Skip to contentSkip to conversation

powerpc/32s: Allocate modules outside of vmalloc space for STRICT_KERNEL_RWX

PATCH Applied Christophe Leroy 3 participants 11 messages Jun 29, 2020 – Aug 21, 2020 PowerPC

lore
Share & tools
lore
#0 lore raw

v2 cover powerpc/32s: Allocate modules outside of vmalloc space for STRICT_KERNEL_RWX

On book3s32 (hash), exec protection is set per 256Mb segments with NX bit. Instead of clearing NX bit on vmalloc space when CONFIG_MODULES is selected, allocate modules in a dedicated segment (0xb0000000-0xbfffffff by default). This allows to keep exec protection on vmalloc space while allowing exec on modules.

v2:
- Removed the two patches that fix ptdump. Will submitted independently
- Only changing the user/kernel boundary for PPC32 now.
- Reordered the patches inside the series.

Christophe Leroy (6):
powerpc/lib: Prepare code-patching for modules allocated outside
vmalloc space
powerpc: Use MODULES_VADDR if defined
powerpc/32s: Only leave NX unset on segments used for modules powerpc/32: Set user/kernel boundary at TASK_SIZE instead of
PAGE_OFFSET
powerpc/32s: Kernel space starts at TASK_SIZE
powerpc/32s: Use dedicated segment for modules with STRICT_KERNEL_RWX

 arch/powerpc/Kconfig                         |  1 +
 arch/powerpc/include/asm/book3s/32/pgtable.h | 15 +++++----------
 arch/powerpc/include/asm/page.h              |  4 +++-
 arch/powerpc/kernel/head_32.S                | 12 ++++++------
 arch/powerpc/kernel/module.c                 | 11 +++++++++++
 arch/powerpc/lib/code-patching.c             |  2 +-
 arch/powerpc/mm/book3s32/hash_low.S          |  2 +-
 arch/powerpc/mm/book3s32/mmu.c               | 17 ++++++++++++++---
 arch/powerpc/mm/kasan/kasan_init_32.c        |  6 ++++++
 arch/powerpc/mm/ptdump/ptdump.c              | 16 ++++++++++++++--
 10 files changed, 62 insertions(+), 24 deletions(-)
Signature · 1 line
2.25.0
#1 lore raw

PATCH v2 1/6 powerpc/lib: Prepare code-patching for modules allocated outside vmalloc space

Use is_vmalloc_or_module_addr() instead of is_vmalloc_addr()

---
 arch/powerpc/lib/code-patching.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/lib/code-patching.c +1 -1
index 0a051dfeb177..8c3934ea6220 100644
@@ -93,7 +93,7 @@ static int map_patch_area(void *addr, unsigned long text_poke_addr)
 	unsigned long pfn;
 	int err;
 
-	if (is_vmalloc_addr(addr))
+	if (is_vmalloc_or_module_addr(addr))
 		pfn = vmalloc_to_pfn(addr);
 	else
 		pfn = __pa_symbol(addr) >> PAGE_SHIFT;
Signature · 1 line
2.25.0
#2 lore raw

PATCH v2 2/6 powerpc: Use MODULES_VADDR if defined

In reply to Christophe Leroy

In order to allow allocation of modules outside of vmalloc space, use MODULES_VADDR and MODULES_END when MODULES_VADDR is defined.

Redefine module_alloc() when MODULES_VADDR defined. Unmap corresponding KASAN shadow memory.

