Revision 595cb5e0b832a3e100cbbdefef797b0c27bf725a authored by Kim Phillips on 21 October 2021, 15:30:06 UTC, committed by Dave Airlie on 21 October 2021, 19:52:12 UTC
This reverts commit aae74ff9caa8de9a45ae2e46068c417817392a26, since it prevents my AMD Milan system from booting, with: [ 27.189558] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 27.197506] #PF: supervisor write access in kernel mode [ 27.203333] #PF: error_code(0x0002) - not-present page [ 27.209064] PGD 0 P4D 0 [ 27.211885] Oops: 0002 [#1] PREEMPT SMP NOPTI [ 27.216744] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.15.0-rc6+ #15 [ 27.223928] Hardware name: AMD Corporation ETHANOL_X/ETHANOL_X, BIOS RXM1006B 08/20/2021 [ 27.232955] RIP: 0010:run_timer_softirq+0x38b/0x4a0 [ 27.238397] Code: 4c 89 f7 e8 37 27 ac 00 49 c7 46 08 00 00 00 00 49 8b 04 24 48 85 c0 74 71 4d 8b 3c 24 4d 89 7e 08 66 90 49 8b 07 49 8b 57 08 <48> 89 02 48 85 c0 74 04 48 89 50 08 49 8b 77 18 41 f6 47 22 20 4c [ 27.259350] RSP: 0018:ffffc42d00003ee8 EFLAGS: 00010086 [ 27.265176] RAX: dead000000000122 RBX: 0000000000000000 RCX: 0000000000000101 [ 27.273134] RDX: 0000000000000000 RSI: 0000000000000087 RDI: 0000000000000001 [ 27.281084] RBP: ffffc42d00003f70 R08: 0000000000000000 R09: 00000000000003eb [ 27.289043] R10: ffffa0860cb300d0 R11: ffffa0c44de290b0 R12: ffffc42d00003ef8 [ 27.297002] R13: 00000000fffef200 R14: ffffa0c44de18dc0 R15: ffffa0867a882350 [ 27.304961] FS: 0000000000000000(0000) GS:ffffa0c44de00000(0000) knlGS:0000000000000000 [ 27.313988] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 27.320396] CR2: 0000000000000000 CR3: 000000014569c001 CR4: 0000000000770ef0 [ 27.328346] PKRU: 55555554 [ 27.331359] Call Trace: [ 27.334073] <IRQ> [ 27.336314] ? __queue_work+0x420/0x420 [ 27.340589] ? lapic_next_event+0x21/0x30 [ 27.345060] ? clockevents_program_event+0x8f/0xe0 [ 27.350402] __do_softirq+0xfb/0x2db [ 27.354388] irq_exit_rcu+0x98/0xd0 [ 27.358275] sysvec_apic_timer_interrupt+0xac/0xd0 [ 27.363620] </IRQ> [ 27.365955] asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 27.371685] RIP: 0010:cpuidle_enter_state+0xcc/0x390 [ 27.377292] Code: 3d 01 79 0a 50 e8 44 ed 77 ff 49 89 c6 0f 1f 44 00 00 31 ff e8 f5 f8 77 ff 80 7d d7 00 0f 85 e6 01 00 00 fb 66 0f 1f 44 00 00 <45> 85 ff 0f 88 17 01 00 00 49 63 c7 4c 2b 75 c8 48 8d 14 40 48 8d [ 27.398243] RSP: 0018:ffffffffb0e03dc8 EFLAGS: 00000246 [ 27.404069] RAX: ffffa0c44de00000 RBX: 0000000000000001 RCX: 000000000000001f [ 27.412028] RDX: 0000000000000000 RSI: ffffffffb0bafc1f RDI: ffffffffb0bbdb81 [ 27.419986] RBP: ffffffffb0e03e00 R08: 00000006549f8f3f R09: ffffffffb1065200 [ 27.427935] R10: ffffa0c44de27ae4 R11: ffffa0c44de27ac4 R12: ffffa0c5634cb000 [ 27.435894] R13: ffffffffb1065200 R14: 00000006549f8f3f R15: 0000000000000001 [ 27.443854] ? cpuidle_enter_state+0xbb/0x390 [ 27.448712] cpuidle_enter+0x2e/0x40 [ 27.452695] call_cpuidle+0x23/0x40 [ 27.456584] do_idle+0x1f0/0x270 [ 27.460181] cpu_startup_entry+0x20/0x30 [ 27.464553] rest_init+0xd4/0xe0 [ 27.468149] arch_call_rest_init+0xe/0x1b [ 27.472619] start_kernel+0x6bc/0x6e2 [ 27.476764] x86_64_start_reservations+0x24/0x26 [ 27.481912] x86_64_start_kernel+0x75/0x79 [ 27.486477] secondary_startup_64_no_verify+0xb0/0xbb [ 27.492111] Modules linked in: kvm_amd(+) kvm ipmi_si(+) ipmi_devintf rapl wmi_bmof ipmi_msghandler input_leds ccp k10temp mac_hid sch_fq_codel msr ip_tables x_tables autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear ast i2c_algo_bit drm_vram_helper drm_ttm_helper ttm drm_kms_helper crct10dif_pclmul crc32_pclmul ghash_clmulni_intel syscopyarea aesni_intel sysfillrect crypto_simd sysimgblt fb_sys_fops cryptd hid_generic cec nvme ahci usbhid drm e1000e nvme_core hid libahci i2c_piix4 wmi [ 27.551789] CR2: 