From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 15 Feb 2019 13:33:32 +0100
Subject: arm64, mm, efi: Account for GICv3 LPI tables in static memblock
 reserve table
Git-commit: 8a5b403d71affa098009cc3dff1b2c45113021ad
Patch-mainline: v5.0-rc7
References: bsc#1117158 bsc#1134671

In the irqchip and EFI code, we have what basically amounts to a quirk
to work around a peculiarity in the GICv3 architecture, which permits
the system memory address of LPI tables to be programmable only once
after a CPU reset. This means kexec kernels must use the same memory
as the first kernel, and thus ensure that this memory has not been
given out for other purposes by the time the ITS init code runs, which
is not very early for secondary CPUs.

On systems with many CPUs, these reservations could overflow the
memblock reservation table, and this was addressed in commit:

  eff896288872 ("efi/arm: Defer persistent reservations until after paging_init()")

However, this turns out to have made things worse, since the allocation
of page tables and heap space for the resized memblock reservation table
itself may overwrite the regions we are attempting to reserve, which may
cause all kinds of corruption, also considering that the ITS will still
be poking bits into that memory in response to incoming MSIs.

So instead, let's grow the static memblock reservation table on such
systems so it can accommodate these reservations at an earlier time.
This will permit us to revert the above commit in a subsequent patch.

[ mingo: Minor cleanups. ]

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20190215123333.21209-2-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Matthias Brugger <mbrugger@suse.com>
---
 arch/arm64/include/asm/memory.h |   11 +++++++++++
 drivers/firmware/efi/efi.c      |   11 ++++++++++-
 include/linux/memblock.h        |    3 ---
 mm/memblock.c                   |   11 +++++++++--
 4 files changed, 30 insertions(+), 6 deletions(-)

--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -300,6 +300,17 @@ static inline void *phys_to_virt(phys_ad
 #define virt_addr_valid(kaddr)		(_virt_addr_is_linear(kaddr) && \
 					 _virt_addr_valid(kaddr))
 
+/*
+ * Given that the GIC architecture permits ITS implementations that can only be
+ * configured with a LPI table address once, GICv3 systems with many CPUs may
+ * end up reserving a lot of different regions after a kexec for their LPI
+ * tables (one per CPU), as we are forced to reuse the same memory after kexec
+ * (and thus reserve it persistently with EFI beforehand)
+ */
+#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS)
+# define INIT_MEMBLOCK_RESERVED_REGIONS	(INIT_MEMBLOCK_REGIONS + NR_CPUS + 1)
+#endif
+
 #include <asm-generic/memory_model.h>
 
 #endif
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -962,7 +962,16 @@ int __ref efi_mem_reserve_persistent(phy
 	/* first try to find a slot in an existing linked list entry */
 	for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) {
 		rsv = __va(prsv);
-		index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
+		/* implement atomic_fetch_add_unless for
+		 * index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
+		 */
+		index = atomic_read(&rsv->count);
+
+		do {
+			if (unlikely(index == rsv->size))
+				break;
+		} while (!atomic_try_cmpxchg(&rsv->count, &index, index + 1));
+
 		if (index < rsv->size) {
 			rsv->entry[index].base = addr;
 			rsv->entry[index].size = size;
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -17,9 +17,6 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-#define INIT_MEMBLOCK_REGIONS	128
-#define INIT_PHYSMEM_REGIONS	4
-
 /* Definition of memblock flags. */
 enum {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -25,8 +25,15 @@
 
 #include "internal.h"
 
+#define INIT_MEMBLOCK_REGIONS			128
+#define INIT_PHYSMEM_REGIONS			4
+
+#ifndef INIT_MEMBLOCK_RESERVED_REGIONS
+# define INIT_MEMBLOCK_RESERVED_REGIONS		INIT_MEMBLOCK_REGIONS
+#endif
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
-static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock;
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
 static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
 #endif
@@ -39,7 +46,7 @@ struct memblock memblock __initdata_memb
 
 	.reserved.regions	= memblock_reserved_init_regions,
 	.reserved.cnt		= 1,	/* empty dummy entry */
-	.reserved.max		= INIT_MEMBLOCK_REGIONS,
+	.reserved.max		= INIT_MEMBLOCK_RESERVED_REGIONS,
 	.reserved.name		= "reserved",
 
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP