From: Kyle Huey <me(a)kylehuey.com>
When management of the PKRU register was moved away from XSTATE, emulation
of PKRU's existence in XSTATE was added for APIs that read XSTATE, but not
for APIs that write XSTATE. This can be seen by running gdb and executing
`p $pkru`, `set $pkru = 42`, and `p $pkru`. On affected kernels (5.14+) the
write to the PKRU register (which gdb performs through ptrace) is ignored.
There are three relevant APIs: PTRACE_SETREGSET with NT_X86_XSTATE,
sigreturn, and KVM_SET_XSAVE. KVM_SET_XSAVE has its own special handling to
make PKRU writes take effect (in fpu_copy_uabi_to_guest_fpstate). Push that
down into copy_uabi_to_xstate and have PTRACE_SETREGSET with NT_X86_XSTATE
and sigreturn pass in pointers to the appropriate PKRU value.
This also adds code to initialize the PKRU value to the hardware init value
(namely 0) if the PKRU bit is not set in the XSTATE header to match XRSTOR.
This is a change to the current KVM_SET_XSAVE behavior.
Changelog since v4:
- Selftest additionally checks PKRU readbacks through ptrace.
- Selftest flips all PKRU bits (except the key used for PROT_EXEC).
Changelog since v3:
- The v3 patch is now part 1 of 2.
- Adds a selftest in part 2 of 2.
Changelog since v2:
- Removed now unused variables in fpu_copy_uabi_to_guest_fpstate
Changelog since v1:
- Handles the error case of copy_to_buffer().
Signed-off-by: Kyle Huey <me(a)kylehuey.com>
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Borislav Petkov <bp(a)suse.de>
Cc: kvm(a)vger.kernel.org # For edge case behavior of KVM_SET_XSAVE
Cc: stable(a)vger.kernel.org # 5.14+
Fixes: e84ba47e313d ("x86/fpu: Hook up PKRU into ptrace()")
---
arch/x86/kernel/fpu/core.c | 13 +------------
arch/x86/kernel/fpu/regset.c | 2 +-
arch/x86/kernel/fpu/signal.c | 2 +-
arch/x86/kernel/fpu/xstate.c | 28 +++++++++++++++++++++++-----
arch/x86/kernel/fpu/xstate.h | 4 ++--
5 files changed, 28 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 3b28c5b25e12..46b935bc87c8 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -391,8 +391,6 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
{
struct fpstate *kstate = gfpu->fpstate;
const union fpregs_state *ustate = buf;
- struct pkru_state *xpkru;
- int ret;
if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) {
if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE)
@@ -406,16 +404,7 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf,
if (ustate->xsave.header.xfeatures & ~xcr0)
return -EINVAL;
- ret = copy_uabi_from_kernel_to_xstate(kstate, ustate);
- if (ret)
- return ret;
-
- /* Retrieve PKRU if not in init state */
- if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) {
- xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU);
- *vpkru = xpkru->pkru;
- }
- return 0;
+ return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru);
}
EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate);
#endif /* CONFIG_KVM */
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 75ffaef8c299..6d056b68f4ed 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -167,7 +167,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
}
fpu_force_restore(fpu);
- ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf);
+ ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf, &target->thread.pkru);
out:
vfree(tmpbuf);
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 91d4b6de58ab..558076dbde5b 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -396,7 +396,7 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
fpregs = &fpu->fpstate->regs;
if (use_xsave() && !fx_only) {
- if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx))
+ if (copy_sigframe_from_user_to_xstate(tsk, buf_fx))
return false;
} else {
if (__copy_from_user(&fpregs->fxsave, buf_fx,
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..e01d3514ae68 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1197,7 +1197,7 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size,
static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
- const void __user *ubuf)
+ const void __user *ubuf, u32 *pkru)
{
struct xregs_state *xsave = &fpstate->regs.xsave;
unsigned int offset, size;
@@ -1235,6 +1235,24 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
for (i = 0; i < XFEATURE_MAX; i++) {
mask = BIT_ULL(i);
+ if (i == XFEATURE_PKRU) {
+ /*
+ * Retrieve PKRU if not in init state, otherwise
+ * initialize it.
