[PATCH v2] riscv: Ensure BPF_JIT_REGION_START aligned with PMD size

[Jisheng Zhang]

Andreas reported commit fc8504765ec5 ("riscv: bpf: Avoid breaking W^X")
breaks booting with one kind of defconfig, I reproduced a kernel panic
with the defconfig:

[    0.138553] Unable to handle kernel paging request at virtual address ffffffff81201220
[    0.139159] Oops [#1]
[    0.139303] Modules linked in:
[    0.139601] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-rc5-default+ #1
[    0.139934] Hardware name: riscv-virtio,qemu (DT)
[    0.140193] epc : __memset+0xc4/0xfc
[    0.140416]  ra : skb_flow_dissector_init+0x1e/0x82
[    0.140609] epc : ffffffff8029806c ra : ffffffff8033be78 sp : ffffffe001647da0
[    0.140878]  gp : ffffffff81134b08 tp : ffffffe001654380 t0 : ffffffff81201158
[    0.141156]  t1 : 0000000000000002 t2 : 0000000000000154 s0 : ffffffe001647dd0
[    0.141424]  s1 : ffffffff80a43250 a0 : ffffffff81201220 a1 : 0000000000000000
[    0.141654]  a2 : 000000000000003c a3 : ffffffff81201258 a4 : 0000000000000064
[    0.141893]  a5 : ffffffff8029806c a6 : 0000000000000040 a7 : ffffffffffffffff
[    0.142126]  s2 : ffffffff81201220 s3 : 0000000000000009 s4 : ffffffff81135088
[    0.142353]  s5 : ffffffff81135038 s6 : ffffffff8080ce80 s7 : ffffffff80800438
[    0.142584]  s8 : ffffffff80bc6578 s9 : 0000000000000008 s10: ffffffff806000ac
[    0.142810]  s11: 0000000000000000 t3 : fffffffffffffffc t4 : 0000000000000000
[    0.143042]  t5 : 0000000000000155 t6 : 00000000000003ff
[    0.143220] status: 0000000000000120 badaddr: ffffffff81201220 cause: 000000000000000f
[    0.143560] [<ffffffff8029806c>] __memset+0xc4/0xfc
[    0.143859] [<ffffffff8061e984>] init_default_flow_dissectors+0x22/0x60
[    0.144092] [<ffffffff800010fc>] do_one_initcall+0x3e/0x168
[    0.144278] [<ffffffff80600df0>] kernel_init_freeable+0x1c8/0x224
[    0.144479] [<ffffffff804868a8>] kernel_init+0x12/0x110
[    0.144658] [<ffffffff800022de>] ret_from_exception+0x0/0xc
[    0.145124] ---[ end trace f1e9643daa46d591 ]---

After some investigation, I think I found the root cause: commit
2bfc6cd81bd ("move kernel mapping outside of linear mapping") moves
BPF JIT region after the kernel:

The &_end is unlikely aligned with PMD size, so the front bpf jit
region sits with part of kernel .data section in one PMD size mapping.
But kernel is mapped in PMD SIZE, when bpf_jit_binary_lock_ro() is
called to make the first bpf jit prog ROX, we will make part of kernel
.data section RO too, so when we write to, for example memset the
.data section, MMU will trigger a store page fault.

To fix the issue, we need to ensure the BPF JIT region is PMD size
aligned. This patch acchieve this goal by restoring the BPF JIT region
to original position, I.E the 128MB before kernel .text section. The
modification to kasan_init.c is inspired by Alexandre.

Reported-by: Andreas Schwab <schwab at linux-m68k.org>
Signed-off-by: Jisheng Zhang <jszhang at kernel.org>
---

Since v1:
 - Fix early boot hang when kasan is enabled
 - Update Documentation/riscv/vm-layout.rst

 Documentation/riscv/vm-layout.rst |  4 ++--
 arch/riscv/include/asm/pgtable.h  |  5 ++---
 arch/riscv/mm/kasan_init.c        | 10 +++++-----
 3 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/Documentation/riscv/vm-layout.rst b/Documentation/riscv/vm-layout.rst
index 329d32098af4..b7f98930d38d 100644
--- a/Documentation/riscv/vm-layout.rst
+++ b/Documentation/riscv/vm-layout.rst
@@ -58,6 +58,6 @@ RISC-V Linux Kernel SV39
                                                               |
   ____________________________________________________________|____________________________________________________________
                     |            |                  |         |
-   ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | modules
-   ffffffff80000000 |   -2    GB | ffffffffffffffff |    2 GB | kernel, BPF
+   ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | modules, BPF
+   ffffffff80000000 |   -2    GB | ffffffffffffffff |    2 GB | kernel
   __________________|____________|__________________|_________|____________________________________________________________
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 9469f464e71a..380cd3a7e548 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -30,9 +30,8 @@
 
 #define BPF_JIT_REGION_SIZE	(SZ_128M)
 #ifdef CONFIG_64BIT
-/* KASLR should leave at least 128MB for BPF after the kernel */
-#define BPF_JIT_REGION_START	PFN_ALIGN((unsigned long)&_end)
-#define BPF_JIT_REGION_END	(BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_START	(BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE)
+#define BPF_JIT_REGION_END	(MODULES_END)
 #else
 #define BPF_JIT_REGION_START	(PAGE_OFFSET - BPF_JIT_REGION_SIZE)
 #define BPF_JIT_REGION_END	(VMALLOC_END)
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 9daacae93e33..d7189c8714a9 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -169,7 +169,7 @@ static void __init kasan_shallow_populate(void *start, void *end)
 
 void __init kasan_init(void)
 {
-	phys_addr_t _start, _end;
+	phys_addr_t p_start, p_end;
 	u64 i;
 
 	/*
@@ -189,9 +189,9 @@ void __init kasan_init(void)
 			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
 
 	/* Populate the linear mapping */
-	for_each_mem_range(i, &_start, &_end) {
-		void *start = (void *)__va(_start);
-		void *end = (void *)__va(_end);
+	for_each_mem_range(i, &p_start, &p_end) {
+		void *start = (void *)__va(p_start);
+		void *end = (void *)__va(p_end);
 
 		if (start >= end)
 			break;
@@ -201,7 +201,7 @@ void __init kasan_init(void)
 
 	/* Populate kernel, BPF, modules mapping */
 	kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR),
-		       kasan_mem_to_shadow((const void *)BPF_JIT_REGION_END));
+		       kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G));
 
 	for (i = 0; i < PTRS_PER_PTE; i++)
 		set_pte(&kasan_early_shadow_pte[i],
-- 
2.32.0