---
 arch/powerpc/kernel/module.c          | 11 +++++++++++
 arch/powerpc/mm/kasan/kasan_init_32.c |  6 ++++++
 2 files changed, 17 insertions(+)
arch/powerpc/kernel/module.c +11 -0
index df649acb5631..a211b0253cdb 100644
@@ -86,3 +86,14 @@ int module_finalize(const Elf_Ehdr *hdr,
 
 	return 0;
 }
+
+#ifdef MODULES_VADDR
+void *module_alloc(unsigned long size)
+{
+	BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
+				    PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+				    __builtin_return_address(0));
+}
+#endif
arch/powerpc/mm/kasan/kasan_init_32.c +6 -0
index 0760e1e754e4..f1bc267d42af 100644
@@ -115,6 +115,12 @@ static void __init kasan_unmap_early_shadow_vmalloc(void)
 	unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
 
 	kasan_update_early_region(k_start, k_end, __pte(0));
+
+#ifdef MODULES_VADDR
+	k_start = (unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR);
+	k_end = (unsigned long)kasan_mem_to_shadow((void *)MODULES_END);
+	kasan_update_early_region(k_start, k_end, __pte(0));
+#endif
 }
 
 static void __init kasan_mmu_init(void)
Signature · 1 line
2.25.0
#3 lore raw

PATCH v2 3/6 powerpc/32s: Only leave NX unset on segments used for modules

In reply to Christophe Leroy

Instead of leaving NX unset on all segments above the start of vmalloc space, only leave NX unset on segments used for modules.

---
 arch/powerpc/mm/book3s32/mmu.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
arch/powerpc/mm/book3s32/mmu.c +14 -3
index 03b6ba54460e..c0162911f6cb 100644
@@ -187,6 +187,17 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 	return __mmu_mapin_ram(border, top);
 }
 
+static bool is_module_segment(unsigned long addr)
+{
+	if (!IS_ENABLED(CONFIG_MODULES))
+		return false;
+	if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
+		return false;
+	if (addr >= ALIGN(VMALLOC_END, SZ_256M))
+		return false;
+	return true;
+}
+
 void mmu_mark_initmem_nx(void)
 {
 	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
@@ -223,9 +234,9 @@ void mmu_mark_initmem_nx(void)
 
 	for (i = TASK_SIZE >> 28; i < 16; i++) {
 		/* Do not set NX on VM space for modules */
-		if (IS_ENABLED(CONFIG_MODULES) &&
-		    (VMALLOC_START & 0xf0000000) == i << 28)
-			break;
+		if (is_module_segment(i << 28))
+			continue;
+
 		mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
 	}
 }
Signature · 1 line
2.25.0
#4 lore raw

Re: [PATCH v2 3/6] powerpc/32s: Only leave NX unset on segments used for modules

Quoted 3 lines · Christophe Leroy

Instead of leaving NX unset on all segments above the start of vmalloc space, only leave NX unset on segments used for modules.

I'm getting this crash:

kernel tried to execute exec-protected page (f294b000) - exploit attempt (uid: 0)

BUG: Unable to handle kernel instruction fetch
Faulting instruction address: 0xf294b000
Oops: Kernel access of bad area, sig: 11 [#1]
BE PAGE_SIZE=4K MMU=Hash PowerMac
Modules linked in: pata_macio(+)
CPU: 0 PID: 87 Comm: udevd Not tainted 5.8.0-rc2-test #49
NIP:  f294b000 LR: 0005c60 CTR: f294b000
REGS: f18d9cc0 TRAP: 0400  Not tainted  (5.8.0-rc2-test)
MSR:  10009032 <E,ME,IR,DR,RI>  CR: 84222422  XER: 20000000

GPR00: c0005c14 f18d9d78 ef30ca20 00000000 ef0000e0 c00993d0 ef6da038 0000005e
GPR08: c09050b8 c08b0000 00000000 f18d9d78 44222422 10072070 00000000 0fefaca4
GPR16: 1006a00c f294d50b 00000120 00000124 c0096ea8 0000000e ef2776c0 ef2776e4
GPR24: f18fd6e8 00000001 c086fe64 c086fe04 00000000 c08b0000 f294b000 ffffffff NIP [f294b000] pata_macio_init+0x0/0xc0 [pata_macio]
LR [c0005c60] do_one_initcall+0x6c/0x160

Call Trace:
[f18d9d78] [c0005c14] do_one_initcall+0x20/0x160 (unreliable)
[f18d9dd8] [c009a22c] do_init_module+0x60/0x1c0
[f18d9df8] [c00993d8] load_module+0x16a8/0x1c14
[f18d9ea8] [c0099aa4] sys_finit_module+0x8c/0x94
[f18d9f38] [c0012174] ret_from_syscall+0x0/0x34

--- interrupt: c01 at 0xfdb4318
LR = 0xfeee9c0
Instruction dump:
XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX <3d20c08b> 3d40c086 9421ffe0 8129106c

---[ end trace 85a98cc836109871 ]---

Andreas.

