linux/arch/powerpc/mm/pageattr.c

128 lines
3.2 KiB
C
Raw Normal View History

2021-06-09 09:34:23 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* MMU-generic set_memory implementation for powerpc
*
* Copyright 2019-2021, IBM Corporation.
*/
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/set_memory.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <mm/mmu_decl.h>
2021-06-09 09:34:23 +08:00
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr,
unsigned long old, unsigned long new)
{
return pte_update(&init_mm, addr, ptep, old & ~new, new & ~old, 0);
}
2021-06-09 09:34:23 +08:00
/*
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
* Updates the attributes of a page atomically.
2021-06-09 09:34:23 +08:00
*
powerpc/mm: Fix set_memory_*() against concurrent accesses Laurent reported that STRICT_MODULE_RWX was causing intermittent crashes on one of his systems: kernel tried to execute exec-protected page (c008000004073278) - exploit attempt? (uid: 0) BUG: Unable to handle kernel instruction fetch Faulting instruction address: 0xc008000004073278 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: drm virtio_console fuse drm_panel_orientation_quirks ... CPU: 3 PID: 44 Comm: kworker/3:1 Not tainted 5.14.0-rc4+ #12 Workqueue: events control_work_handler [virtio_console] NIP: c008000004073278 LR: c008000004073278 CTR: c0000000001e9de0 REGS: c00000002e4ef7e0 TRAP: 0400 Not tainted (5.14.0-rc4+) MSR: 800000004280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 24002822 XER: 200400cf ... NIP fill_queue+0xf0/0x210 [virtio_console] LR fill_queue+0xf0/0x210 [virtio_console] Call Trace: fill_queue+0xb4/0x210 [virtio_console] (unreliable) add_port+0x1a8/0x470 [virtio_console] control_work_handler+0xbc/0x1e8 [virtio_console] process_one_work+0x290/0x590 worker_thread+0x88/0x620 kthread+0x194/0x1a0 ret_from_kernel_thread+0x5c/0x64 Jordan, Fabiano & Murilo were able to reproduce and identify that the problem is caused by the call to module_enable_ro() in do_init_module(), which happens after the module's init function has already been called. Our current implementation of change_page_attr() is not safe against concurrent accesses, because it invalidates the PTE before flushing the TLB and then installing the new PTE. That leaves a window in time where there is no valid PTE for the page, if another CPU tries to access the page at that time we see something like the fault above. We can't simply switch to set_pte_at()/flush TLB, because our hash MMU code doesn't handle a set_pte_at() of a valid PTE. See [1]. But we do have pte_update(), which replaces the old PTE with the new, meaning there's no window where the PTE is invalid. And the hash MMU version hash__pte_update() deals with synchronising the hash page table correctly. [1]: https://lore.kernel.org/linuxppc-dev/87y318wp9r.fsf@linux.ibm.com/ Fixes: 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") Reported-by: Laurent Vivier <lvivier@redhat.com> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Murilo Opsfelder Araújo <muriloo@linux.ibm.com> Tested-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20210818120518.3603172-1-mpe@ellerman.id.au
2021-08-15 12:10:24 +08:00
* This sequence is safe against concurrent updates, and also allows updating the
* attributes of a page currently being executed or accessed.
