From: Logan Gunthorpe <logang@deltatee.com>
To: linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org
Cc: Stefan O'Rear <sorear2@gmail.com>,
Albert Ou <aou@eecs.berkeley.edu>,
Palmer Dabbelt <palmer@sifive.com>,
Mike Rapoport <rppt@linux.ibm.com>, Zong Li <zong@andestech.com>,
Anup Patel <anup.patel@wdc.com>, Guo Ren <ren_guo@c-sky.com>,
Stephen Bates <sbates@raithlin.com>,
Logan Gunthorpe <logang@deltatee.com>,
Christoph Hellwig <hch@lst.de>
Subject: [PATCH 6/7] RISC-V: Implement memory hot remove
Date: Wed, 27 Mar 2019 15:36:42 -0600 [thread overview]
Message-ID: <20190327213643.23789-7-logang@deltatee.com> (raw)
In-Reply-To: <20190327213643.23789-1-logang@deltatee.com>
Implementing arch_remove_memory() and filling in vmemap_free() allows
us to declare ARCH_ENABLE_MEMORY_HOTREMOVE.
arch_remove_memory() is very similar to x86 and we roughly copy the
remove_pagetable() function from x86 but with a bunch of the unnecessary
features stripped out.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: "Stefan O'Rear" <sorear2@gmail.com>
Cc: Anup Patel <anup.patel@wdc.com>
Cc: Zong Li <zong@andestech.com>
Cc: Guo Ren <ren_guo@c-sky.com>
---
arch/riscv/Kconfig | 3 +
arch/riscv/include/asm/pgtable-64.h | 2 +
arch/riscv/include/asm/pgtable.h | 5 +
arch/riscv/mm/init.c | 186 ++++++++++++++++++++++++++++
4 files changed, 196 insertions(+)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 9477214a00e7..2cb39b4d6d6b 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -86,6 +86,9 @@ config ARCH_SELECT_MEMORY_MODEL
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+ def_bool y
+
config STACKTRACE_SUPPORT
def_bool y
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 7aa0ea9bd8bb..d369be5467cf 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -67,6 +67,8 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
}
#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
{
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 2a5070540996..e071e2be3a6c 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -173,6 +173,11 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
return (unsigned long)pfn_to_virt(pmd_val(pmd) >> _PAGE_PFN_SHIFT);
}
+static inline struct page *pud_page(pud_t pud)
+{
+ return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT);
+}
+
/* Yields the page frame number (PFN) of a page table entry */
static inline unsigned long pte_pfn(pte_t pte)
{
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 0a54c3adf0ac..fffe1238434e 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -240,9 +240,175 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
+static void __meminit free_pagetable(struct page *page, int order)
+{
+ unsigned long magic;
+ unsigned int nr_pages = 1 << order;
+
+ /* bootmem page has reserved flag */
+ if (PageReserved(page)) {
+ __ClearPageReserved(page);
+
+ magic = (unsigned long)page->freelist;
+ if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
+ while (nr_pages--)
+ put_page_bootmem(page++);
+ } else {
+ while (nr_pages--)
+ free_reserved_page(page++);
+ }
+ } else {
+ free_pages((unsigned long)page_address(page), order);
+ }
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+ pte_t *pte;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte = pte_start + i;
+ if (!pte_none(*pte))
+ return;
+ }
+
+ /* free a pte table */
+ free_pagetable(pmd_page(*pmd), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pmd_clear(pmd);
+ spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+ pmd_t *pmd;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ pmd = pmd_start + i;
+ if (!pmd_none(*pmd))
+ return;
+ }
+
+ /* free a pmd table */
+ free_pagetable(pud_page(*pud), 0);
+ spin_lock(&init_mm.page_table_lock);
+ pud_clear(pud);
+ spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit
+remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pte_t *pte;
+
+ pte = pte_start + pte_index(addr);
+ for (; addr < end; addr = next, pte++) {
+ next = (addr + PAGE_SIZE) & PAGE_MASK;
+ if (next > end)
+ next = end;
+
+ if (!pte_present(*pte))
+ continue;
+
+ free_pagetable(pte_page(*pte), 0);