Signature · 3 lines
Andreas Schwab, [email protected]
GPG Key fingerprint = 7578 EB47 D4E5 4D69 2510  2552 DF73 E780 A9DA AEC1
"And now for something completely different."
#5 lore raw

Re: [PATCH v2 3/6] powerpc/32s: Only leave NX unset on segments used for modules

Le 21/08/2020 à 00:00, Andreas Schwab a écrit :

Quoted 24 lines · Christophe Leroy
Quoted 4 lines

Instead of leaving NX unset on all segments above the start of vmalloc space, only leave NX unset on segments used for modules.

I'm getting this crash:

kernel tried to execute exec-protected page (f294b000) - exploit attempt (uid: 0)

BUG: Unable to handle kernel instruction fetch
Faulting instruction address: 0xf294b000
Oops: Kernel access of bad area, sig: 11 [#1]
BE PAGE_SIZE=4K MMU=Hash PowerMac
Modules linked in: pata_macio(+)
CPU: 0 PID: 87 Comm: udevd Not tainted 5.8.0-rc2-test #49
NIP:  f294b000 LR: 0005c60 CTR: f294b000
REGS: f18d9cc0 TRAP: 0400  Not tainted  (5.8.0-rc2-test)
MSR:  10009032 <E,ME,IR,DR,RI>  CR: 84222422  XER: 20000000

GPR00: c0005c14 f18d9d78 ef30ca20 00000000 ef0000e0 c00993d0 ef6da038 0000005e
GPR08: c09050b8 c08b0000 00000000 f18d9d78 44222422 10072070 00000000 0fefaca4
GPR16: 1006a00c f294d50b 00000120 00000124 c0096ea8 0000000e ef2776c0 ef2776e4
GPR24: f18fd6e8 00000001 c086fe64 c086fe04 00000000 c08b0000 f294b000 ffffffff NIP [f294b000] pata_macio_init+0x0/0xc0 [pata_macio]
LR [c0005c60] do_one_initcall+0x6c/0x160

Quoted 13 lines
Call Trace:
[f18d9d78] [c0005c14] do_one_initcall+0x20/0x160 (unreliable)
[f18d9dd8] [c009a22c] do_init_module+0x60/0x1c0
[f18d9df8] [c00993d8] load_module+0x16a8/0x1c14
[f18d9ea8] [c0099aa4] sys_finit_module+0x8c/0x94
[f18d9f38] [c0012174] ret_from_syscall+0x0/0x34
--- interrupt: c01 at 0xfdb4318
    LR = 0xfeee9c0
Instruction dump:
XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX
XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX <3d20c08b> 3d40c086 9421ffe0 8129106c
---[ end trace 85a98cc836109871 ]---

Please try the patch at https://patchwork.ozlabs.org/project/linuxppc-dev/patch/07884ed033c31e074747b7eb8eaa329d15db07ec.1596641219.git.christophe.leroy@csgroup.eu/

And if you are using KAsan, also take https://patchwork.ozlabs.org/project/linuxppc-dev/patch/6eddca2d5611fd57312a88eae31278c87a8fc99d.1596641224.git.christophe.leroy@csgroup.eu/

Allthough I have some doubt that it will fix it, because the faulting instruction address is at 0xf294b000 which is within the vmalloc area. In the likely case the patch doesn't fix the issue, can you provide your .config and a dump of /sys/kernel/debug/powerpc/segment_registers (You have to have CONFIG_PPC_PTDUMP enabled for that) and also the below part from boot log.