0000000000000000 [ 27.555482] ---[ end trace 897987dfe93dccc6 ]--- [ 27.560630] RIP: 0010:run_timer_softirq+0x38b/0x4a0 [ 27.566069] Code: 4c 89 f7 e8 37 27 ac 00 49 c7 46 08 00 00 00 00 49 8b 04 24 48 85 c0 74 71 4d 8b 3c 24 4d 89 7e 08 66 90 49 8b 07 49 8b 57 08 <48> 89 02 48 85 c0 74 04 48 89 50 08 49 8b 77 18 41 f6 47 22 20 4c [ 27.587021] RSP: 0018:ffffc42d00003ee8 EFLAGS: 00010086 [ 27.592848] RAX: dead000000000122 RBX: 0000000000000000 RCX: 0000000000000101 [ 27.600808] RDX: 0000000000000000 RSI: 0000000000000087 RDI: 0000000000000001 [ 27.608765] RBP: ffffc42d00003f70 R08: 0000000000000000 R09: 00000000000003eb [ 27.616716] R10: ffffa0860cb300d0 R11: ffffa0c44de290b0 R12: ffffc42d00003ef8 [ 27.624673] R13: 00000000fffef200 R14: ffffa0c44de18dc0 R15: ffffa0867a882350 [ 27.632624] FS: 0000000000000000(0000) GS:ffffa0c44de00000(0000) knlGS:0000000000000000 [ 27.641650] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 27.648159] CR2: 0000000000000000 CR3: 000000014569c001 CR4: 0000000000770ef0 [ 27.656119] PKRU: 55555554 [ 27.659133] Kernel panic - not syncing: Fatal exception in interrupt [ 29.030411] Shutting down cpus with NMI [ 29.034699] Kernel Offset: 0x2e600000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 29.046790] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Since unreliable, found by bisecting for KASAN's use-after-free in enqueue_timer+0x4f/0x1e0, where the timer callback is called. Reported-by: Kim Phillips <kim.phillips@amd.com> Signed-off-by: Kim Phillips <kim.phillips@amd.com> Fixes: aae74ff9caa8 ("drm/ast: Add detect function support") Link: https://lore.kernel.org/lkml/0f7871be-9ca6-5ae4-3a40-5db9a8fb2365@amd.com/ Cc: Ainux <ainux.wang@gmail.com> Cc: Thomas Zimmermann <tzimmermann@suse.de> Cc: David Airlie <airlied@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: sterlingteng@gmail.com Cc: chenhuacai@kernel.org Cc: Chuck Lever III <chuck.lever@oracle.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Borislav Petkov <bp@suse.de> Cc: Jon Grimm <jon.grimm@amd.com> Cc: dri-devel <dri-devel@lists.freedesktop.org> Cc: linux-kernel <linux-kernel@vger.kernel.org> Signed-off-by: Dave Airlie <airlied@redhat.com> Link: https://patchwork.freedesktop.org/patch/msgid/20211021153006.92983-1-kim.phillips@amd.com
1 parent 7e1c544
mincore.c
// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/mincore.c
*
* Copyright (C) 1994-2006 Linus Torvalds
*/
/*
* The mincore() system call.
*/
#include <linux/pagemap.h>
#include <linux/gfp.h>
#include <linux/pagewalk.h>
#include <linux/mman.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/shmem_fs.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <linux/uaccess.h>
static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
unsigned char present;
unsigned char *vec = walk->private;
/*
* Hugepages under user process are always in RAM and never
* swapped out, but theoretically it needs to be checked.
*/
present = pte && !huge_pte_none(huge_ptep_get(pte));
for (; addr != end; vec++, addr += PAGE_SIZE)
*vec = present;
walk->private = vec;
#else
BUG();
#endif
return 0;
}
/*
* Later we can get more picky about what "in core" means precisely.
* For now, simply check to see if the page is in the page cache,
* and is up to date; i.e. that no page-in operation would be required
* at this time if an application were to map and access this page.
*/
static unsigned char mincore_page(struct address_space *mapping, pgoff_t index)
{
unsigned char present = 0;
struct page *page;
/*
* When tmpfs swaps out a page from a file, any process mapping that
* file will not get a swp_entry_t in its pte, but rather it is like
* any other file mapping (ie. marked !present and faulted in with
* tmpfs's .fault). So swapped out tmpfs mappings are tested here.
