Hi,
with Michael, we realized that this patch merged upstream solves an
issue in the device emulation in the vhost-vsock module.
Before this patch, the emulation did not meet the VIRTIO vsock
specification, assuming that the buffer in the RX virtqueue was always 4 KB,
without checking the actual size.
Please, backport the following patch to fix this issue:
commit 6dbd3e66e7785a2f055bf84d98de9b8fd31ff3f5
Author: Stefano Garzarella <sgarzare(a)redhat.com>
Date: Tue Jul 30 17:43:33 2019 +0200
vhost/vsock: split packets to send using multiple buffers
If the packets to sent to the guest are bigger than the buffer
available, we can split them, using multiple buffers and fixing
the length in the packet header.
This is safe since virtio-vsock supports only stream sockets.
Signed-off-by: Stefano Garzarella <sgarzare(a)redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha(a)redhat.com>
Acked-by: Michael S. Tsirkin <mst(a)redhat.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
The commit applies and builds against 4.14, 4.19, and 5.3
Thanks,
Stefano
The patch below does not apply to the 5.3-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 7a5ee6edb42e0bb487954806d34877995b6b8d59 Mon Sep 17 00:00:00 2001
From: Chenyi Qiang <chenyi.qiang(a)intel.com>
Date: Wed, 6 Nov 2019 14:35:20 +0800
Subject: [PATCH] KVM: X86: Fix initialization of MSR lists
The three MSR lists(msrs_to_save[], emulated_msrs[] and
msr_based_features[]) are global arrays of kvm.ko, which are
adjusted (copy supported MSRs forward to override the unsupported MSRs)
when insmod kvm-{intel,amd}.ko, but it doesn't reset these three arrays
to their initial value when rmmod kvm-{intel,amd}.ko. Thus, at the next
installation, kvm-{intel,amd}.ko will do operations on the modified
arrays with some MSRs lost and some MSRs duplicated.
So define three constant arrays to hold the initial MSR lists and
initialize msrs_to_save[], emulated_msrs[] and msr_based_features[]
based on the constant arrays.
Cc: stable(a)vger.kernel.org
Reviewed-by: Xiaoyao Li <xiaoyao.li(a)intel.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang(a)intel.com>
[Remove now useless conditionals. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ff395f812719..8c8a5e20ea06 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1132,13 +1132,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
* and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
*
- * This list is modified at module load time to reflect the
+ * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
+ * extract the supported MSRs from the related const lists.
+ * msrs_to_save is selected from the msrs_to_save_all to reflect the
* capabilities of the host cpu. This capabilities test skips MSRs that are
- * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
+ * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
* may depend on host virtualization features rather than host cpu features.
*/
-static u32 msrs_to_save[] = {
+static const u32 msrs_to_save_all[] = {
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_STAR,
#ifdef CONFIG_X86_64
@@ -1179,9 +1181,10 @@ static u32 msrs_to_save[] = {
MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
};
+static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
static unsigned num_msrs_to_save;
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs_all[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@@ -1220,7 +1223,7 @@ static u32 emulated_msrs[] = {
* by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
* We always support the "true" VMX control MSRs, even if the host
* processor does not, so I am putting these registers here rather
- * than in msrs_to_save.
+ * than in msrs_to_save_all.
*/
MSR_IA32_VMX_BASIC,
MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@@ -1239,13 +1242,14 @@ static u32 emulated_msrs[] = {
MSR_KVM_POLL_CONTROL,
};
+static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
static unsigned num_emulated_msrs;
/*
* List of msr numbers which are used to expose MSR-based features that
* can be used by a hypervisor to validate requested CPU features.