+ */
+ if (hdr.xfeatures & mask) {
+ struct pkru_state xpkru = {0};
+
+ if (copy_from_buffer(&xpkru, xstate_offsets[i],
+ sizeof(xpkru), kbuf, ubuf))
+ return -EFAULT;
+
+ *pkru = xpkru.pkru;
+ } else {
+ *pkru = 0;
+ }
+ }
+
if (hdr.xfeatures & mask) {
void *dst = __raw_xsave_addr(xsave, i);
@@ -1264,9 +1282,9 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf,
* Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S]
* format and copy to the target thread. Used by ptrace and KVM.
*/
-int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf)
+int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru)
{
- return copy_uabi_to_xstate(fpstate, kbuf, NULL);
+ return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru);
}
/*
@@ -1274,10 +1292,10 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf)
* XSAVE[S] format and copy to the target thread. This is called from the
* sigreturn() and rt_sigreturn() system calls.
*/
-int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate,
+int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
const void __user *ubuf)
{
- return copy_uabi_to_xstate(fpstate, NULL, ubuf);
+ return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
}
static bool validate_independent_components(u64 mask)
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 5ad47031383b..a4ecb04d8d64 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -46,8 +46,8 @@ extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
u32 pkru_val, enum xstate_copy_mode copy_mode);
extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode mode);
-extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf);
-extern int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf);
+extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
+extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf);
extern void fpu__init_cpu_xstate(void);
--
2.37.1
migrate_vma_setup() has a fast path in migrate_vma_collect_pmd() that
installs migration entries directly if it can lock the migrating page.
When removing a dirty pte the dirty bit is supposed to be carried over
to the underlying page to prevent it being lost.
Currently migrate_vma_*() can only be used for private anonymous
mappings. That means loss of the dirty bit usually doesn't result in
data loss because these pages are typically not file-backed. However
pages may be backed by swap storage which can result in data loss if an
attempt is made to migrate a dirty page that doesn't yet have the
PageDirty flag set.
In this case migration will fail due to unexpected references but the
dirty pte bit will be lost. If the page is subsequently reclaimed data
won't be written back to swap storage as it is considered uptodate,
resulting in data loss if the page is subsequently accessed.
Prevent this by copying the dirty bit to the page when removing the pte
to match what try_to_migrate_one() does.
Signed-off-by: Alistair Popple <apopple(a)nvidia.com>
Acked-by: Peter Xu <peterx(a)redhat.com>
Reported-by: Huang Ying <ying.huang(a)intel.com>
Fixes: 8c3328f1f36a ("mm/migrate: migrate_vma() unmap page from vma while collecting pages")
Cc: stable(a)vger.kernel.org
---
Changes for v2:
- Fixed up Reported-by tag.
- Added Peter's Acked-by.
- Atomically read and clear the pte to prevent the dirty bit getting
set after reading it.
- Added fixes tag
---
mm/migrate_device.c | 21 ++++++++-------------
1 file changed, 8 insertions(+), 13 deletions(-)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 27fb37d..e2d09e5 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -7,6 +7,7 @@
#include <linux/export.h>
#include <linux/memremap.h>
#include <linux/migrate.h>
+#include <linux/mm.h>
#include <linux/mm_inline.h>
#include <linux/mmu_notifier.h>
#include <linux/oom.h>
@@ -61,7 +62,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
struct migrate_vma *migrate = walk->private;
struct vm_area_struct *vma = walk->vma;
struct mm_struct *mm = vma->vm_mm;
- unsigned long addr = start, unmapped = 0;
+ unsigned long addr = start;
spinlock_t *ptl;
pte_t *ptep;
@@ -193,11 +194,10 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
bool anon_exclusive;
pte_t swp_pte;
+ flush_cache_page(vma, addr, pte_pfn(*ptep));
+ pte = ptep_clear_flush(vma, addr, ptep);
anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
if (anon_exclusive) {
- flush_cache_page(vma, addr, pte_pfn(*ptep));
- ptep_clear_flush(vma, addr, ptep);
-
if (page_try_share_anon_rmap(page)) {
set_pte_at(mm, addr, ptep, pte);
unlock_page(page);
@@ -205,12 +205,14 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
mpfn = 0;
goto next;
}
- } else {
- ptep_get_and_clear(mm, addr, ptep);
}
migrate->cpages++;
+ /* Set the dirty flag on the folio now the pte is gone. */
+ if (pte_dirty(pte))
+ folio_mark_dirty(page_folio(page));
+
/* Setup special migration page table entry */
if (mpfn & MIGRATE_PFN_WRITE)
entry = make_writable_migration_entry(
@@ -242,9 +244,6 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
*/
page_remove_rmap(page, vma, false);
put_page(page);
-
- if (pte_present(pte))
- unmapped++;
} else {
put_page(page);
mpfn = 0;
@@ -257,10 +256,6 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(ptep - 1, ptl);
- /* Only flush the TLB if we actually modified any entries */
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
-
return 0;
}
base-commit: ffcf9c5700e49c0aee42dcba9a12ba21338e8136
--
git-series 0.9.1
device_register() always calls device_initialize() so calling device_del()
is safe even if device_register() fails. Implement the following advice
from the comment block above device_register(): "NOTE: _Never_ directly free
@dev after calling this function, even if it returned an error! Always use
put_device() to give up the reference initialized in this function instead."
