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:   Vijay Balakrishna <vijayb@linux.microsoft.com>
To:     Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>
Cc:     Nicolas Saenz Julienne <nsaenz@kernel.org>,
        Anshuman Khandual <anshuman.khandual@arm.com>,
        Mike Rapoport <rppt@kernel.org>,
        Ard Biesheuvel <ardb@kernel.org>,
        Pavel Tatashin <pasha.tatashin@soleen.com>,
        Vijay Balakrishna <vijayb@linux.microsoft.com>,
        linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org
Subject: [PATCH] arm64: Do not defer reserve_crashkernel() for platforms with no DMA memory zones
Date:   Wed, 16 Feb 2022 16:04:54 -0800
Message-Id: <1645056294-6509-1-git-send-email-vijayb@linux.microsoft.com>
Precedence: bulk

The following patches resulted in deferring crash kernel reservation to
mem_init(), mainly aimed at platforms with DMA memory zones (no IOMMU),
in particular Raspberry Pi 4.

commit 1a8e1cef7603 ("arm64: use both ZONE_DMA and ZONE_DMA32")
commit 8424ecdde7df ("arm64: mm: Set ZONE_DMA size based on devicetree's dma-ranges")
commit 0a30c53573b0 ("arm64: mm: Move reserve_crashkernel() into mem_init()")
commit 2687275a5843 ("arm64: Force NO_BLOCK_MAPPINGS if crashkernel reservation is required")

Above changes introduced boot slowdown due to linear map creation for
all the memory banks with NO_BLOCK_MAPPINGS, see discussion[1].  The proposed
changes restore crash kernel reservation to earlier behavior thus avoids
slow boot, particularly for platforms with IOMMU (no DMA memory zones).

[1] https://lore.kernel.org/all/9436d033-579b-55fa-9b00-6f4b661c2dd7@linux.microsoft.com/

Signed-off-by: Vijay Balakrishna <vijayb@linux.microsoft.com>
Cc: stable@vger.kernel.org
---
Tested changes to confirm no ~150ms boot slowdown on our SoC with IOMMU
and 8GB memory.  Also tested with ZONE_DMA and/or ZONE_DMA32 configs to confirm
no regression to deferring scheme of crash kernel memory reservation.
In both cases successfully collected kernel crash dump.
---
 arch/arm64/mm/init.c | 14 +++++++++++---
 arch/arm64/mm/mmu.c  | 24 +++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index db63cc885771..f2a982c19b75 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -62,7 +62,11 @@ EXPORT_SYMBOL(memstart_addr);
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
  */
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+#if !defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#endif
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -153,8 +157,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
-	if (!arm64_dma_phys_limit)
-		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -315,6 +317,10 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
+#if !defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
+	reserve_crashkernel();
+#endif
+
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -357,11 +363,13 @@ void __init bootmem_init(void)
 	 */
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
+#if defined(CONFIG_ZONE_DMA) || defined(CONFIG_ZONE_DMA32)
 	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
 	reserve_crashkernel();
+#endif
 
 	memblock_dump_all();
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index acfae9b41cc8..e7faf5edccfc 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -517,7 +517,7 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
 
-	if (can_set_direct_map() || crash_mem_map || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
@@ -528,6 +528,14 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
 
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map && !crashk_res.end)
+		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+	if (crashk_res.end)
+		memblock_mark_nomap(crashk_res.start,
+				    resource_size(&crashk_res));
+#endif
 	/* map all the memory banks */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -554,6 +562,20 @@ static void __init map_mem(pgd_t *pgdp)
 	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+#ifdef CONFIG_KEXEC_CORE
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+	if (crashk_res.end) {
+		__map_memblock(pgdp, crashk_res.start, crashk_res.end + 1,
+			       PAGE_KERNEL,
+			       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+		memblock_clear_nomap(crashk_res.start,
+				     resource_size(&crashk_res));
+	}
+#endif
 }
 
 void mark_rodata_ro(void)
-- 
2.35.1