[RFC v2 06/26] mm/asi: Add ASI page-table entry allocation functions

From: Alexandre Chartre <alexandre.chartre@oracle.com>
To: pbonzini@redhat.com, rkrcmar@redhat.com, tglx@linutronix.de,
	mingo@redhat.com, bp@alien8.de, hpa@zytor.com,
	dave.hansen@linux.intel.com, luto@kernel.org,
	peterz@infradead.org, kvm@vger.kernel.org, x86@kernel.org,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: konrad.wilk@oracle.com, jan.setjeeilers@oracle.com,
	liran.alon@oracle.com, jwadams@google.com, graf@amazon.de,
	rppt@linux.vnet.ibm.com, alexandre.chartre@oracle.com
Subject: [RFC v2 06/26] mm/asi: Add ASI page-table entry allocation functions
Date: Thu, 11 Jul 2019 16:25:18 +0200	[thread overview]
Message-ID: <1562855138-19507-7-git-send-email-alexandre.chartre@oracle.com> (raw)
In-Reply-To: <1562855138-19507-1-git-send-email-alexandre.chartre@oracle.com>

Add functions to allocate p4d/pud/pmd/pte pages for an ASI page-table
and keep track of them.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 arch/x86/mm/asi_pagetable.c |  111 +++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 111 insertions(+), 0 deletions(-)

diff --git a/arch/x86/mm/asi_pagetable.c b/arch/x86/mm/asi_pagetable.c
index a89e02e..0fc6d59 100644
--- a/arch/x86/mm/asi_pagetable.c
+++ b/arch/x86/mm/asi_pagetable.c
@@ -4,6 +4,8 @@
  *
  */
 
+#include <linux/mm.h>
+
 #include <asm/asi.h>
 
 /*
@@ -159,3 +161,112 @@ static bool asi_valid_offset(struct asi *asi, void *offset)
 
 	return p4d;
 }
+
+/*
+ * asi_pXX_alloc() functions are equivalent to kernel pXX_alloc() functions
+ * but, in addition, they keep track of new pages allocated for the specified
+ * ASI.
+ */
+
+static pte_t *asi_pte_alloc(struct asi *asi, pmd_t *pmd, unsigned long addr)
+{
+	struct page *page;
+	pte_t *pte;
+	int err;
+
+	if (pmd_none(*pmd)) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		pte = (pte_t *)page_address(page);
+		err = asi_add_backend_page(asi, pte, PGT_LEVEL_PTE);
+		if (err) {
+			free_page((unsigned long)pte);
+			return ERR_PTR(err);
+		}
+		set_pmd_safe(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+		pte = pte_offset_map(pmd, addr);
+	} else {
+		pte = asi_pte_offset(asi, pmd,  addr);
+	}
+
+	return pte;
+}
+
+static pmd_t *asi_pmd_alloc(struct asi *asi, pud_t *pud, unsigned long addr)
+{
+	struct page *page;
+	pmd_t *pmd;
+	int err;
+
+	if (pud_none(*pud)) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		pmd = (pmd_t *)page_address(page);
+		err = asi_add_backend_page(asi, pmd, PGT_LEVEL_PMD);
+		if (err) {
+			free_page((unsigned long)pmd);
+			return ERR_PTR(err);
+		}
+		set_pud_safe(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+		pmd = pmd_offset(pud, addr);
+	} else {
+		pmd = asi_pmd_offset(asi, pud, addr);
+	}
+
+	return pmd;
+}
+
+static pud_t *asi_pud_alloc(struct asi *asi, p4d_t *p4d, unsigned long addr)
+{
+	struct page *page;
+	pud_t *pud;
+	int err;
+
+	if (p4d_none(*p4d)) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		pud = (pud_t *)page_address(page);
+		err = asi_add_backend_page(asi, pud, PGT_LEVEL_PUD);
+		if (err) {
+			free_page((unsigned long)pud);
+			return ERR_PTR(err);
+		}
+		set_p4d_safe(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+		pud = pud_offset(p4d, addr);
+	} else {
+		pud = asi_pud_offset(asi, p4d, addr);
+	}
+
+	return pud;
+}
+
+static p4d_t *asi_p4d_alloc(struct asi *asi, pgd_t *pgd, unsigned long addr)
+{
+	struct page *page;
+	p4d_t *p4d;
+	int err;
+
+	if (!pgtable_l5_enabled())
+		return (p4d_t *)pgd;
+
+	if (pgd_none(*pgd)) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			return ERR_PTR(-ENOMEM);
+		p4d = (p4d_t *)page_address(page);
+		err = asi_add_backend_page(asi, p4d, PGT_LEVEL_P4D);
+		if (err) {
+			free_page((unsigned long)p4d);
+			return ERR_PTR(err);
+		}
+		set_pgd_safe(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+		p4d = p4d_offset(pgd, addr);
+	} else {
+		p4d = asi_p4d_offset(asi, pgd, addr);
+	}
+
+	return p4d;
+}
-- 
1.7.1