2021-06-09 09:34:23 +08:00
*/
static int change_page_attr(pte_t *ptep, unsigned long addr, void *data)
{
long action = (long)data;
addr &= PAGE_MASK;
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
/* modify the PTE bits as desired */
2021-06-09 09:34:23 +08:00
switch (action) {
case SET_MEMORY_RO:
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
/* Don't clear DIRTY bit */
pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO);
2021-06-09 09:34:23 +08:00
break;
case SET_MEMORY_ROX:
/* Don't clear DIRTY bit */
pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_ROX);
break;
2021-06-09 09:34:23 +08:00
case SET_MEMORY_RW:
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW);
2021-06-09 09:34:23 +08:00
break;
case SET_MEMORY_NX:
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
pte_update_delta(ptep, addr, _PAGE_KERNEL_ROX, _PAGE_KERNEL_RO);
2021-06-09 09:34:23 +08:00
break;
case SET_MEMORY_X:
powerpc/set_memory: Avoid spinlock recursion in change_page_attr() Commit 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") included a spin_lock() to change_page_attr() in order to safely perform the three step operations. But then commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") modify it to use pte_update() and do the operation safely against concurrent access. In the meantime, Maxime reported some spinlock recursion. [ 15.351649] BUG: spinlock recursion on CPU#0, kworker/0:2/217 [ 15.357540] lock: init_mm+0x3c/0x420, .magic: dead4ead, .owner: kworker/0:2/217, .owner_cpu: 0 [ 15.366563] CPU: 0 PID: 217 Comm: kworker/0:2 Not tainted 5.15.0+ #523 [ 15.373350] Workqueue: events do_free_init [ 15.377615] Call Trace: [ 15.380232] [e4105ac0] [800946a4] do_raw_spin_lock+0xf8/0x120 (unreliable) [ 15.387340] [e4105ae0] [8001f4ec] change_page_attr+0x40/0x1d4 [ 15.393413] [e4105b10] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.400009] [e4105b60] [80169620] free_pcp_prepare+0x1e4/0x4a0 [ 15.406045] [e4105ba0] [8016c5a0] free_unref_page+0x40/0x2b8 [ 15.411979] [e4105be0] [8018724c] kasan_depopulate_vmalloc_pte+0x6c/0x94 [ 15.418989] [e4105c00] [801424e0] __apply_to_page_range+0x164/0x310 [ 15.425451] [e4105c50] [80187834] kasan_release_vmalloc+0xbc/0x134 [ 15.431898] [e4105c70] [8015f7a8] __purge_vmap_area_lazy+0x4e4/0xdd8 [ 15.438560] [e4105d30] [80160d10] _vm_unmap_aliases.part.0+0x17c/0x24c [ 15.445283] [e4105d60] [801642d0] __vunmap+0x2f0/0x5c8 [ 15.450684] [e4105db0] [800e32d0] do_free_init+0x68/0x94 [ 15.456181] [e4105dd0] [8005d094] process_one_work+0x4bc/0x7b8 [ 15.462283] [e4105e90] [8005d614] worker_thread+0x284/0x6e8 [ 15.468227] [e4105f00] [8006aaec] kthread+0x1f0/0x210 [ 15.473489] [e4105f40] [80017148] ret_from_kernel_thread+0x14/0x1c Remove the read / modify / write sequence to make the operation atomic and remove the spin_lock() in change_page_attr(). To do the operation atomically, we can't use pte modification helpers anymore. Because all platforms have different combination of bits, it is not easy to use those bits directly. But all have the _PAGE_KERNEL_{RO/ROX/RW/RWX} set of flags. All we need it to compare two sets to know which bits are set or cleared. For instance, by comparing _PAGE_KERNEL_ROX and _PAGE_KERNEL_RO you know which bit gets cleared and which bit get set when changing exec permission. Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/all/20211212112152.GA27070@sakura/ Link: https://lore.kernel.org/r/43c3c76a1175ae6dc1a3d3b5c3f7ecb48f683eea.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:33 +08:00
pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_ROX);
2021-06-09 09:34:23 +08:00
break;
powerpc: Add set_memory_{p/np}() and remove set_memory_attr() set_memory_attr() was implemented by commit 4d1755b6a762 ("powerpc/mm: implement set_memory_attr()") because the set_memory_xx() couldn't be used at that time to modify memory "on the fly" as explained it the commit. But set_memory_attr() uses set_pte_at() which leads to warnings when CONFIG_DEBUG_VM is selected, because set_pte_at() is unexpected for updating existing page table entries. The check could be bypassed by using __set_pte_at() instead, as it was the case before commit c988cfd38e48 ("powerpc/32: use set_memory_attr()") but since commit 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") it is now possible to use set_memory_xx() functions to update page table entries "on the fly" because the update is now atomic. For DEBUG_PAGEALLOC we need to clear and set back _PAGE_PRESENT. Add set_memory_np() and set_memory_p() for that. Replace all uses of set_memory_attr() by the relevant set_memory_xx() and remove set_memory_attr(). Fixes: c988cfd38e48 ("powerpc/32: use set_memory_attr()") Cc: stable@vger.kernel.org Reported-by: Maxime Bizon <mbizon@freebox.fr> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Tested-by: Maxime Bizon <mbizon@freebox.fr> Reviewed-by: Russell Currey <ruscur@russell.cc> Depends-on: 9f7853d7609d ("powerpc/mm: Fix set_memory_*() against concurrent accesses") Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/cda2b44b55c96f9ac69fa92e68c01084ec9495c5.1640344012.git.christophe.leroy@csgroup.eu