[    0.000000] Memory: 509556K/524288K available (7088K kernel code, 592K rwdata, 1304K rodata, 356K init, 803K bss, 14732K reserved, 0K cma-reserved)
[    0.000000] Kernel virtual memory layout:
[    0.000000]   * 0xff7ff000..0xfffff000  : fixmap
[    0.000000]   * 0xff7fd000..0xff7ff000  : early ioremap
[    0.000000]   * 0xe1000000..0xff7fd000  : vmalloc & ioremap

Thanks
Christophe

#6 lore raw

Re: [PATCH v2 3/6] powerpc/32s: Only leave NX unset on segments used for modules

Quoted 47 lines · Christophe Leroy

Le 21/08/2020 à 00:00, Andreas Schwab a écrit :

Quoted 30 lines · Christophe Leroy
Quoted 4 lines

Instead of leaving NX unset on all segments above the start of vmalloc space, only leave NX unset on segments used for modules.

I'm getting this crash:

kernel tried to execute exec-protected page (f294b000) - exploit attempt (uid: 0)

BUG: Unable to handle kernel instruction fetch
Faulting instruction address: 0xf294b000
Oops: Kernel access of bad area, sig: 11 [#1]
BE PAGE_SIZE=4K MMU=Hash PowerMac
Modules linked in: pata_macio(+)
CPU: 0 PID: 87 Comm: udevd Not tainted 5.8.0-rc2-test #49
NIP:  f294b000 LR: 0005c60 CTR: f294b000
REGS: f18d9cc0 TRAP: 0400  Not tainted  (5.8.0-rc2-test)
MSR:  10009032 <E,ME,IR,DR,RI>  CR: 84222422  XER: 20000000

GPR00: c0005c14 f18d9d78 ef30ca20 00000000 ef0000e0 c00993d0 ef6da038 0000005e
GPR08: c09050b8 c08b0000 00000000 f18d9d78 44222422 10072070 00000000 0fefaca4
GPR16: 1006a00c f294d50b 00000120 00000124 c0096ea8 0000000e ef2776c0 ef2776e4
GPR24: f18fd6e8 00000001 c086fe64 c086fe04 00000000 c08b0000 f294b000 ffffffff NIP [f294b000] pata_macio_init+0x0/0xc0 [pata_macio]
LR [c0005c60] do_one_initcall+0x6c/0x160

Call Trace:
[f18d9d78] [c0005c14] do_one_initcall+0x20/0x160 (unreliable)
[f18d9dd8] [c009a22c] do_init_module+0x60/0x1c0
[f18d9df8] [c00993d8] load_module+0x16a8/0x1c14
[f18d9ea8] [c0099aa4] sys_finit_module+0x8c/0x94
[f18d9f38] [c0012174] ret_from_syscall+0x0/0x34
Quoted 7 lines

--- interrupt: c01 at 0xfdb4318
    LR = 0xfeee9c0
Instruction dump:
XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX <3d20c08b> 3d40c086 9421ffe0 8129106c

---[ end trace 85a98cc836109871 ]---

Please try the patch at https://patchwork.ozlabs.org/project/linuxppc-dev/patch/07884ed033c31e074747b7eb8eaa329d15db07ec.1596641219.git.christophe.leroy@csgroup.eu/

And if you are using KAsan, also take https://patchwork.ozlabs.org/project/linuxppc-dev/patch/6eddca2d5611fd57312a88eae31278c87a8fc99d.1596641224.git.christophe.leroy@csgroup.eu/

Quoted 8 lines

Allthough I have some doubt that it will fix it, because the faulting instruction address is at 0xf294b000 which is within the vmalloc area. In the likely case the patch doesn't fix the issue, can you provide your .config and a dump of /sys/kernel/debug/powerpc/segment_registers (You have to have CONFIG_PPC_PTDUMP enabled for that) and also the below part from boot log.