*/
-static u32 msr_based_features[] = {
+static const u32 msr_based_features_all[] = {
MSR_IA32_VMX_BASIC,
MSR_IA32_VMX_TRUE_PINBASED_CTLS,
MSR_IA32_VMX_PINBASED_CTLS,
@@ -1270,6 +1274,7 @@ static u32 msr_based_features[] = {
MSR_IA32_ARCH_CAPABILITIES,
};
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
static unsigned int num_msr_based_features;
static u64 kvm_get_arch_capabilities(void)
@@ -5090,22 +5095,22 @@ static void kvm_init_msr_list(void)
{
struct x86_pmu_capability x86_pmu;
u32 dummy[2];
- unsigned i, j;
+ unsigned i;
BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
- "Please update the fixed PMCs in msrs_to_save[]");
+ "Please update the fixed PMCs in msrs_to_saved_all[]");
perf_get_x86_pmu_capability(&x86_pmu);
- for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
- if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
+ for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
+ if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
continue;
/*
* Even MSRs that are valid in the host may not be exposed
* to the guests in some cases.
*/
- switch (msrs_to_save[i]) {
+ switch (msrs_to_save_all[i]) {
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported())
continue;
@@ -5133,17 +5138,17 @@ static void kvm_init_msr_list(void)
break;
case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
if (!kvm_x86_ops->pt_supported() ||
- msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
+ msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
continue;
break;
case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
- if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+ if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
continue;
break;
case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
- if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+ if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
continue;
}
@@ -5151,34 +5156,25 @@ static void kvm_init_msr_list(void)
break;
}
- if (j < i)
- msrs_to_save[j] = msrs_to_save[i];
- j++;
+ msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
}
- num_msrs_to_save = j;
- for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
- if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+ for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
+ if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
continue;
- if (j < i)
- emulated_msrs[j] = emulated_msrs[i];
- j++;
+ emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
}
- num_emulated_msrs = j;
- for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
+ for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
struct kvm_msr_entry msr;
- msr.index = msr_based_features[i];
+ msr.index = msr_based_features_all[i];
if (kvm_get_msr_feature(&msr))
continue;
- if (j < i)
- msr_based_features[j] = msr_based_features[i];
- j++;
+ msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
}
- num_msr_based_features = j;
}
static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
When a port sends PLOGI, discovery state should be changed to login
pending, otherwise RELOGIN_NEEDED bit is set in
qla24xx_handle_plogi_done_event(). RELOGIN_NEEDED triggers another
PLOGI, and it never goes out of the loop until login timer expires.
Fixes: 8777e4314d397 ("scsi: qla2xxx: Migrate NVME N2N handling into state machine")
Fixes: 8b5292bcfcacf ("scsi: qla2xxx: Fix Relogin to prevent modifying scan_state flag")
Cc: Quinn Tran <qutran(a)marvell.com>
Cc: stable(a)vger.kernel.org
Acked-by: Himanshu Madhani <hmadhani(a)marvell.com>
Reviewed-by: Hannes Reinecke <hare(a)suse.de>
Tested-by: Hannes Reinecke <hare(a)suse.de>
Signed-off-by: Roman Bolshakov <r.bolshakov(a)yadro.com>
---
drivers/scsi/qla2xxx/qla_init.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 4f3da968163e..fcb309be50d9 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -533,6 +533,7 @@ static int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport)
e->u.fcport.fcport = fcport;
fcport->flags |= FCF_ASYNC_ACTIVE;
+ fcport->disc_state = DSC_LOGIN_PEND;
return qla2x00_post_work(vha, e);
}
--
2.24.0
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 5df373e95689b9519b8557da7c5bd0db0856d776 Mon Sep 17 00:00:00 2001
From: Vinayak Menon <vinmenon(a)codeaurora.org>
Date: Fri, 15 Nov 2019 17:35:00 -0800
Subject: [PATCH] mm/page_io.c: do not free shared swap slots
The following race is observed due to which a processes faulting on a
swap entry, finds the page neither in swapcache nor swap. This causes
zram to give a zero filled page that gets mapped to the process,
resulting in a user space crash later.
Consider parent and child processes Pa and Pb sharing the same swap slot
with swap_count 2. Swap is on zram with SWP_SYNCHRONOUS_IO set.
Virtual address 'VA' of Pa and Pb points to the shared swap entry.