Keep the kfree() call in the error path since srp_release_dev() does not
free the host.
Cc: stable(a)vger.kernel.org
Signed-off-by: Bart Van Assche <bvanassche(a)acm.org>
---
drivers/infiniband/ulp/srp/ib_srp.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 7720ea270ed8..8fd6a88f7a9c 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3909,20 +3909,19 @@ static struct srp_host *srp_add_port(struct srp_device *device, u8 port)
port);
if (device_register(&host->dev))
- goto free_host;
+ goto put_host;
if (device_create_file(&host->dev, &dev_attr_add_target))
- goto err_class;
+ goto put_host;
if (device_create_file(&host->dev, &dev_attr_ibdev))
- goto err_class;
+ goto put_host;
if (device_create_file(&host->dev, &dev_attr_port))
- goto err_class;
+ goto put_host;
return host;
-err_class:
- device_unregister(&host->dev);
-
-free_host:
+put_host:
+ device_del(&host->dev);
+ put_device(&host->dev);
kfree(host);
return NULL;
From: Dmitry Osipenko <dmitry.osipenko(a)collabora.com>
The busy status bit may never de-assert if number of programmed skip
bits is incorrect, resulting in a kernel hang because the bit is polled
endlessly in the code. Fix it by adding timeout for the bit-polling.
This problem is reproducible by setting the data_bit_offset field of
the HEVC slice params to a wrong value by userspace.
Cc: stable(a)vger.kernel.org
Reported-by: Nicolas Dufresne <nicolas.dufresne(a)collabora.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne(a)collabora.com>
---
drivers/staging/media/sunxi/cedrus/cedrus_h265.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
index f703c585d91c5..f0bc118021b0a 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
@@ -227,6 +227,7 @@ static void cedrus_h265_pred_weight_write(struct cedrus_dev *dev,
static void cedrus_h265_skip_bits(struct cedrus_dev *dev, int num)
{
int count = 0;
+ u32 reg;
while (count < num) {
int tmp = min(num - count, 32);
@@ -234,8 +235,9 @@ static void cedrus_h265_skip_bits(struct cedrus_dev *dev, int num)
cedrus_write(dev, VE_DEC_H265_TRIGGER,
VE_DEC_H265_TRIGGER_FLUSH_BITS |
VE_DEC_H265_TRIGGER_TYPE_N_BITS(tmp));
- while (cedrus_read(dev, VE_DEC_H265_STATUS) & VE_DEC_H265_STATUS_VLD_BUSY)
- udelay(1);
+
+ if (cedrus_wait_for(dev, VE_DEC_H265_STATUS, VE_DEC_H265_STATUS_VLD_BUSY))
+ dev_err_ratelimited(dev->dev, "timed out waiting to skip bits\n");
count += tmp;
}
--
2.37.2
The watchdog needs to be schedule before we trigger the decode
operation, otherwise there is a risk that the decoder IRQ will be
called before we have schedule the watchdog. As a side effect, the
watchdog would never be cancelled and its function would be called
at an inappropriate time.
This was observed while running Fluster with GStreamer as a backend.
Some programming error would cause the decoder IRQ to be call very
quickly after the trigger. Later calls into the driver would deadlock
due to the unbalanced state.