2021-12-24 19:07:40 +08:00
case SET_MEMORY_NP:
pte_update(&init_mm, addr, ptep, _PAGE_PRESENT, 0, 0);
break;
case SET_MEMORY_P:
pte_update(&init_mm, addr, ptep, 0, _PAGE_PRESENT, 0);
break;
2021-06-09 09:34:23 +08:00
default:
WARN_ON_ONCE(1);
break;
}
/* See ptesync comment in radix__set_pte_at() */
if (radix_enabled())
asm volatile("ptesync": : :"memory");
powerpc/mm: Fix set_memory_*() against concurrent accesses Laurent reported that STRICT_MODULE_RWX was causing intermittent crashes on one of his systems: kernel tried to execute exec-protected page (c008000004073278) - exploit attempt? (uid: 0) BUG: Unable to handle kernel instruction fetch Faulting instruction address: 0xc008000004073278 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: drm virtio_console fuse drm_panel_orientation_quirks ... CPU: 3 PID: 44 Comm: kworker/3:1 Not tainted 5.14.0-rc4+ #12 Workqueue: events control_work_handler [virtio_console] NIP: c008000004073278 LR: c008000004073278 CTR: c0000000001e9de0 REGS: c00000002e4ef7e0 TRAP: 0400 Not tainted (5.14.0-rc4+) MSR: 800000004280b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE> CR: 24002822 XER: 200400cf ... NIP fill_queue+0xf0/0x210 [virtio_console] LR fill_queue+0xf0/0x210 [virtio_console] Call Trace: fill_queue+0xb4/0x210 [virtio_console] (unreliable) add_port+0x1a8/0x470 [virtio_console] control_work_handler+0xbc/0x1e8 [virtio_console] process_one_work+0x290/0x590 worker_thread+0x88/0x620 kthread+0x194/0x1a0 ret_from_kernel_thread+0x5c/0x64 Jordan, Fabiano & Murilo were able to reproduce and identify that the problem is caused by the call to module_enable_ro() in do_init_module(), which happens after the module's init function has already been called. Our current implementation of change_page_attr() is not safe against concurrent accesses, because it invalidates the PTE before flushing the TLB and then installing the new PTE. That leaves a window in time where there is no valid PTE for the page, if another CPU tries to access the page at that time we see something like the fault above. We can't simply switch to set_pte_at()/flush TLB, because our hash MMU code doesn't handle a set_pte_at() of a valid PTE. See [1]. But we do have pte_update(), which replaces the old PTE with the new, meaning there's no window where the PTE is invalid. And the hash MMU version hash__pte_update() deals with synchronising the hash page table correctly. [1]: https://lore.kernel.org/linuxppc-dev/87y318wp9r.fsf@linux.ibm.com/ Fixes: 1f9ad21c3b38 ("powerpc/mm: Implement set_memory() routines") Reported-by: Laurent Vivier <lvivier@redhat.com> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Murilo Opsfelder Araújo <muriloo@linux.ibm.com> Tested-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20210818120518.3603172-1-mpe@ellerman.id.au
2021-08-15 12:10:24 +08:00
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
2021-06-09 09:34:23 +08:00
return 0;
}
int change_memory_attr(unsigned long addr, int numpages, long action)
{
unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
unsigned long size = numpages * PAGE_SIZE;
if (!numpages)
return 0;
if (WARN_ON_ONCE(is_vmalloc_or_module_addr((void *)addr) &&
is_vm_area_hugepages((void *)addr)))
return -EINVAL;
#ifdef CONFIG_PPC_BOOK3S_64
/*
* On hash, the linear mapping is not in the Linux page table so
* apply_to_existing_page_range() will have no effect. If in the future
* the set_memory_* functions are used on the linear map this will need
* to be updated.
*/
if (!radix_enabled()) {
int region = get_region_id(addr);
if (WARN_ON_ONCE(region != VMALLOC_REGION_ID && region != IO_REGION_ID))
return -EINVAL;
}
#endif
return apply_to_existing_page_range(&init_mm, start, size,
change_page_attr, (void *)action);
}
#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
#ifdef CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
int err;
unsigned long addr = (unsigned long)page_address(page);
if (PageHighMem(page))
return;
if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled())
err = hash__kernel_map_pages(page, numpages, enable);
else if (enable)
err = set_memory_p(addr, numpages);
else
err = set_memory_np(addr, numpages);
if (err)
panic("%s: changing memory protections failed\n", __func__);
}
#endif
#endif