@@ -60,6 +60,7 @@
#include <linux/stackprotector.h>
#include <linux/cpuhotplug.h>
#include <linux/mc146818rtc.h>
+#include <linux/numa_replication.h>
#include <asm/acpi.h>
#include <asm/cacheinfo.h>
@@ -244,6 +245,7 @@ static void notrace start_secondary(void *unused)
* limit the things done here to the most necessary things.
*/
cr4_init();
+ numa_setup_pgd();
/*
* 32-bit specific. 64-bit reaches this code with the correct page
@@ -17,6 +17,7 @@
#include <linux/highmem.h>
#include <linux/pci.h>
#include <linux/ptdump.h>
+#include <linux/numa_replication.h>
#include <asm/e820/types.h>
@@ -433,7 +434,15 @@ void ptdump_walk_user_pgd_level_checkwx(void)
void ptdump_walk_pgd_level_checkwx(void)
{
+#ifdef CONFIG_KERNEL_REPLICATION
+ int node;
+
+ for_each_replica(node)
+ ptdump_walk_pgd_level_core(NULL, &init_mm,
+ per_numa_pgd(&init_mm, node), true, false);
+#else
ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
+#endif
}
static int __init pt_dump_init(void)
@@ -20,6 +20,7 @@
#include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/
#include <linux/mm_types.h>
#include <linux/mm.h> /* find_and_lock_vma() */
+#include <linux/numa_replication.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/traps.h> /* dotraplinkage, ... */
@@ -1031,7 +1032,8 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address)
error_code != (X86_PF_INSTR | X86_PF_PROT))
return 0;
- pgd = init_mm.pgd + pgd_index(address);
+ pgd = per_numa_pgd(&init_mm, numa_node_id());
+
if (!pgd_present(*pgd))
return 0;
@@ -2,6 +2,7 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/hugetlb.h>
+#include <linux/numa_replication.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>
@@ -120,23 +121,25 @@ struct mm_struct *pgd_page_get_mm(struct page *page)
return page->pt_mm;
}
-static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
+static void pgd_ctor(struct mm_struct *mm, int nid)
{
+ pgd_t *dst_pgd = per_numa_pgd(mm, nid);
+ pgd_t *src_pgd = per_numa_pgd(&init_mm, nid);
/* If the pgd points to a shared pagetable level (either the
ptes in non-PAE, or shared PMD in PAE), then just copy the
references from swapper_pg_dir. */
if (CONFIG_PGTABLE_LEVELS == 2 ||
(CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
CONFIG_PGTABLE_LEVELS >= 4) {
- clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ clone_pgd_range(dst_pgd + KERNEL_PGD_BOUNDARY,
+ src_pgd + KERNEL_PGD_BOUNDARY,
KERNEL_PGD_PTRS);
}
/* list required to sync kernel mapping updates */
if (!SHARED_KERNEL_PMD) {
- pgd_set_mm(pgd, mm);
- pgd_list_add(pgd);
+ pgd_set_mm(dst_pgd, mm);
+ pgd_list_add(dst_pgd);
}
}
@@ -416,20 +419,33 @@ static inline void _pgd_free(pgd_t *pgd)
{
free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
}
+
+#ifdef CONFIG_KERNEL_REPLICATION
+static inline pgd_t *_pgd_alloc_node(int nid)
+{
+ struct page *pages;
+
+ pages = __alloc_pages_node(nid, GFP_PGTABLE_USER,
+ PGD_ALLOCATION_ORDER);
+ return (pgd_t *)page_address(pages);
+}
+
+#else
+#define _pgd_alloc_node(nid) _pgd_alloc()
+#endif /* CONFIG_KERNEL_REPLICATION */
#endif /* CONFIG_X86_PAE */
pgd_t *pgd_alloc(struct mm_struct *mm)
{
- pgd_t *pgd;
+ int nid;
pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
pmd_t *pmds[MAX_PREALLOCATED_PMDS];
- pgd = _pgd_alloc();
-
- if (pgd == NULL)
- goto out;
-
- mm->pgd = pgd;
+ for_each_replica(nid) {
+ per_numa_pgd(mm, nid) = _pgd_alloc_node(nid);
+ if (per_numa_pgd(mm, nid) == NULL)
+ goto out_free_pgd;
+ }
if (sizeof(pmds) != 0 &&
preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
@@ -449,16 +465,22 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
*/
spin_lock(&pgd_lock);
- pgd_ctor(mm, pgd);
- if (sizeof(pmds) != 0)
- pgd_prepopulate_pmd(mm, pgd, pmds);
+ for_each_replica(nid) {
+ pgd_ctor(mm, nid);
+ if (sizeof(pmds) != 0)
+ pgd_prepopulate_pmd(mm, per_numa_pgd(mm, nid), pmds);
- if (sizeof(u_pmds) != 0)
- pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
+ if (sizeof(u_pmds) != 0)
+ pgd_prepopulate_user_pmd(mm, per_numa_pgd(mm, nid), u_pmds);
+ }
+
