Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Leonardo Bras <leobras.c@gmail.com>
To:     Michael Ellerman <mpe@ellerman.id.au>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Leonardo Bras <leobras.c@gmail.com>,
        Sandipan Das <sandipan@linux.ibm.com>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
        Logan Gunthorpe <logang@deltatee.com>,
        Mike Rapoport <rppt@kernel.org>,
        Bharata B Rao <bharata@linux.ibm.com>,
        Dan Williams <dan.j.williams@intel.com>,
        Nicholas Piggin <npiggin@gmail.com>,
        Nathan Lynch <nathanl@linux.ibm.com>,
        David Hildenbrand <david@redhat.com>,
        Laurent Dufour <ldufour@linux.ibm.com>,
        Scott Cheloha <cheloha@linux.ibm.com>,
        David Gibson <david@gibson.dropbear.id.au>
Cc:     linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH 2/3] powerpc/mm/hash: Avoid multiple HPT resize-ups on memory hotplug
Date:   Fri, 12 Mar 2021 04:29:40 -0300
Message-Id: <20210312072940.598696-3-leobras.c@gmail.com>
In-Reply-To: <20210312072940.598696-1-leobras.c@gmail.com>
References: <20210312072940.598696-1-leobras.c@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Every time a memory hotplug happens, and the memory limit crosses a 2^n
value, it may be necessary to perform HPT resizing-up, which can take
some time (over 100ms in my tests).

It usually is not an issue, but it can take some time if a lot of memory
is added to a guest with little starting memory:
Adding 256G to a 2GB guest, for example will require 8 HPT resizes.

Perform an HPT resize before memory hotplug, updating HPT to its
final size (considering a successful hotplug), taking the number of
HPT resizes to at most one per memory hotplug action.

Signed-off-by: Leonardo Bras <leobras.c@gmail.com>
---
 arch/powerpc/include/asm/book3s/64/hash.h       |  2 ++
 arch/powerpc/include/asm/sparsemem.h            |  2 ++
 arch/powerpc/mm/book3s64/hash_utils.c           | 14 ++++++++++++++
 arch/powerpc/mm/book3s64/pgtable.c              |  6 ++++++
 arch/powerpc/platforms/pseries/hotplug-memory.c |  6 ++++++
 5 files changed, 30 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index d959b0195ad9..843b0a178590 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -255,6 +255,8 @@ int hash__create_section_mapping(unsigned long start, unsigned long end,
 				 int nid, pgprot_t prot);
 int hash__remove_section_mapping(unsigned long start, unsigned long end);
 
+void hash_memory_batch_expand_prepare(unsigned long newsize);
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index d072866842e4..16b5f5300c84 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -17,6 +17,8 @@ extern int remove_section_mapping(unsigned long start, unsigned long end);
 extern int memory_add_physaddr_to_nid(u64 start);
 #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
 
+void memory_batch_expand_prepare(unsigned long newsize);
+
 #ifdef CONFIG_NUMA
 extern int hot_add_scn_to_nid(unsigned long scn_addr);
 #else
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index cfb3ec164f56..1f6aa0bf27e7 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -858,6 +858,20 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end)
 
 	return rc;
 }
+
+void hash_memory_batch_expand_prepare(unsigned long newsize)
+{
+	/*
+	 * Resizing-up HPT should never fail, but there are some cases system starts with higher
+	 * SHIFT than required, and we go through the funny case of resizing HPT down while
+	 * adding memory
+	 */
+
+	while (resize_hpt_for_hotplug(newsize, false) == -ENOSPC) {
+		newsize *= 2;
+		pr_warn("Hash collision while resizing HPT\n");
+	}
+}
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __init hash_init_partition_table(phys_addr_t hash_table,
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 5b3a3bae21aa..f1cd8af0f67f 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -193,6 +193,12 @@ int __meminit remove_section_mapping(unsigned long start, unsigned long end)
 
 	return hash__remove_section_mapping(start, end);
 }
+
+void memory_batch_expand_prepare(unsigned long newsize)
+{
+	if (!radix_enabled())
+		hash_memory_batch_expand_prepare(newsize);
+}
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 void __init mmu_partition_table_init(void)
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 8377f1f7c78e..353c71249214 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -671,6 +671,8 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add)
 	if (lmbs_available < lmbs_to_add)
 		return -EINVAL;
 
+	memory_batch_expand_prepare(memblock_phys_mem_size() + lmbs_to_add * drmem_lmb_size());
+
 	for_each_drmem_lmb(lmb) {
 		if (lmb->flags & DRCONF_MEM_ASSIGNED)
 			continue;
@@ -734,6 +736,8 @@ static int dlpar_memory_add_by_index(u32 drc_index)
 
 	pr_info("Attempting to hot-add LMB, drc index %x\n", drc_index);
 
+	memory_batch_expand_prepare(memblock_phys_mem_size() +
+				     drmem_info->n_lmbs * drmem_lmb_size());
 	lmb_found = 0;
 	for_each_drmem_lmb(lmb) {
 		if (lmb->drc_index == drc_index) {
@@ -788,6 +792,8 @@ static int dlpar_memory_add_by_ic(u32 lmbs_to_add, u32 drc_index)
 	if (lmbs_available < lmbs_to_add)
 		return -EINVAL;
 
+	memory_batch_expand_prepare(memblock_phys_mem_size() + lmbs_to_add * drmem_lmb_size());
+
 	for_each_drmem_lmb_in_range(lmb, start_lmb, end_lmb) {
 		if (lmb->flags & DRCONF_MEM_ASSIGNED)
 			continue;
-- 
2.29.2