diff mbox series

[v5,8/8] x86/module: enable ROX caches for module text

Message ID 20241009180816.83591-9-rppt@kernel.org (mailing list archive)
State Superseded
Headers show
Series x86/module: use large ROX pages for text allocations | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch, async
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-17 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc

Commit Message

Mike Rapoport Oct. 9, 2024, 6:08 p.m. UTC 
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

Enable execmem's cache of PMD_SIZE'ed pages mapped as ROX for module
text allocations.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 arch/x86/mm/init.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

Comments

Sergey Senozhatsky Oct. 10, 2024, 8:30 a.m. UTC | #1 
On (24/10/09 21:08), Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Enable execmem's cache of PMD_SIZE'ed pages mapped as ROX for module
> text allocations.
> 

With this modprobe disappoints kmemleak

[   12.700128] kmemleak: Found object by alias at 0xffffffffa000a000
[   12.702179] CPU: 5 UID: 0 PID: 410 Comm: modprobe Tainted: G                 N 6.12.0-rc2+ #760
[   12.704656] Tainted: [N]=TEST
[   12.705526] Call Trace:
[   12.706250]  <TASK>
[   12.706888]  dump_stack_lvl+0x3e/0xdb
[   12.707961]  __find_and_get_object+0x100/0x110
[   12.709256]  kmemleak_no_scan+0x2e/0xb0
[   12.710354]  kmemleak_load_module+0xad/0xe0
[   12.711557]  load_module+0x2391/0x45a0
[   12.712507]  __se_sys_finit_module+0x4e0/0x7a0
[   12.713599]  do_syscall_64+0x54/0xf0
[   12.714477]  ? irqentry_exit_to_user_mode+0x33/0x100
[   12.715696]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[   12.716931] RIP: 0033:0x7fc7af51f059
[   12.717816] Code: 08 89 e8 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 8f 1d 0d 00 f7 d8 64 89 01 48
[   12.722324] RSP: 002b:00007ffc1d0b0c18 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[   12.724173] RAX: ffffffffffffffda RBX: 00005618a9439b20 RCX: 00007fc7af51f059
[   12.725884] RDX: 0000000000000000 RSI: 000056187aea098b RDI: 0000000000000003
[   12.727617] RBP: 0000000000000000 R08: 0000000000000060 R09: 00005618a943af60
[   12.729361] R10: 0000000000000038 R11: 0000000000000246 R12: 000056187aea098b
[   12.731101] R13: 0000000000040000 R14: 00005618a9439ac0 R15: 0000000000000000
[   12.732814]  </TASK>
[   12.733362] kmemleak: Object 0xffffffffa0000000 (size 2097152):
[   12.734800] kmemleak:   comm "modprobe", pid 410, jiffies 4294880489
[   12.736334] kmemleak:   min_count = 2
[   12.737228] kmemleak:   count = 0
[   12.738043] kmemleak:   flags = 0x5
[   12.738917] kmemleak:   checksum = 0
[   12.739783] kmemleak:   backtrace:
[   12.740606]  kmemleak_vmalloc+0x29/0xc0
[   12.741532]  kasan_alloc_module_shadow+0xbe/0xe0
[   12.742649]  execmem_vmalloc+0x116/0x220
[   12.743596]  execmem_alloc+0xfb/0x3d0
[   12.744479]  load_module+0x1e84/0x45a0
[   12.745383]  __se_sys_finit_module+0x4e0/0x7a0
[   12.746452]  do_syscall_64+0x54/0xf0
[   12.747319]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[   12.748772] kmemleak: Not scanning unknown object at 0xffffffffa000a000
[   12.750364] CPU: 5 UID: 0 PID: 410 Comm: modprobe Tainted: G                 N 6.12.0-rc2+ #760
[   12.752441] Tainted: [N]=TEST
[   12.753165] Call Trace:
[   12.753760]  <TASK>
[   12.754279]  dump_stack_lvl+0x3e/0xdb
[   12.755165]  kmemleak_load_module+0xad/0xe0
[   12.756165]  load_module+0x2391/0x45a0
[   12.757068]  __se_sys_finit_module+0x4e0/0x7a0
[   12.758135]  do_syscall_64+0x54/0xf0
[   12.759099]  ? irqentry_exit_to_user_mode+0x33/0x100
[   12.760292]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[   12.761508] RIP: 0033:0x7fc7af51f059
[   12.762372] Code: 08 89 e8 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 8f 1d 0d 00 f7 d8 64 89 01 48
[   12.772361] RSP: 002b:00007ffc1d0b0c18 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[   12.774957] RAX: ffffffffffffffda RBX: 00005618a9439b20 RCX: 00007fc7af51f059
[   12.776635] RDX: 0000000000000000 RSI: 000056187aea098b RDI: 0000000000000003
[   12.778283] RBP: 0000000000000000 R08: 0000000000000060 R09: 00005618a943af60
[   12.779949] R10: 0000000000000038 R11: 0000000000000246 R12: 000056187aea098b
[   12.781619] R13: 0000000000040000 R14: 00005618a9439ac0 R15: 0000000000000000
[   12.783319]  </TASK>
Mike Rapoport Oct. 10, 2024, 3:20 p.m. UTC | #2 
On Thu, Oct 10, 2024 at 05:30:33PM +0900, Sergey Senozhatsky wrote:
> On (24/10/09 21:08), Mike Rapoport wrote:
> > From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> > 
> > Enable execmem's cache of PMD_SIZE'ed pages mapped as ROX for module
> > text allocations.
> > 
> 
> With this modprobe disappoints kmemleak
> 
> [   12.700128] kmemleak: Found object by alias at 0xffffffffa000a000
> [   12.702179] CPU: 5 UID: 0 PID: 410 Comm: modprobe Tainted: G                 N 6.12.0-rc2+ #760
> [   12.704656] Tainted: [N]=TEST
> [   12.705526] Call Trace:
> [   12.706250]  <TASK>
> [   12.706888]  dump_stack_lvl+0x3e/0xdb
> [   12.707961]  __find_and_get_object+0x100/0x110
> [   12.709256]  kmemleak_no_scan+0x2e/0xb0
> [   12.710354]  kmemleak_load_module+0xad/0xe0
> [   12.711557]  load_module+0x2391/0x45a0
> [   12.712507]  __se_sys_finit_module+0x4e0/0x7a0
> [   12.713599]  do_syscall_64+0x54/0xf0
> [   12.714477]  ? irqentry_exit_to_user_mode+0x33/0x100
> [   12.715696]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
> [   12.716931] RIP: 0033:0x7fc7af51f059
> [   12.717816] Code: 08 89 e8 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 8f 1d 0d 00 f7 d8 64 89 01 48
> [   12.722324] RSP: 002b:00007ffc1d0b0c18 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
> [   12.724173] RAX: ffffffffffffffda RBX: 00005618a9439b20 RCX: 00007fc7af51f059
> [   12.725884] RDX: 0000000000000000 RSI: 000056187aea098b RDI: 0000000000000003
> [   12.727617] RBP: 0000000000000000 R08: 0000000000000060 R09: 00005618a943af60
> [   12.729361] R10: 0000000000000038 R11: 0000000000000246 R12: 000056187aea098b
> [   12.731101] R13: 0000000000040000 R14: 00005618a9439ac0 R15: 0000000000000000
> [   12.732814]  </TASK>

