From 1543e317f1da31b75942316931e8f491a8920811 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 04 Jan 2024 10:08:02 +0000
Subject: [PATCH] disable FB
---
kernel/arch/powerpc/mm/init_64.c | 158 +++++++++++++++++++++++++++++++++++-----------------
1 files changed, 106 insertions(+), 52 deletions(-)
diff --git a/kernel/arch/powerpc/mm/init_64.c b/kernel/arch/powerpc/mm/init_64.c
index a5091c0..db040f3 100644
--- a/kernel/arch/powerpc/mm/init_64.c
+++ b/kernel/arch/powerpc/mm/init_64.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* PowerPC version
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -11,12 +12,6 @@
*
* Dave Engebretsen <engebret@us.ibm.com>
* Rework for PPC64 port.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
*/
#undef DEBUG
@@ -52,7 +47,6 @@
#include <asm/rtas.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
-#include <asm/pgtable.h>
#include <asm/mmu.h>
#include <linux/uaccess.h>
#include <asm/smp.h>
@@ -66,40 +60,50 @@
#include <asm/iommu.h>
#include <asm/vdso.h>
-#include "mmu_decl.h"
-
-phys_addr_t memstart_addr = ~0;
-EXPORT_SYMBOL_GPL(memstart_addr);
-phys_addr_t kernstart_addr;
-EXPORT_SYMBOL_GPL(kernstart_addr);
+#include <mm/mmu_decl.h>
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
- * Given an address within the vmemmap, determine the pfn of the page that
- * represents the start of the section it is within. Note that we have to
+ * Given an address within the vmemmap, determine the page that
+ * represents the start of the subsection it is within. Note that we have to
* do this by hand as the proffered address may not be correctly aligned.
* Subtraction of non-aligned pointers produces undefined results.
*/
-static unsigned long __meminit vmemmap_section_start(unsigned long page)
+static struct page * __meminit vmemmap_subsection_start(unsigned long vmemmap_addr)
{
- unsigned long offset = page - ((unsigned long)(vmemmap));
+ unsigned long start_pfn;
+ unsigned long offset = vmemmap_addr - ((unsigned long)(vmemmap));
/* Return the pfn of the start of the section. */
- return (offset / sizeof(struct page)) & PAGE_SECTION_MASK;
+ start_pfn = (offset / sizeof(struct page)) & PAGE_SUBSECTION_MASK;
+ return pfn_to_page(start_pfn);
}
/*
- * Check if this vmemmap page is already initialised. If any section
- * which overlaps this vmemmap page is initialised then this page is
- * initialised already.
+ * Since memory is added in sub-section chunks, before creating a new vmemmap
+ * mapping, the kernel should check whether there is an existing memmap mapping
+ * covering the new subsection added. This is needed because kernel can map
+ * vmemmap area using 16MB pages which will cover a memory range of 16G. Such
+ * a range covers multiple subsections (2M)
+ *
+ * If any subsection in the 16G range mapped by vmemmap is valid we consider the
+ * vmemmap populated (There is a page table entry already present). We can't do
+ * a page table lookup here because with the hash translation we don't keep
+ * vmemmap details in linux page table.
*/
-static int __meminit vmemmap_populated(unsigned long start, int page_size)
+static int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size)
{
- unsigned long end = start + page_size;
- start = (unsigned long)(pfn_to_page(vmemmap_section_start(start)));
+ struct page *start;
+ unsigned long vmemmap_end = vmemmap_addr + vmemmap_map_size;
+ start = vmemmap_subsection_start(vmemmap_addr);
- for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
- if (pfn_valid(page_to_pfn((struct page *)start)))
+ for (; (unsigned long)start < vmemmap_end; start += PAGES_PER_SUBSECTION)
+ /*
+ * pfn valid check here is intended to really check
+ * whether we have any subsection already initialized
+ * in this range.
+ */
+ if (pfn_valid(page_to_pfn(start)))
return 1;
return 0;
@@ -158,16 +162,16 @@
return next++;
}
-static __meminit void vmemmap_list_populate(unsigned long phys,
- unsigned long start,
- int node)
+static __meminit int vmemmap_list_populate(unsigned long phys,
+ unsigned long start,
+ int node)
{
struct vmemmap_backing *vmem_back;
vmem_back = vmemmap_list_alloc(node);
if (unlikely(!vmem_back)) {
- WARN_ON(1);
- return;
+ pr_debug("vmemap list allocation failed\n");
+ return -ENOMEM;
}
vmem_back->phys = phys;
@@ -175,15 +179,32 @@
vmem_back->list = vmemmap_list;
vmemmap_list = vmem_back;
+ return 0;
+}
+
+static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+ unsigned long page_size)
+{
+ unsigned long nr_pfn = page_size / sizeof(struct page);
+ unsigned long start_pfn = page_to_pfn((struct page *)start);
+
+ if ((start_pfn + nr_pfn - 1) > altmap->end_pfn)
+ return true;
+
+ if (start_pfn < altmap->base_pfn)
+ return true;
+
+ return false;
}
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
+ bool altmap_alloc;
unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
/* Align to the page size of the linear mapping. */
- start = _ALIGN_DOWN(start, page_size);
+ start = ALIGN_DOWN(start, page_size);
pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
@@ -191,6 +212,12 @@
void *p = NULL;
int rc;
+ /*
+ * This vmemmap range is backing different subsections. If any
+ * of that subsection is marked valid, that means we already
+ * have initialized a page table covering this range and hence
+ * the vmemmap range is populated.
