powerpc/64/mm: implement page mapping percpu first chunk allocator

Implement page mapping percpu first chunk allocator as a fallback to
the embedding allocator. With 4K hash translation we limit our page
table range to 64TB and commit: 0034d395 ("powerpc/mm/hash64: Map all the
kernel regions in the same 0xc range") moved all kernel mapping to
that 64TB range. In-order to support sparse memory layout we need
to increase our linear mapping space and reduce other mappings.

With such a layout percpu embedded first chunk allocator will fail
because of small vmalloc range. Add a fallback to page mapping
percpu first chunk allocator for such failures.

The below dmesg output can be observed in such case.

 percpu: max_distance=0x1ffffef00000 too large for vmalloc space 0x10000000000
 PERCPU: auto allocator failed (-22), falling back to page size
 percpu: 40 4K pages/cpu s148816 r0 d15024
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200608070904.387440-2-aneesh.kumar@linux.ibm.com

arch/powerpc/Kconfig

@@ -59,7 +59,10 @@ config HAVE_SETUP_PER_CPU_AREA
 	def_bool PPC64
 
 config NEED_PER_CPU_EMBED_FIRST_CHUNK
-	def_bool PPC64
+	def_bool y if PPC64
+
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
+	def_bool y if PPC64
 
 config NR_IRQS
 	int "Number of virtual interrupt numbers"

arch/powerpc/kernel/setup_64.c

@@ -66,6 +66,7 @@
 #include <asm/feature-fixups.h>
 #include <asm/kup.h>
 #include <asm/early_ioremap.h>
+#include <asm/pgalloc.h>
 
 #include "setup.h"
 
@@ -811,13 +812,58 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
+static void __init pcpu_populate_pte(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		pud_t *new;
+
+		new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+		if (!new)
+			goto err_alloc;
+		p4d_populate(&init_mm, p4d, new);
+	}
+
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud)) {
+		pmd_t *new;
+
+		new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pud_populate(&init_mm, pud, new);
+	}
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd)) {
+		pte_t *new;
+
+		new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+		if (!new)
+			goto err_alloc;
+		pmd_populate_kernel(&init_mm, pmd, new);
+	}
+
+	return;
+
+err_alloc:
+	panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
+	      __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+}
+
+
 void __init setup_per_cpu_areas(void)
 {
 	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
 	size_t atom_size;
 	unsigned long delta;
 	unsigned int cpu;
-	int rc;
+	int rc = -EINVAL;
 
 	/*
 	 * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
@@ -829,8 +875,18 @@ void __init setup_per_cpu_areas(void)
 	else
 		atom_size = 1 << 20;
 
-	rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
-				    pcpu_alloc_bootmem, pcpu_free_bootmem);
+	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+		rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
+					    pcpu_alloc_bootmem, pcpu_free_bootmem);
+		if (rc)
+			pr_warn("PERCPU: %s allocator failed (%d), "
+				"falling back to page size\n",
+				pcpu_fc_names[pcpu_chosen_fc], rc);
+	}
+
+	if (rc < 0)
+		rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem,
+					   pcpu_populate_pte);
 	if (rc < 0)
 		panic("cannot initialize percpu area (err=%d)", rc);