Below is a quick fix, I'll revisit module - kmemleak interaction in v6


diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c
index b4cc03842d70..df873dad049d 100644
--- a/kernel/module/debug_kmemleak.c
+++ b/kernel/module/debug_kmemleak.c
@@ -14,7 +14,8 @@ void kmemleak_load_module(const struct module *mod,
 {
 	/* only scan writable, non-executable sections */
 	for_each_mod_mem_type(type) {
-		if (type != MOD_DATA && type != MOD_INIT_DATA)
+		if (type != MOD_DATA && type != MOD_INIT_DATA &&
+		    !mod->mem[type].is_rox)
 			kmemleak_no_scan(mod->mem[type].base);
 	}
 }
diff mbox series

Patch

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index eb503f53c319..a0ec99fb9385 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1053,6 +1053,15 @@  unsigned long arch_max_swapfile_size(void)
 #ifdef CONFIG_EXECMEM
 static struct execmem_info execmem_info __ro_after_init;
 
+static void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable)
+{
+	/* fill memory with INT3 instructions */
+	if (writeable)
+		memset(ptr, INT3_INSN_OPCODE, size);
+	else
+		text_poke_set(ptr, INT3_INSN_OPCODE, size);
+}
+
 struct execmem_info __init *execmem_arch_setup(void)
 {
 	unsigned long start, offset = 0;
@@ -1063,8 +1072,23 @@  struct execmem_info __init *execmem_arch_setup(void)
 	start = MODULES_VADDR + offset;
 
 	execmem_info = (struct execmem_info){
+		.fill_trapping_insns = execmem_fill_trapping_insns,
 		.ranges = {
-			[EXECMEM_DEFAULT] = {
+			[EXECMEM_MODULE_TEXT] = {
+				.flags	= EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL_ROX,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_KPROBES ... EXECMEM_BPF] = {
+				.flags	= EXECMEM_KASAN_SHADOW,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_MODULE_DATA] = {
 				.flags	= EXECMEM_KASAN_SHADOW,
 				.start	= start,
 				.end	= MODULES_END,