*/
page = find_get_incore_page(mapping, index);
if (page) {
present = PageUptodate(page);
put_page(page);
}
return present;
}
static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
struct vm_area_struct *vma, unsigned char *vec)
{
unsigned long nr = (end - addr) >> PAGE_SHIFT;
int i;
if (vma->vm_file) {
pgoff_t pgoff;
pgoff = linear_page_index(vma, addr);
for (i = 0; i < nr; i++, pgoff++)
vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
} else {
for (i = 0; i < nr; i++)
vec[i] = 0;
}
return nr;
}
static int mincore_unmapped_range(unsigned long addr, unsigned long end,
__always_unused int depth,
struct mm_walk *walk)
{
walk->private += __mincore_unmapped_range(addr, end,
walk->vma, walk->private);
return 0;
}
static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
spinlock_t *ptl;
struct vm_area_struct *vma = walk->vma;
pte_t *ptep;
unsigned char *vec = walk->private;
int nr = (end - addr) >> PAGE_SHIFT;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
memset(vec, 1, nr);
spin_unlock(ptl);
goto out;
}
if (pmd_trans_unstable(pmd)) {
__mincore_unmapped_range(addr, end, vma, vec);
goto out;
}
ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
for (; addr != end; ptep++, addr += PAGE_SIZE) {
pte_t pte = *ptep;
if (pte_none(pte))
__mincore_unmapped_range(addr, addr + PAGE_SIZE,
vma, vec);
else if (pte_present(pte))
*vec = 1;
else { /* pte is a swap entry */
swp_entry_t entry = pte_to_swp_entry(pte);
if (non_swap_entry(entry)) {
/*
* migration or hwpoison entries are always
* uptodate
*/
*vec = 1;
} else {
#ifdef CONFIG_SWAP
*vec = mincore_page(swap_address_space(entry),
swp_offset(entry));
#else
WARN_ON(1);
*vec = 1;
#endif
}
}
vec++;
}
pte_unmap_unlock(ptep - 1, ptl);
out:
walk->private += nr;
cond_resched();
return 0;
}
static inline bool can_do_mincore(struct vm_area_struct *vma)
{
if (vma_is_anonymous(vma))
return true;
if (!vma->vm_file)
return false;
/*
* Reveal pagecache information only for non-anonymous mappings that
* correspond to the files the calling process could (if tried) open
* for writing; otherwise we'd be including shared non-exclusive
* mappings, which opens a side channel.
*/
return inode_owner_or_capable(&init_user_ns,
file_inode(vma->vm_file)) ||
file_permission(vma->vm_file, MAY_WRITE) == 0;
}
static const struct mm_walk_ops mincore_walk_ops = {
.pmd_entry = mincore_pte_range,
.pte_hole = mincore_unmapped_range,
.hugetlb_entry = mincore_hugetlb,
};
/*
* Do a chunk of "sys_mincore()". We've already checked
* all the arguments, we hold the mmap semaphore: we should
* just return the amount of info we're asked for.
*/
static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
{
struct vm_area_struct *vma;
unsigned long end;
int err;
vma = find_vma(current->mm, addr);
if (!vma || addr < vma->vm_start)
return -ENOMEM;
end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
if (!can_do_mincore(vma)) {
unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE);
memset(vec, 1, pages);
return pages;
}
err = walk_page_range(vma->vm_mm, addr, end, &mincore_walk_ops, vec);
if (err < 0)
return err;
return (end - addr) >> PAGE_SHIFT;
}
/*
* The mincore(2) system call.
*
* mincore() returns the memory residency status of the pages in the
* current process's address space specified by [addr, addr + len).
* The status is returned in a vector of bytes. The least significant
* bit of each byte is 1 if the referenced page is in memory, otherwise
* it is zero.
*
* Because the status of a page can change after mincore() checks it
* but before it returns to the application, the returned vector may
* contain stale information. Only locked pages are guaranteed to
* remain in memory.
*
* return values:
* zero - success
* -EFAULT - vec points to an illegal address
* -EINVAL - addr is not a multiple of PAGE_SIZE
* -ENOMEM - Addresses in the range [addr, addr + len] are
* invalid for the address space of this process, or
* specify one or more pages which are not currently
* mapped
* -EAGAIN - A kernel resource was temporarily unavailable.
*/
SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
unsigned char __user *, vec)
{
long retval;
unsigned long pages;
unsigned char *tmp;
start = untagged_addr(start);
/* Check the start address: needs to be page-aligned.. */
if (start & ~PAGE_MASK)
return -EINVAL;
/* ..and we need to be passed a valid user-space range */
if (!access_ok((void __user *) start, len))
return -ENOMEM;
/* This also avoids any overflows on PAGE_ALIGN */
pages = len >> PAGE_SHIFT;
pages += (offset_in_page(len)) != 0;
if (!access_ok(vec, pages))
return -EFAULT;
tmp = (void *) __get_free_page(GFP_USER);
if (!tmp)
return -EAGAIN;
retval = 0;
while (pages) {
/*
* Do at most PAGE_SIZE entries per iteration, due to
* the temporary buffer size.
*/
mmap_read_lock(current->mm);
retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
mmap_read_unlock(current->mm);
if (retval <= 0)
break;
if (copy_to_user(vec, tmp, retval)) {
retval = -EFAULT;
break;
}
pages -= retval;
vec += retval;
start += retval << PAGE_SHIFT;
retval = 0;
}
free_page((unsigned long) tmp);
return retval;
}
Computing file changes ...