mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Vitaly Kuznetsov](/assets/img/avatar_default.png)
KASAN detected the following issue: BUG: KASAN: slab-out-of-bounds in hyperv_flush_tlb_multi+0xf88/0x1060 Read of size 4 at addr ffff8880011ccbc0 by task kcompactd0/33 CPU: 1 PID: 33 Comm: kcompactd0 Not tainted 5.14.0-39.el9.x86_64+debug #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.0 12/17/2019 Call Trace: dump_stack_lvl+0x57/0x7d print_address_description.constprop.0+0x1f/0x140 ? hyperv_flush_tlb_multi+0xf88/0x1060 __kasan_report.cold+0x7f/0x11e ? hyperv_flush_tlb_multi+0xf88/0x1060 kasan_report+0x38/0x50 hyperv_flush_tlb_multi+0xf88/0x1060 flush_tlb_mm_range+0x1b1/0x200 ptep_clear_flush+0x10e/0x150 ... Allocated by task 0: kasan_save_stack+0x1b/0x40 __kasan_kmalloc+0x7c/0x90 hv_common_init+0xae/0x115 hyperv_init+0x97/0x501 apic_intr_mode_init+0xb3/0x1e0 x86_late_time_init+0x92/0xa2 start_kernel+0x338/0x3eb secondary_startup_64_no_verify+0xc2/0xcb The buggy address belongs to the object at ffff8880011cc800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 960 bytes inside of 1024-byte region [ffff8880011cc800, ffff8880011ccc00) 'hyperv_flush_tlb_multi+0xf88/0x1060' points to hv_cpu_number_to_vp_number() and '960 bytes' means we're trying to get VP_INDEX for CPU#240. 'nr_cpus' here is exactly 240 so we're trying to access past hv_vp_index's last element. This can (and will) happen when 'cpus' mask is empty and cpumask_last() will return '>=nr_cpus'. Commitad0a6bad44
("x86/hyperv: check cpu mask after interrupt has been disabled") tried to deal with empty cpumask situation but apparently didn't fully fix the issue. 'cpus' cpumask which is passed to hyperv_flush_tlb_multi() is 'mm_cpumask(mm)' (which is '&mm->cpu_bitmap'). This mask changes every time the particular mm is scheduled/unscheduled on some CPU (see switch_mm_irqs_off()), disabling IRQs on the CPU which is performing remote TLB flush has zero influence on whether the particular process can get scheduled/unscheduled on _other_ CPUs so e.g. in the case where the mm was scheduled on one other CPU and got unscheduled during hyperv_flush_tlb_multi()'s execution will lead to cpumask becoming empty. It doesn't seem that there's a good way to protect 'mm_cpumask(mm)' from changing during hyperv_flush_tlb_multi()'s execution. It would be possible to copy it in the very beginning of the function but this is a waste. It seems we can deal with changing cpumask just fine. When 'cpus' cpumask changes during hyperv_flush_tlb_multi()'s execution, there are two possible issues: - 'Under-flushing': we will not flush TLB on a CPU which got added to the mask while hyperv_flush_tlb_multi() was already running. This is not a problem as this is equal to mm getting scheduled on that CPU right after TLB flush. - 'Over-flushing': we may flush TLB on a CPU which is already cleared from the mask. First, extra TLB flush preserves correctness. Second, Hyper-V's TLB flush hypercall takes 'mm->pgd' argument so Hyper-V may avoid the flush if CR3 doesn't match. Fix the immediate issue with cpumask_last()/hv_cpu_number_to_vp_number() and remove the pointless cpumask_empty() check from the beginning of the function as it really doesn't protect anything. Also, avoid the hypercall altogether when 'flush->processor_mask' ends up being empty. Fixes:ad0a6bad44
("x86/hyperv: check cpu mask after interrupt has been disabled") Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Reviewed-by: Michael Kelley <mikelley@microsoft.com> Link: https://lore.kernel.org/r/20220106094611.1404218-1-vkuznets@redhat.com Signed-off-by: Wei Liu <wei.liu@kernel.org>
243 lines
6.3 KiB
C
243 lines
6.3 KiB
C
#define pr_fmt(fmt) "Hyper-V: " fmt
|
|
|
|
#include <linux/hyperv.h>
|
|
#include <linux/log2.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/types.h>
|
|
|
|
#include <asm/fpu/api.h>
|
|
#include <asm/mshyperv.h>
|
|
#include <asm/msr.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/tlb.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <asm/trace/hyperv.h>
|
|
|
|
/* Each gva in gva_list encodes up to 4096 pages to flush */
|
|
#define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
|
|
|
|
static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
|
|
const struct flush_tlb_info *info);
|
|
|
|
/*
|
|
* Fills in gva_list starting from offset. Returns the number of items added.