Cc: stable(a)vger.kernel.org
Fixes: 7c38a551bda1 ("media: cedrus: Add watchdog for job completion")
Signed-off-by: Nicolas Dufresne <nicolas.dufresne(a)collabora.com>
---
drivers/staging/media/sunxi/cedrus/cedrus_dec.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
index 3b6aa78a2985f..e7f7602a5ab40 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_dec.c
@@ -106,11 +106,11 @@ void cedrus_device_run(void *priv)
/* Trigger decoding if setup went well, bail out otherwise. */
if (!error) {
- dev->dec_ops[ctx->current_codec]->trigger(ctx);
-
/* Start the watchdog timer. */
schedule_delayed_work(&dev->watchdog_work,
msecs_to_jiffies(2000));
+
+ dev->dec_ops[ctx->current_codec]->trigger(ctx);
} else {
v4l2_m2m_buf_done_and_job_finish(ctx->dev->m2m_dev,
ctx->fh.m2m_ctx,
--
2.37.2
From: Dongliang Mu <mudongliangabcd(a)gmail.com>
In alloc_inode, inode_init_always() could return -ENOMEM if
security_inode_alloc() fails, which causes inode->i_private
uninitialized. Then nilfs_is_metadata_file_inode() returns
true and nilfs_free_inode() wrongly calls nilfs_mdt_destroy(),
which frees the uninitialized inode->i_private
and leads to crashes(e.g., UAF/GPF).
Fix this by moving security_inode_alloc just prior to
this_cpu_inc(nr_inodes)
Link: https://lkml.kernel.org/r/CAFcO6XOcf1Jj2SeGt=jJV59wmhESeSKpfR0omdFRq+J9nD1v…
Reported-by: butt3rflyh4ck <butterflyhuangxx(a)gmail.com>
Reported-by: Hao Sun <sunhao.th(a)gmail.com>
Reported-by: Jiacheng Xu <stitch(a)zju.edu.cn>
Signed-off-by: Dongliang Mu <mudongliangabcd(a)gmail.com>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: stable(a)vger.kernel.org
---
v1->v2: move security_inode_alloc at the very end according to Al Viro
other than initializing i_private before security_inode_alloc.
fs/inode.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 6462276dfdf0..49d1eb91728c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -192,8 +192,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
inode->i_wb_frn_history = 0;
#endif
- if (security_inode_alloc(inode))
- goto out;
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
@@ -228,6 +226,9 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
inode->i_fsnotify_mask = 0;
#endif
inode->i_flctx = NULL;
+
+ if (security_inode_alloc(inode))
+ goto out;
this_cpu_inc(nr_inodes);
return 0;
--
2.35.1
After xHC controller is started, either in probe or resume, it can take
a while before any of the connected usb devices are visible to the roothub
due to link training.
It's possible xhci driver loads, sees no acivity and suspends the host
before the USB device is visible.
In one testcase with a hotplugged xHC controller the host finally detected
the connected USB device and generated a wake 500ms after host initial
start.
If hosts didn't suspend the device duringe training it probablty wouldn't
take up to 500ms to detect it, but looking at specs reveal USB3 link
training has a couple long timeout values, such as 120ms
RxDetectQuietTimeout, and 360ms PollingLFPSTimeout.
So Add a 500ms grace period that keeps polling the roothub for 500ms after
start, preventing runtime suspend until USB devices are detected.
Cc: stable(a)vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com>
---
drivers/usb/host/xhci-hub.c | 11 +++++++++++
drivers/usb/host/xhci.c | 4 +++-
drivers/usb/host/xhci.h | 2 +-
3 files changed, 15 insertions(+), 2 deletions(-)
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 0fdc014c9401..b30298986a69 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1648,6 +1648,17 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
status = bus_state->resuming_ports;
+ /*
+ * SS devices are only visible to roothub after link training completes.
+ * Keep polling roothubs for a grace period after xHC start
+ */
+ if (xhci->run_graceperiod) {
+ if (time_before(jiffies, xhci->run_graceperiod))
+ status = 1;
+ else
+ xhci->run_graceperiod = 0;
+ }
+
mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
/* For each port, did anything change? If so, set that bit in buf. */
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 65858f607437..1afd32beec99 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -151,9 +151,11 @@ int xhci_start(struct xhci_hcd *xhci)
xhci_err(xhci, "Host took too long to start, "
"waited %u microseconds.\n",
XHCI_MAX_HALT_USEC);
- if (!ret)
+ if (!ret) {
/* clear state flags. Including dying, halted or removing */
xhci->xhc_state = 0;
+ xhci->run_graceperiod = jiffies + msecs_to_jiffies(500);
+ }
return ret;
}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 1960b47acfb2..df6f2ebaff18 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1826,7 +1826,7 @@ struct xhci_hcd {
/* Host controller watchdog timer structures */
unsigned int xhc_state;
-
+ unsigned long run_graceperiod;
u32 command;
struct s3_save s3;
/* Host controller is dying - not responding to commands. "I'm not dead yet!"
--
2.25.1