[    0.000000] Memory: 509556K/524288K available (7088K kernel code, 592K rwdata, 1304K rodata, 356K init, 803K bss, 14732K reserved, 0K cma-reserved) [    0.000000] Kernel virtual memory layout:
[    0.000000]   * 0xff7ff000..0xfffff000  : fixmap
[    0.000000]   * 0xff7fd000..0xff7ff000  : early ioremap
[    0.000000]   * 0xe1000000..0xff7fd000  : vmalloc & ioremap

I found the issue, when VMALLOC_END is above 0xf0000000, ALIGN(VMALLOC_END, SZ_256M) is 0 so the test is always false.

The below change should fix it.

arch/powerpc/mm/book3s32/mmu.c +2 -2
index 82ae9e06a773..d426eaf76bb0 100644
@@ -194,12 +194,12 @@ static bool is_module_segment(unsigned long addr)
 #ifdef MODULES_VADDR
 	if (addr < ALIGN_DOWN(MODULES_VADDR, SZ_256M))
 		return false;
-	if (addr >= ALIGN(MODULES_END, SZ_256M))
+	if (addr > ALIGN(MODULES_END, SZ_256M) - 1)
 		return false;
 #else
 	if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
 		return false;
-	if (addr >= ALIGN(VMALLOC_END, SZ_256M))
+	if (addr > ALIGN(VMALLOC_END, SZ_256M) - 1)
 		return false;
 #endif
 	return true;

Christophe

#7 lore raw

PATCH v2 4/6 powerpc/32: Set user/kernel boundary at TASK_SIZE instead of PAGE_OFFSET

In reply to Christophe Leroy

User space stops at TASK_SIZE. At the moment, kernel space starts at PAGE_OFFSET.

In order to use space between TASK_SIZE and PAGE_OFFSET for modules, make TASK_SIZE the limit between user and kernel space.

Note that fault.c already considers TASK_SIZE as the boundary between user and kernel space.

---
 arch/powerpc/include/asm/page.h | 4 +++-
 arch/powerpc/mm/ptdump/ptdump.c | 8 ++++++--
 2 files changed, 9 insertions(+), 3 deletions(-)
arch/powerpc/include/asm/page.h +3 -1
index a63fe6f3a0ff..254687258f42 100644
@@ -255,8 +255,10 @@ static inline bool pfn_valid(unsigned long pfn)
  */
 #ifdef CONFIG_PPC_BOOK3E_64
 #define is_kernel_addr(x)	((x) >= 0x8000000000000000ul)
-#else
+#elif defined(CONFIG_PPC_BOOK3S_64)
 #define is_kernel_addr(x)	((x) >= PAGE_OFFSET)
+#else
+#define is_kernel_addr(x)	((x) >= TASK_SIZE)
 #endif
 
 #ifndef CONFIG_PPC_BOOK3S_64
arch/powerpc/mm/ptdump/ptdump.c +6 -2
index de6e05ef871c..9d942136c7be 100644
@@ -348,7 +348,11 @@ static void populate_markers(void)
 {
 	int i = 0;
 
+#ifdef CONFIG_PPC64
 	address_markers[i++].start_address = PAGE_OFFSET;
+#else
+	address_markers[i++].start_address = TASK_SIZE;
+#endif
 	address_markers[i++].start_address = VMALLOC_START;
 	address_markers[i++].start_address = VMALLOC_END;
 #ifdef CONFIG_PPC64
@@ -385,7 +389,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 	struct pg_state st = {
 		.seq = m,
 		.marker = address_markers,
-		.start_address = PAGE_OFFSET,
+		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
 	};
 
 #ifdef CONFIG_PPC64
@@ -429,7 +433,7 @@ void ptdump_check_wx(void)
 		.seq = NULL,
 		.marker = address_markers,
 		.check_wx = true,
-		.start_address = PAGE_OFFSET,
+		.start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE,
 	};
 
 #ifdef CONFIG_PPC64
Signature · 1 line
2.25.0
#8 lore raw

PATCH v2 5/6 powerpc/32s: Kernel space starts at TASK_SIZE

In reply to Christophe Leroy

Kernel space starts at TASK_SIZE. Select kernel page table when address is over TASK_SIZE.