|
|
*/
|
|
static inline int fill_gva_list(u64 gva_list[], int offset,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
int gva_n = offset;
|
|
unsigned long cur = start, diff;
|
|
|
|
do {
|
|
diff = end > cur ? end - cur : 0;
|
|
|
|
gva_list[gva_n] = cur & PAGE_MASK;
|
|
/*
|
|
* Lower 12 bits encode the number of additional
|
|
* pages to flush (in addition to the 'cur' page).
|
|
*/
|
|
if (diff >= HV_TLB_FLUSH_UNIT) {
|
|
gva_list[gva_n] |= ~PAGE_MASK;
|
|
cur += HV_TLB_FLUSH_UNIT;
|
|
} else if (diff) {
|
|
gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
|
|
cur = end;
|
|
}
|
|
|
|
gva_n++;
|
|
|
|
} while (cur < end);
|
|
|
|
return gva_n - offset;
|
|
}
|
|
|
|
static void hyperv_flush_tlb_multi(const struct cpumask *cpus,
|
|
const struct flush_tlb_info *info)
|
|
{
|
|
int cpu, vcpu, gva_n, max_gvas;
|
|
struct hv_tlb_flush **flush_pcpu;
|
|
struct hv_tlb_flush *flush;
|
|
u64 status;
|
|
unsigned long flags;
|
|
|
|
trace_hyperv_mmu_flush_tlb_multi(cpus, info);
|
|
|
|
if (!hv_hypercall_pg)
|
|
goto do_native;
|
|
|
|
local_irq_save(flags);
|
|
|
|
flush_pcpu = (struct hv_tlb_flush **)
|
|
this_cpu_ptr(hyperv_pcpu_input_arg);
|
|
|
|
flush = *flush_pcpu;
|
|
|
|
if (unlikely(!flush)) {
|
|
local_irq_restore(flags);
|
|
goto do_native;
|
|
}
|
|
|
|
if (info->mm) {
|
|
/*
|
|
* AddressSpace argument must match the CR3 with PCID bits
|
|
* stripped out.
|
|
*/
|
|
flush->address_space = virt_to_phys(info->mm->pgd);
|
|
flush->address_space &= CR3_ADDR_MASK;
|
|
flush->flags = 0;
|
|
} else {
|
|
flush->address_space = 0;
|
|
flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
|
|
}
|
|
|
|
flush->processor_mask = 0;
|
|
if (cpumask_equal(cpus, cpu_present_mask)) {
|
|
flush->flags |= HV_FLUSH_ALL_PROCESSORS;
|
|
} else {
|
|
/*
|
|
* From the supplied CPU set we need to figure out if we can get
|
|
* away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
|
|
* hypercalls. This is possible when the highest VP number in
|
|
* the set is < 64. As VP numbers are usually in ascending order
|
|
* and match Linux CPU ids, here is an optimization: we check
|
|
* the VP number for the highest bit in the supplied set first
|
|
* so we can quickly find out if using *_EX hypercalls is a
|
|
* must. We will also check all VP numbers when walking the
|
|
* supplied CPU set to remain correct in all cases.
|
|
*/
|
|
cpu = cpumask_last(cpus);
|
|
|
|
if (cpu < nr_cpumask_bits && hv_cpu_number_to_vp_number(cpu) >= 64)
|
|
goto do_ex_hypercall;
|
|
|
|
for_each_cpu(cpu, cpus) {
|
|
vcpu = hv_cpu_number_to_vp_number(cpu);
|
|
if (vcpu == VP_INVAL) {
|
|
local_irq_restore(flags);
|
|
goto do_native;
|
|
}
|
|
|
|
if (vcpu >= 64)
|
|
goto do_ex_hypercall;
|
|
|
|
__set_bit(vcpu, (unsigned long *)
|
|
&flush->processor_mask);
|
|
}
|
|
|
|
/* nothing to flush if 'processor_mask' ends up being empty */
|
|
if (!flush->processor_mask) {
|
|
local_irq_restore(flags);
|
|
return;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* We can flush not more than max_gvas with one hypercall. Flush the
|
|
* whole address space if we were asked to do more.