+ */
if (vmemmap_populated(start, page_size))
continue;
@@ -199,14 +226,36 @@
* fail due to alignment issues when using 16MB hugepages, so
* fall back to system memory if the altmap allocation fail.
*/
- if (altmap)
- p = altmap_alloc_block_buf(page_size, altmap);
- if (!p)
- p = vmemmap_alloc_block_buf(page_size, node);
+ if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
+ p = vmemmap_alloc_block_buf(page_size, node, altmap);
+ if (!p)
+ pr_debug("altmap block allocation failed, falling back to system memory");
+ else
+ altmap_alloc = true;
+ }
+ if (!p) {
+ p = vmemmap_alloc_block_buf(page_size, node, NULL);
+ altmap_alloc = false;
+ }
if (!p)
return -ENOMEM;
- vmemmap_list_populate(__pa(p), start, node);
+ if (vmemmap_list_populate(__pa(p), start, node)) {
+ /*
+ * If we don't populate vmemap list, we don't have
+ * the ability to free the allocated vmemmap
+ * pages in section_deactivate. Hence free them
+ * here.
+ */
+ int nr_pfns = page_size >> PAGE_SHIFT;
+ unsigned long page_order = get_order(page_size);
+
+ if (altmap_alloc)
+ vmem_altmap_free(altmap, nr_pfns);
+ else
+ free_pages((unsigned long)p, page_order);
+ return -ENOMEM;
+ }
pr_debug(" * %016lx..%016lx allocated at %p\n",
start, start + page_size, p);
@@ -236,10 +285,8 @@
vmem_back_prev = vmem_back;
}
- if (unlikely(!vmem_back)) {
- WARN_ON(1);
+ if (unlikely(!vmem_back))
return 0;
- }
/* remove it from vmemmap_list */
if (vmem_back == vmemmap_list) /* remove head */
@@ -263,24 +310,23 @@
unsigned long alt_start = ~0, alt_end = ~0;
unsigned long base_pfn;
- start = _ALIGN_DOWN(start, page_size);
+ start = ALIGN_DOWN(start, page_size);
if (altmap) {
alt_start = altmap->base_pfn;
- alt_end = altmap->base_pfn + altmap->reserve +
- altmap->free + altmap->alloc + altmap->align;
+ alt_end = altmap->base_pfn + altmap->reserve + altmap->free;
}
pr_debug("vmemmap_free %lx...%lx\n", start, end);
for (; start < end; start += page_size) {
unsigned long nr_pages, addr;
- struct page *section_base;
struct page *page;
/*
- * the section has already be marked as invalid, so
- * vmemmap_populated() true means some other sections still
- * in this page, so skip it.
+ * We have already marked the subsection we are trying to remove
+ * invalid. So if we want to remove the vmemmap range, we
+ * need to make sure there is no subsection marked valid
+ * in this range.
*/
if (vmemmap_populated(start, page_size))
continue;
@@ -290,7 +336,6 @@
continue;
page = pfn_to_page(addr >> PAGE_SHIFT);
- section_base = pfn_to_page(vmemmap_section_start(start));
nr_pages = 1 << page_order;
base_pfn = PHYS_PFN(addr);
@@ -379,13 +424,15 @@
}
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;
}
}
@@ -404,9 +451,16 @@
if (!(mfmsr() & MSR_HV))
early_check_vec5();
- if (early_radix_enabled())
+ if (early_radix_enabled()) {
radix__early_init_devtree();
- else
+ /*
+ * We have finalized the translation we are going to use by now.
+ * Radix mode is not limited by RMA / VRMA addressing.
+ * Hence don't limit memblock allocations.
+ */
+ ppc64_rma_size = ULONG_MAX;
+ memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
+ } else
hash__early_init_devtree();
}
#endif /* CONFIG_PPC_BOOK3S_64 */
--
Gitblit v1.6.2