---
 arch/powerpc/kernel/head_32.S       | 12 ++++++------
 arch/powerpc/mm/book3s32/hash_low.S |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)
arch/powerpc/kernel/head_32.S +6 -6
index 705c042309d8..bbef6ce8322b 100644
@@ -474,7 +474,7 @@ InstructionTLBMiss:
 	/* Get PTE (linux-style) and check access */
 	mfspr	r3,SPRN_IMISS
 #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
-	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
+	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 #endif
 	mfspr	r2, SPRN_SPRG_PGDIR
@@ -484,7 +484,7 @@ InstructionTLBMiss:
 	li	r1,_PAGE_PRESENT | _PAGE_EXEC
 #endif
 #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
-	bge-	112f
+	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 #endif
@@ -541,7 +541,7 @@ DataLoadTLBMiss:
  */
 	/* Get PTE (linux-style) and check access */
 	mfspr	r3,SPRN_DMISS
-	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
+	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
 #ifdef CONFIG_SWAP
@@ -549,7 +549,7 @@ DataLoadTLBMiss:
 #else
 	li	r1, _PAGE_PRESENT
 #endif
-	bge-	112f
+	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
@@ -621,7 +621,7 @@ DataStoreTLBMiss:
  */
 	/* Get PTE (linux-style) and check access */
 	mfspr	r3,SPRN_DMISS
-	lis	r1,PAGE_OFFSET@h		/* check if kernel address */
+	lis	r1, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r1,r3
 	mfspr	r2, SPRN_SPRG_PGDIR
 #ifdef CONFIG_SWAP
@@ -629,7 +629,7 @@ DataStoreTLBMiss:
 #else
 	li	r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
 #endif
-	bge-	112f
+	bgt-	112f
 	lis	r2, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
 112:	rlwimi	r2,r3,12,20,29		/* insert top 10 bits of address */
arch/powerpc/mm/book3s32/hash_low.S +1 -1
index 923ad8f374eb..1690d369688b 100644
@@ -62,7 +62,7 @@ _GLOBAL(hash_page)
 	isync
 #endif
 	/* Get PTE (linux-style) and check access */
-	lis	r0,KERNELBASE@h		/* check if kernel address */
+	lis	r0, TASK_SIZE@h		/* check if kernel address */
 	cmplw	0,r4,r0
 	ori	r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
 	mfspr	r5, SPRN_SPRG_PGDIR	/* phys page-table root */
Signature · 1 line
2.25.0
#9 lore raw

PATCH v2 6/6 powerpc/32s: Use dedicated segment for modules with STRICT_KERNEL_RWX

In reply to Christophe Leroy

When STRICT_KERNEL_RWX is set, we want to set NX bit on vmalloc segments. But modules require exec.

Use a dedicated segment for modules. There is not much space above kernel, and we don't waste vmalloc space to do alignment. Therefore, we take the segment before PAGE_OFFSET for modules.

---
 arch/powerpc/Kconfig                         |  1 +
 arch/powerpc/include/asm/book3s/32/pgtable.h | 15 +++++----------
 arch/powerpc/mm/ptdump/ptdump.c              |  8 ++++++++
 3 files changed, 14 insertions(+), 10 deletions(-)
arch/powerpc/Kconfig +1 -0
index 51abc59c3334..963b3bc7d969 100644
@@ -1194,6 +1194,7 @@ config TASK_SIZE_BOOL
 config TASK_SIZE
 	hex "Size of user task space" if TASK_SIZE_BOOL
 	default "0x80000000" if PPC_8xx
+	default "0xb0000000" if PPC_BOOK3S_32 && STRICT_KERNEL_RWX
 	default "0xc0000000"
 endmenu
 
arch/powerpc/include/asm/book3s/32/pgtable.h +5 -10
index 224912432821..36443cda8dcf 100644
@@ -184,17 +184,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
  */
 #define VMALLOC_OFFSET (0x1000000) /* 16M */
 
