUD_SHIFT)
@@ -166,10 +158,10 @@
#else
if (pshift >= PGDIR_SHIFT) {
ptl = &mm->page_table_lock;
- hpdp = (hugepd_t *)pg;
+ hpdp = (hugepd_t *)p4;
} else {
pdshift = PUD_SHIFT;
- pu = pud_alloc(mm, pg, addr);
+ pu = pud_alloc(mm, p4, addr);
if (!pu)
return NULL;
if (pshift >= PUD_SHIFT) {
@@ -188,6 +180,9 @@
if (!hpdp)
return NULL;
+ if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT)
+ return pte_alloc_map(mm, (pmd_t *)hpdp, addr);
+
BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr,
@@ -253,7 +248,7 @@
struct hugepd_freelist {
struct rcu_head rcu;
unsigned int index;
- void *ptes[0];
+ void *ptes[];
};
static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
@@ -330,13 +325,34 @@
if (shift >= pdshift)
hugepd_free(tlb, hugepte);
- else if (IS_ENABLED(CONFIG_PPC_8xx))
- pgtable_free_tlb(tlb, hugepte, 0);
else
pgtable_free_tlb(tlb, hugepte,
get_hugepd_cache_index(pdshift - shift));
}
+static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ unsigned long start = addr;
+ pgtable_t token = pmd_pgtable(*pmd);
+
+ start &= PMD_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PMD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pmd_clear(pmd);
+ pte_free_tlb(tlb, token, addr);
+ mm_dec_nr_ptes(tlb->mm);
+}
+
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
@@ -352,11 +368,17 @@
pmd = pmd_offset(pud, addr);
next = pmd_addr_end(addr, end);
if (!is_hugepd(__hugepd(pmd_val(*pmd)))) {
+ if (pmd_none_or_clear_bad(pmd))
+ continue;
+
/*
* if it is not hugepd pointer, we should already find
* it cleared.
*/
- WARN_ON(!pmd_none_or_clear_bad(pmd));
+ WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx));
+
+ hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling);
+
continue;
}
/*
@@ -390,7 +412,7 @@
mm_dec_nr_pmds(tlb->mm);
}
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
@@ -400,7 +422,7 @@
start = addr;
do {
- pud = pud_offset(pgd, addr);
+ pud = pud_offset(p4d, addr);
next = pud_addr_end(addr, end);
if (!is_hugepd(__hugepd(pud_val(*pud)))) {
if (pud_none_or_clear_bad(pud))
@@ -435,8 +457,8 @@
if (end - 1 > ceiling - 1)
return;
- pud = pud_offset(pgd, start);
- pgd_clear(pgd);
+ pud = pud_offset(p4d, start);
+ p4d_clear(p4d);
pud_free_tlb(tlb, pud, start);
mm_dec_nr_puds(tlb->mm);
}
@@ -449,6 +471,7 @@
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
+ p4d_t *p4d;
unsigned long next;
/*
@@ -471,10 +494,11 @@
do {
next = pgd_addr_end(addr, end);
pgd = pgd_offset(tlb->mm, addr);
+ p4d = p4d_offset(pgd, addr);
if (!is_hugepd(__hugepd(pgd_val(*pgd)))) {
- if (pgd_none_or_clear_bad(pgd))
+ if (p4d_none_or_clear_bad(p4d))
continue;
- hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
} else {
unsigned long more;
/*
@@ -487,7 +511,7 @@
if (more > next)
next = more;
- free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
+ free_hugepd_range(tlb, (hugepd_t *)p4d, PGDIR_SHIFT,
addr, next, floor, ceiling);
}
} while (addr = next, addr != end);
@@ -558,7 +582,7 @@
return vma_kernel_pagesize(vma);
}
-static int __init add_huge_page_size(unsigned long long size)
+bool __init arch_hugetlb_valid_size(unsigned long size)
{
int shift = __ffs(size);
int mmu_psize;
@@ -566,38 +590,28 @@
/* Check that it is a page size supported by the hardware and
* that it fits within pagetable and slice limits. */
if (size <= PAGE_SIZE || !is_power_of_2(size))
- return -EINVAL;
+ return false;
mmu_psize = check_and_get_huge_psize(shift);
if (mmu_psize < 0)
- return -EINVAL;
+ return false;
BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
- /* Return if huge page size has already been setup */
- if (size_to_hstate(size))
- return 0;
+ return true;
+}
+
+static int __init add_huge_page_size(unsigned long long size)
+{
+ int shift = __ffs(size);
+
+ if (!arch_hugetlb_valid_size((unsigned long)size))
+ return -EINVAL;
hugetlb_add_hstate(shift - PAGE_SHIFT);
-
return 0;
}
-static int __init hugepage_setup_sz(char *str)
-{
- unsigned long long size;
-
- size = memparse(str, &str);
-
- if (add_huge_page_size(size) != 0) {
- hugetlb_bad_size();
- pr_err("Invalid huge page size specified(%llu)\n", size);
- }
-
- return 1;
-}
-__setup("hugepagesz=", hugepage_setup_sz);
-
static int __init hugetlbpage_init(void)
{
bool configured = false;
@@ -684,3 +698,21 @@
}
}
}
+
+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);
+ }
+}