Pa Pb
fault on VA fault on VA
do_swap_page do_swap_page
lookup_swap_cache fails lookup_swap_cache fails
Pb scheduled out
swapin_readahead (deletes zram entry)
swap_free (makes swap_count 1)
Pb scheduled in
swap_readpage (swap_count == 1)
Takes SWP_SYNCHRONOUS_IO path
zram enrty absent
zram gives a zero filled page
Fix this by making sure that swap slot is freed only when swap count
drops down to one.
Link: http://lkml.kernel.org/r/1571743294-14285-1-git-send-email-vinmenon@codeaur…
Fixes: aa8d22a11da9 ("mm: swap: SWP_SYNCHRONOUS_IO: skip swapcache only if swapped page has no other reference")
Signed-off-by: Vinayak Menon <vinmenon(a)codeaurora.org>
Suggested-by: Minchan Kim <minchan(a)google.com>
Acked-by: Minchan Kim <minchan(a)kernel.org>
Cc: Michal Hocko <mhocko(a)suse.com>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org>
diff --git a/mm/page_io.c b/mm/page_io.c
index 24ee600f9131..60a66a58b9bf 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page)
{
struct swap_info_struct *sis;
struct gendisk *disk;
+ swp_entry_t entry;
/*
* There is no guarantee that the page is in swap cache - the software
@@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page)
* we again wish to reclaim it.
*/
disk = sis->bdev->bd_disk;
- if (disk->fops->swap_slot_free_notify) {
- swp_entry_t entry;
+ entry.val = page_private(page);
+ if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
unsigned long offset;
- entry.val = page_private(page);
offset = swp_offset(entry);
SetPageDirty(page);
The following commit has been merged into the x86/urgent branch of tip:
Commit-ID: 4a13b0e3e10996b9aa0b45a764ecfe49f6fcd360
Gitweb: https://git.kernel.org/tip/4a13b0e3e10996b9aa0b45a764ecfe49f6fcd360
Author: Andy Lutomirski <luto(a)kernel.org>
AuthorDate: Sun, 24 Nov 2019 08:50:03 -08:00
Committer: Ingo Molnar <mingo(a)kernel.org>
CommitterDate: Mon, 25 Nov 2019 09:36:47 +01:00
x86/entry/32: Fix FIXUP_ESPFIX_STACK with user CR3
UNWIND_ESPFIX_STACK needs to read the GDT, and the GDT mapping that
can be accessed via %fs is not mapped in the user pagetables. Use
SGDT to find the cpu_entry_area mapping and read the espfix offset
from that instead.
Reported-and-tested-by: Borislav Petkov <bp(a)alien8.de>
Signed-off-by: Andy Lutomirski <luto(a)kernel.org>
Cc: Peter Zijlstra <peterz(a)infradead.org>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Linus Torvalds <torvalds(a)linux-foundation.org>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Ingo Molnar <mingo(a)kernel.org>
---
arch/x86/entry/entry_32.S | 21 ++++++++++++++++++---
1 file changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 0b8c931..f07baf0 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -415,7 +415,8 @@
.macro CHECK_AND_APPLY_ESPFIX
#ifdef CONFIG_X86_ESPFIX32
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
@@ -1147,12 +1148,26 @@ ENDPROC(entry_INT80_32)
* We can't call C functions using the ESPFIX stack. This code reads
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
+ *
+ * We might be on user CR3 here, so percpu data is not mapped and we can't
+ * access the GDT through the percpu segment. Instead, use SGDT to find
+ * the cpu_entry_area alias of the GDT.
*/
#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
- mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
- mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+ pushl %ecx
+ subl $2*4, %esp
+ sgdt (%esp)
+ movl 2(%esp), %ecx /* GDT address */
+ /*
+ * Careful: ECX is a linear pointer, so we need to force base
+ * zero. %cs is the only known-linear segment we have right now.
+ */
+ mov %cs:GDT_ESPFIX_OFFSET + 4(%ecx), %al /* bits 16..23 */
+ mov %cs:GDT_ESPFIX_OFFSET + 7(%ecx), %ah /* bits 24..31 */
shl $16, %eax
+ addl $2*4, %esp
+ popl %ecx
addl %esp, %eax /* the adjusted stack pointer */
pushl $__KERNEL_DS
pushl %eax