+
+ spin_lock(&init_mm.page_table_lock);
+ pte_clear(&init_mm, addr, pte);
+ spin_unlock(&init_mm.page_table_lock);
+ }
+
+ flush_tlb_all();
+}
+
+static void __meminit
+remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pte_t *pte_base;
+ pmd_t *pmd;
+
+ pmd = pmd_start + pmd_index(addr);
+ for (; addr < end; addr = next, pmd++) {
+ next = pmd_addr_end(addr, end);
+
+ if (!pmd_present(*pmd))
+ continue;
+
+ pte_base = (pte_t *)pmd_page_vaddr(*pmd);
+ remove_pte_table(pte_base, addr, next);
+ free_pte_table(pte_base, pmd);
+ }
+}
+
+static void __meminit
+remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pmd_t *pmd_base;
+ pud_t *pud;
+
+ pud = pud_start + pud_index(addr);
+ for (; addr < end; addr = next, pud++) {
+ next = pud_addr_end(addr, end);
+
+ if (!pud_present(*pud))
+ continue;
+
+ pmd_base = pmd_offset(pud, 0);
+ remove_pmd_table(pmd_base, addr, next);
+ free_pmd_table(pmd_base, pud);
+ }
+}
+
+static void __meminit
+remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pud_t *pud_base;
+ p4d_t *p4d;
+
+ p4d = p4d_start + p4d_index(addr);
+ for (; addr < end; addr = next, p4d++) {
+ next = p4d_addr_end(addr, end);
+
+ if (!p4d_present(*p4d))
+ continue;
+
+ pud_base = pud_offset(p4d, 0);
+ remove_pud_table(pud_base, addr, next);
+ }
+}
+
+/* start and end are both virtual address. */
+static void __meminit
+remove_pagetable(unsigned long start, unsigned long end)
+{
+ unsigned long next;
+ unsigned long addr;
+ pgd_t *pgd;
+ p4d_t *p4d;
+
+ for (addr = start; addr < end; addr = next) {
+ next = pgd_addr_end(addr, end);
+
+ pgd = pgd_offset_k(addr);
+ if (!pgd_present(*pgd))
+ continue;
+
+ p4d = p4d_offset(pgd, 0);
+ remove_p4d_table(p4d, addr, next);
+ }
+
+ flush_tlb_all();
+}
+
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
+ remove_pagetable(start, end);
}
int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
@@ -264,4 +430,24 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
return ret;
}
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int __ref arch_remove_memory(int nid, u64 start, u64 size,
+ struct vmem_altmap *altmap)
+{
+ unsigned long start_pfn = start >> PAGE_SHIFT;
+ unsigned long nr_pages = size >> PAGE_SHIFT;
+ struct page *page = pfn_to_page(start_pfn);
+ struct zone *zone;
+ int ret;
+
+ if (altmap)
+ page += vmem_altmap_offset(altmap);
+ zone = page_zone(page);
+ ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
+ WARN_ON_ONCE(ret);
+
+ return ret;
+}
+
+#endif
#endif
--
2.20.1
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2019-03-27 21:37 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-27 21:36 [PATCH 0/7] RISC-V: Sparsmem, Memory Hotplug and pte_devmap for P2P Logan Gunthorpe
2019-03-27 21:36 ` [PATCH 1/7] RISC-V: Implement sparsemem Logan Gunthorpe
2019-03-27 21:36 ` [PATCH 2/7] RISC-V: doc: Add file describing the virtual memory map Logan Gunthorpe
2019-03-28 11:49 ` Mike Rapoport
2019-03-28 15:51 ` Logan Gunthorpe
2019-03-27 21:36 ` [PATCH 3/7] RISC-V: Rework kernel's virtual address space mapping Logan Gunthorpe
2019-03-28 5:39 ` Palmer Dabbelt
2019-03-28 6:28 ` Anup Patel
2019-03-28 15:54 ` Logan Gunthorpe
2019-03-27 21:36 ` [PATCH 4/7] RISC-V: Update page tables to cover the whole linear mapping Logan Gunthorpe
2019-03-28 10:03 ` Anup Patel
2019-03-28 18:24 ` Logan Gunthorpe
2019-03-27 21:36 ` [PATCH 5/7] RISC-V: Implement memory hotplug Logan Gunthorpe
2019-03-27 21:36 ` Logan Gunthorpe [this message]
2019-03-27 21:36 ` [PATCH 7/7] RISC-V: Implement pte_devmap() Logan Gunthorpe
2019-04-24 23:23 ` [PATCH 0/7] RISC-V: Sparsmem, Memory Hotplug and pte_devmap for P2P Palmer Dabbelt
2019-04-26 16:37 ` Logan Gunthorpe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190327213643.23789-7-logang@deltatee.com \
--to=logang@deltatee.com \
--cc=anup.patel@wdc.com \
--cc=aou@eecs.berkeley.edu \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@sifive.com \
--cc=ren_guo@c-sky.com \
--cc=rppt@linux.ibm.com \
--cc=sbates@raithlin.com \
--cc=sorear2@gmail.com \
--cc=zong@andestech.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).