|
|
*/
|
|
max_gvas = (PAGE_SIZE - sizeof(*flush)) / sizeof(flush->gva_list[0]);
|
|
|
|
if (info->end == TLB_FLUSH_ALL) {
|
|
flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
|
|
status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
|
|
flush, NULL);
|
|
} else if (info->end &&
|
|
((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
|
|
status = hv_do_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE,
|
|
flush, NULL);
|
|
} else {
|
|
gva_n = fill_gva_list(flush->gva_list, 0,
|
|
info->start, info->end);
|
|
status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
|
|
gva_n, 0, flush, NULL);
|
|
}
|
|
goto check_status;
|
|
|
|
do_ex_hypercall:
|
|
status = hyperv_flush_tlb_others_ex(cpus, info);
|
|
|
|
check_status:
|
|
local_irq_restore(flags);
|
|
|
|
if (hv_result_success(status))
|
|
return;
|
|
do_native:
|
|
native_flush_tlb_multi(cpus, info);
|
|
}
|
|
|
|
static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
|
|
const struct flush_tlb_info *info)
|
|
{
|
|
int nr_bank = 0, max_gvas, gva_n;
|
|
struct hv_tlb_flush_ex **flush_pcpu;
|
|
struct hv_tlb_flush_ex *flush;
|
|
u64 status;
|
|
|
|
if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
|
|
return HV_STATUS_INVALID_PARAMETER;
|
|
|
|
flush_pcpu = (struct hv_tlb_flush_ex **)
|
|
this_cpu_ptr(hyperv_pcpu_input_arg);
|
|
|
|
flush = *flush_pcpu;
|
|
|
|
if (info->mm) {
|
|
/*
|
|
* AddressSpace argument must match the CR3 with PCID bits
|
|
* stripped out.
|
|
*/
|
|
flush->address_space = virt_to_phys(info->mm->pgd);
|
|
flush->address_space &= CR3_ADDR_MASK;
|
|
flush->flags = 0;
|
|
} else {
|
|
flush->address_space = 0;
|
|
flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
|
|
}
|
|
|
|
flush->hv_vp_set.valid_bank_mask = 0;
|
|
|
|
flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
|
|
nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
|
|
if (nr_bank < 0)
|
|
return HV_STATUS_INVALID_PARAMETER;
|
|
|
|
/*
|
|
* We can flush not more than max_gvas with one hypercall. Flush the
|
|
* whole address space if we were asked to do more.
|
|
*/
|
|
max_gvas =
|
|
(PAGE_SIZE - sizeof(*flush) - nr_bank *
|
|
sizeof(flush->hv_vp_set.bank_contents[0])) /
|
|
sizeof(flush->gva_list[0]);
|
|
|
|
if (info->end == TLB_FLUSH_ALL) {
|
|
flush->flags |= HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY;
|
|
status = hv_do_rep_hypercall(
|
|
HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
|
|
0, nr_bank, flush, NULL);
|
|
} else if (info->end &&
|
|
((info->end - info->start)/HV_TLB_FLUSH_UNIT) > max_gvas) {
|
|
status = hv_do_rep_hypercall(
|
|
HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
|
|
0, nr_bank, flush, NULL);
|
|
} else {
|
|
gva_n = fill_gva_list(flush->gva_list, nr_bank,
|
|
info->start, info->end);
|
|
status = hv_do_rep_hypercall(
|
|
HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX,
|
|
gva_n, nr_bank, flush, NULL);
|
|
}
|
|
|
|
return status;
|
|
}
|
|
|
|
void hyperv_setup_mmu_ops(void)
|
|
{
|
|
if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
|
|
return;
|
|
|
|
pr_info("Using hypercall for remote TLB flush\n");
|
|
pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
|
|
pv_ops.mmu.tlb_remove_table = tlb_remove_table;
|
|
}
|