-/*
- * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules
- * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear
- * memory shall not share segments.
- */
-#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES)
-#define VMALLOC_START ((ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \
-		       ~(VMALLOC_OFFSET - 1))
-#else
 #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
-#endif
 
 #ifdef CONFIG_KASAN_VMALLOC
 #define VMALLOC_END	ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
@@ -202,6 +192,11 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
 #define VMALLOC_END	ioremap_bot
 #endif
 
+#ifdef CONFIG_STRICT_KERNEL_RWX
+#define MODULES_END	ALIGN_DOWN(PAGE_OFFSET, SZ_256M)
+#define MODULES_VADDR	(MODULES_END - SZ_256M)
+#endif
+
 #ifndef __ASSEMBLY__
 #include <linux/sched.h>
 #include <linux/threads.h>
arch/powerpc/mm/ptdump/ptdump.c +8 -0
index 9d942136c7be..b2ed1ca4f254 100644
@@ -74,6 +74,10 @@ struct addr_marker {
 
 static struct addr_marker address_markers[] = {
 	{ 0,	"Start of kernel VM" },
+#ifdef MODULES_VADDR
+	{ 0,	"modules start" },
+	{ 0,	"modules end" },
+#endif
 	{ 0,	"vmalloc() Area" },
 	{ 0,	"vmalloc() End" },
 #ifdef CONFIG_PPC64
@@ -352,6 +356,10 @@ static void populate_markers(void)
 	address_markers[i++].start_address = PAGE_OFFSET;
 #else
 	address_markers[i++].start_address = TASK_SIZE;
+#endif
+#ifdef MODULES_VADDR
+	address_markers[i++].start_address = MODULES_VADDR;
+	address_markers[i++].start_address = MODULES_END;
 #endif
 	address_markers[i++].start_address = VMALLOC_START;
 	address_markers[i++].start_address = VMALLOC_END;
Signature · 1 line
2.25.0
#10 lore raw
In reply to Christophe Leroy
Quoted 6 lines · Christophe Leroy

On book3s32 (hash), exec protection is set per 256Mb segments with NX bit. Instead of clearing NX bit on vmalloc space when CONFIG_MODULES is selected, allocate modules in a dedicated segment (0xb0000000-0xbfffffff by default). This allows to keep exec protection on vmalloc space while allowing exec on modules.

Quoted 6 lines

v2:
- Removed the two patches that fix ptdump. Will submitted independently
- Only changing the user/kernel boundary for PPC32 now.
- Reordered the patches inside the series.

[...]

Applied to powerpc/next.

[1/6] powerpc/lib: Prepare code-patching for modules allocated outside vmalloc space

      https://git.kernel.org/powerpc/c/ccc8fcf72a6953fbfd6998999d622295f522b952
[2/6] powerpc: Use MODULES_VADDR if defined
      https://git.kernel.org/powerpc/c/7fbc22ce29931630da200cfc90fe5a454f54a794
[3/6] powerpc/32s: Only leave NX unset on segments used for modules
      https://git.kernel.org/powerpc/c/c496433197154144c310a17939736bc5c155914d
[4/6] powerpc/32: Set user/kernel boundary at TASK_SIZE instead of PAGE_OFFSET
      https://git.kernel.org/powerpc/c/b6be1bb7f7216b9e9f33f57abe6e3290c0e66bd4
[5/6] powerpc/32s: Kernel space starts at TASK_SIZE
      https://git.kernel.org/powerpc/c/f1a1f7a15eb0e13b84791ff2738b84e414501718
[6/6] powerpc/32s: Use dedicated segment for modules with STRICT_KERNEL_RWX
      https://git.kernel.org/powerpc/c/6ca055322da8fe25ff9ac50db6f3b7b59b6f961c

cheers