Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Anthony Yznaga <anthony.yznaga@oracle.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de, x86@kernel.org,
        hpa@zytor.com, dave.hansen@linux.intel.com, luto@kernel.org,
        peterz@infradead.org, rppt@kernel.org, akpm@linux-foundation.org,
        ebiederm@xmission.com, keescook@chromium.org, graf@amazon.com,
        jason.zeng@intel.com, lei.l.li@intel.com,
        steven.sistare@oracle.com, fam.zheng@bytedance.com,
        mgalaxy@akamai.com, kexec@lists.infradead.org
Subject: [RFC v3 10/21] PKRAM: prepare for adding preserved ranges to memblock reserved
Date:   Wed, 26 Apr 2023 17:08:46 -0700
Message-Id: <1682554137-13938-11-git-send-email-anthony.yznaga@oracle.com>
In-Reply-To: <1682554137-13938-1-git-send-email-anthony.yznaga@oracle.com>
References: <1682554137-13938-1-git-send-email-anthony.yznaga@oracle.com>
Precedence: bulk

Calling memblock_reserve() repeatedly to add preserved ranges is
inefficient and risks clobbering preserved memory if the memblock
reserved regions array must be resized.  Instead, calculate the size
needed to accommodate the preserved ranges, find a suitable range for
a new reserved regions array that does not overlap any preserved range,
and populate it with a new, merged regions array.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 mm/pkram.c | 244 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 244 insertions(+)

diff --git a/mm/pkram.c b/mm/pkram.c
index 3790e5180feb..c649504fa1fa 100644
--- a/mm/pkram.c
+++ b/mm/pkram.c
@@ -7,6 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -1138,3 +1139,246 @@ static unsigned long pkram_populate_regions_list(void)
 