+ for_each_online_node(nid) {
+ per_numa_pgd(mm, nid) = per_numa_pgd(mm, numa_closest_memory_node(nid));
+ }
spin_unlock(&pgd_lock);
- return pgd;
+ return mm->pgd;
out_free_user_pmds:
if (sizeof(u_pmds) != 0)
@@ -467,17 +489,25 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
if (sizeof(pmds) != 0)
free_pmds(mm, pmds, PREALLOCATED_PMDS);
out_free_pgd:
- _pgd_free(pgd);
-out:
+ for_each_replica(nid) {
+ if (per_numa_pgd(mm, nid) != NULL)
+ _pgd_free(per_numa_pgd(mm, nid));
+ }
return NULL;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
+ int nid;
+
pgd_mop_up_pmds(mm, pgd);
- pgd_dtor(pgd);
- paravirt_pgd_free(mm, pgd);
- _pgd_free(pgd);
+ for_each_replica(nid) {
+ pgd_t *pgd_numa = per_numa_pgd(mm, nid);
+
+ pgd_dtor(pgd_numa);
+ paravirt_pgd_free(mm, pgd_numa);
+ _pgd_free(pgd_numa);
+ }
}
/*
@@ -10,6 +10,7 @@
#include <linux/debugfs.h>
#include <linux/sched/smt.h>
#include <linux/task_work.h>
+#include <linux/numa_replication.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
@@ -491,6 +492,22 @@ void cr4_update_pce(void *ignored)
static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
#endif
+#ifdef CONFIG_KERNEL_REPLICATION
+extern struct mm_struct *poking_mm;
+static pgd_t *get_next_pgd(struct mm_struct *next)
+{
+ if (next == poking_mm)
+ return next->pgd;
+ else
+ return next->pgd_numa[numa_node_id()];
+}
+#else
+static pgd_t *get_next_pgd(struct mm_struct *next)
+{
+ return next->pgd;
+}
+#endif /*CONFIG_KERNEL_REPLICATION*/
+
void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
@@ -502,6 +519,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
u64 next_tlb_gen;
bool need_flush;
u16 new_asid;
+ pgd_t *next_pgd;
/*
* NB: The scheduler will call us with prev == next when switching
@@ -636,15 +654,17 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
}
set_tlbstate_lam_mode(next);
+
+ next_pgd = get_next_pgd(next);
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
+ load_new_mm_cr3(next_pgd, new_asid, new_lam, true);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- load_new_mm_cr3(next->pgd, new_asid, new_lam, false);
+ load_new_mm_cr3(next_pgd, new_asid, new_lam, false);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
@@ -703,7 +723,7 @@ void initialize_tlbstate_and_flush(void)
unsigned long cr3 = __read_cr3();
/* Assert that CR3 already references the right mm. */
- WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
+ WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(per_numa_pgd(mm, numa_node_id())));
/* LAM expected to be disabled */
WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
@@ -718,7 +738,7 @@ void initialize_tlbstate_and_flush(void)
!(cr4_read_shadow() & X86_CR4_PCIDE));
/* Disable LAM, force ASID 0 and force a TLB flush. */
- write_cr3(build_cr3(mm->pgd, 0, 0));
+ write_cr3(build_cr3(per_numa_pgd(mm, numa_node_id()), 0, 0));
/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
@@ -1091,7 +1111,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
unsigned long __get_current_cr3_fast(void)
{
unsigned long cr3 =
- build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
+ build_cr3(per_numa_pgd(this_cpu_read(cpu_tlbstate.loaded_mm), numa_node_id()),
this_cpu_read(cpu_tlbstate.loaded_mm_asid),
tlbstate_lam_cr3_mask());
@@ -99,6 +99,7 @@
#include <linux/init_syscalls.h>
#include <linux/stackdepot.h>
#include <linux/randomize_kstack.h>
+#include <linux/numa_replication.h>
#include <net/net_namespace.h>
#include <asm/io.h>
@@ -921,11 +922,13 @@ void start_kernel(void)
* These use large bootmem allocations and must precede
* initalization of page allocator
*/
+ numa_reserve_memory();
setup_log_buf(0);
vfs_caches_init_early();
sort_main_extable();
trap_init();
mm_core_init();
+ numa_replicate_kernel();
poking_init();
ftrace_init();
@@ -1446,6 +1449,8 @@ static int __ref kernel_init(void *unused)
free_initmem();
mark_readonly();
+ numa_replicate_kernel_rodata();
+ numa_clear_linear_addresses();
/*
* Kernel mappings are now finalized - update the userspace page-table
* to finalize PTI.