 	return priv.nr_regions;
 }
+
+struct pkram_region *pkram_first_region(struct pkram_super_block *sb,
+					struct pkram_region_list **rlp, int *idx)
+{
+	WARN_ON(!sb);
+	WARN_ON(!sb->region_list_pfn);
+
+	if (!sb || !sb->region_list_pfn)
+		return NULL;
+
+	*rlp = pfn_to_kaddr(sb->region_list_pfn);
+	*idx = 0;
+
+	return &(*rlp)->regions[0];
+}
+
+struct pkram_region *pkram_next_region(struct pkram_region_list **rlp, int *idx)
+{
+	struct pkram_region_list *rl = *rlp;
+	int i = *idx;
+
+	i++;
+	if (i >= PKRAM_REGIONS_LIST_MAX) {
+		if (!rl->next_pfn) {
+			pr_err("PKRAM: %s: no more pkram_region_list pages\n", __func__);
+			return NULL;
+		}
+		rl = pfn_to_kaddr(rl->next_pfn);
+		*rlp = rl;
+		i = 0;
+	}
+	*idx = i;
+
+	if (rl->regions[i].size == 0)
+		return NULL;
+
+	return &rl->regions[i];
+}
+
+struct pkram_region *pkram_first_region_topdown(struct pkram_super_block *sb,
+						struct pkram_region_list **rlp, int *idx)
+{
+	struct pkram_region_list *rl;
+
+	WARN_ON(!sb);
+	WARN_ON(!sb->region_list_pfn);
+
+	if (!sb || !sb->region_list_pfn)
+		return NULL;
+
+	rl = pfn_to_kaddr(sb->region_list_pfn);
+	if (!rl->prev_pfn) {
+		WARN_ON(1);
+		return NULL;
+	}
+	rl = pfn_to_kaddr(rl->prev_pfn);
+
+	*rlp = rl;
+
+	*idx = (sb->nr_regions - 1) % PKRAM_REGIONS_LIST_MAX;
+
+	return &rl->regions[*idx];
+}
+
+struct pkram_region *pkram_next_region_topdown(struct pkram_region_list **rlp, int *idx)
+{
+	struct pkram_region_list *rl = *rlp;
+	int i = *idx;
+
+	if (i == 0) {
+		if (!rl->prev_pfn)
+			return NULL;
+		rl = pfn_to_kaddr(rl->prev_pfn);
+		*rlp = rl;
+		i = PKRAM_REGIONS_LIST_MAX - 1;
+	} else
+		i--;
+
+	*idx = i;
+
+	return &rl->regions[i];
+}
+
+/*
+ * Use the pkram regions list to allocate a block of memory that does
+ * not overlap with preserved pages.
+ */
+phys_addr_t __init alloc_topdown(phys_addr_t size)
+{
+	phys_addr_t hole_start, hole_end, hole_size;
+	struct pkram_region_list *rl;
+	struct pkram_region *r;
+	phys_addr_t addr = 0;
+	int idx;
+
+	hole_end = memblock.current_limit;
+	r = pkram_first_region_topdown(pkram_sb, &rl, &idx);
+
+	while (r) {
+		hole_start = r->base + r->size;
+		hole_size = hole_end - hole_start;
+
+		if (hole_size >= size) {
+			addr = memblock_phys_alloc_range(size, PAGE_SIZE,
+							hole_start, hole_end);
+			if (addr)
+				break;
+		}
+
+		hole_end = r->base;
+		r = pkram_next_region_topdown(&rl, &idx);
+	}
+
+	if (!addr)
+		addr = memblock_phys_alloc_range(size, PAGE_SIZE, 0, hole_end);
+
+	return addr;
+}
+
+int __init pkram_create_merged_reserved(struct memblock_type *new)
+{
+	unsigned long cnt_a;
+	unsigned long cnt_b;
+	long i, j, k;
+	struct memblock_region *r;
+	struct memblock_region *rgn;
+	struct pkram_region *pkr;
+	struct pkram_region_list *rl;
+	int idx;
+	unsigned long total_size = 0;
+	unsigned long nr_preserved = 0;
+
+	cnt_a = memblock.reserved.cnt;
+	cnt_b = pkram_sb->nr_regions;
+
+	i = 0;
+	j = 0;
+	k = 0;
+
+	pkr = pkram_first_region(pkram_sb, &rl, &idx);
+	if (!pkr)
+		return -EINVAL;
+	while (i < cnt_a && j < cnt_b && pkr) {
+		r = &memblock.reserved.regions[i];
+		rgn = &new->regions[k];
+
+		if (r->base + r->size <= pkr->base) {
+			*rgn = *r;
+			i++;
+		} else if (pkr->base + pkr->size <= r->base) {
+			rgn->base = pkr->base;
+			rgn->size = pkr->size;
+			memblock_set_region_node(rgn, MAX_NUMNODES);
+
+			nr_preserved +=  (rgn->size >> PAGE_SHIFT);
+			pkr = pkram_next_region(&rl, &idx);
+			j++;
+		} else {
+			pr_err("PKRAM: unexpected overlap:\n");
+			pr_err("PKRAM: reserved: base=%pa,size=%pa,flags=0x%x\n", &r->base,
+				&r->size, (int)r->flags);
+			pr_err("PKRAM: pkram: base=%pa,size=%pa\n", &pkr->base, &pkr->size);
+			return -EBUSY;
+		}
+		total_size += rgn->size;
+		k++;
+	}
+
+	while (i < cnt_a) {
+		r = &memblock.reserved.regions[i];
+		rgn = &new->regions[k];
+
+		*rgn = *r;
+
+		total_size += rgn->size;
+		i++;
+		k++;
+	}
+	while (j < cnt_b && pkr) {
+		rgn = &new->regions[k];
+		rgn->base = pkr->base;
+		rgn->size = pkr->size;
+		memblock_set_region_node(rgn, MAX_NUMNODES);
+
+		nr_preserved += (rgn->size >> PAGE_SHIFT);
+		total_size += rgn->size;
+		pkr = pkram_next_region(&rl, &idx);
+		j++;
+		k++;
+	}
+
+	WARN_ON(cnt_a + cnt_b != k);
+	new->cnt = cnt_a + cnt_b;
+	new->total_size = total_size;
+
+	return 0;
+}
+
+/*
+ * Reserve pages that belong to preserved memory.  This is accomplished by
+ * merging the existing reserved ranges with the preserved ranges into
+ * a new, sufficiently sized memblock reserved array.
+ *
+ * This function should be called at boot time as early as possible to prevent
+ * preserved memory from being recycled.
+ */
+int __init pkram_merge_with_reserved(void)
+{
+	struct memblock_type new;
+	unsigned long new_max;
+	phys_addr_t new_size;
+	phys_addr_t addr;
+	int err;
+
+	/*
+	 * Need space to insert one more range into memblock.reserved
+	 * without memblock_double_array() being called.
+	 */
+	if (memblock.reserved.cnt == memblock.reserved.max) {
+		WARN_ONCE(1, "PKRAM: no space for new memblock list\n");
+		return -ENOMEM;
+	}
+
+	new_max = memblock.reserved.max + pkram_sb->nr_regions;
+	new_size = PAGE_ALIGN(sizeof(struct memblock_region) * new_max);
+
+	addr = alloc_topdown(new_size);
+	if (!addr)
+		return -ENOMEM;
+
+	new.regions = __va(addr);
+	new.max = new_max;
+	err = pkram_create_merged_reserved(&new);
+	if (err)
+		return err;
+
+	memblock.reserved.cnt = new.cnt;
+	memblock.reserved.max = new.max;
+	memblock.reserved.total_size = new.total_size;
+	memblock.reserved.regions = new.regions;
+
+	return 0;
+}
-- 
1.9.4