I upgraded from kernel 6.1.94 to 6.1.99 on one of my machines and noticed that
the dmesg line "Incomplete global flushes, disabling PCID" had disappeared from
the log.
That message comes from commit c26b9e193172f48cd0ccc64285337106fb8aa804, which
disables PCID support on some broken hardware in arch/x86/mm/init.c:
#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \
.family = 6, \
.model = _model, \
}
/*
* INVLPG may not properly flush Global entries
* on these CPUs when PCIDs are enabled.
*/
static const struct x86_cpu_id invlpg_miss_ids[] = {
INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
{}
...
if (x86_match_cpu(invlpg_miss_ids)) {
pr_info("Incomplete global flushes, disabling PCID");
setup_clear_cpu_cap(X86_FEATURE_PCID);
return;
}
arch/x86/mm/init.c, which has that code, hasn't changed in 6.1.94 -> 6.1.99.
However I found a commit changing how x86_match_cpu() behaves in 6.1.96:
commit 8ab1361b2eae44077fef4adea16228d44ffb860c
Author: Tony Luck <tony.luck(a)intel.com>
Date: Mon May 20 15:45:33 2024 -0700
x86/cpu: Fix x86_match_cpu() to match just X86_VENDOR_INTEL
I suspect this broke the PCID disabling code in arch/x86/mm/init.c.
The commit message says:
"Add a new flags field to struct x86_cpu_id that has a bit set to indicate that
this entry in the array is valid. Update X86_MATCH*() macros to set that bit.
Change the end-marker check in x86_match_cpu() to just check the flags field
for this bit."
But the PCID disabling code in 6.1.99 does not make use of the
X86_MATCH*() macros; instead, it defines a new INTEL_MATCH() macro without the
X86_CPU_ID_FLAG_ENTRY_VALID flag.
I looked in upstream git and found an existing fix:
commit 2eda374e883ad297bd9fe575a16c1dc850346075
Author: Tony Luck <tony.luck(a)intel.com>
Date: Wed Apr 24 11:15:18 2024 -0700
x86/mm: Switch to new Intel CPU model defines
New CPU #defines encode vendor and family as well as model.
[ dhansen: vertically align 0's in invlpg_miss_ids[] ]
Signed-off-by: Tony Luck <tony.luck(a)intel.com>
Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de>
Link: https://lore.kernel.org/all/20240424181518.41946-1-tony.luck%40intel.com
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 679893ea5e68..6b43b6480354 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -261,21 +261,17 @@ static void __init probe_page_size_mask(void)
}
}
-#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \
- .family = 6, \
- .model = _model, \
- }
/*
* INVLPG may not properly flush Global entries
* on these CPUs when PCIDs are enabled.
*/
static const struct x86_cpu_id invlpg_miss_ids[] = {
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
- INTEL_MATCH(INTEL_FAM6_ATOM_GRACEMONT ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+ X86_MATCH_VFM(INTEL_ALDERLAKE, 0),
+ X86_MATCH_VFM(INTEL_ALDERLAKE_L, 0),
+ X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_P, 0),
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, 0),
{}
};
The fix removed the custom INTEL_MATCH macro and uses the X86_MATCH*() macros
with X86_CPU_ID_FLAG_ENTRY_VALID. This fixed commit was never backported to 6.1,
so it looks like a stable series regression due to a missing backport.
If I apply the fix patch on 6.1.99, the PCID disabling code activates again.
I had to change all the INTEL_* definitions to the old definitions to make it
build:
static const struct x86_cpu_id invlpg_miss_ids[] = {
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE ),
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ),
- INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P),
- INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S),
+ X86_MATCH_VFM(INTEL_FAM6_ALDERLAKE, 0),
+ X86_MATCH_VFM(INTEL_FAM6_ALDERLAKE_L, 0),
+ X86_MATCH_VFM(INTEL_FAM6_ALDERLAKE_N, 0),
+ X86_MATCH_VFM(INTEL_FAM6_RAPTORLAKE, 0),
+ X86_MATCH_VFM(INTEL_FAM6_RAPTORLAKE_P, 0),
+ X86_MATCH_VFM(INTEL_FAM6_RAPTORLAKE_S, 0),
{}
};
I only looked at the code in arch/x86/mm/init.c, so there may be other uses of
x86_match_cpu() in the kernel that are also broken in 6.1.99.
This email is meant as a bug report, not a pull request. Someone else should
confirm the problem and submit the appropriate fix.
Otherwise when the tracer changes syscall number to -1, the kernel fails
to initialize a0 with -ENOSYS and subsequently fails to return the error
code of the failed syscall to userspace. For example, it will break
strace syscall tampering.
Fixes: 52449c17bdd1 ("riscv: entry: set a0 = -ENOSYS only when syscall != -1")
Reported-by: "Dmitry V. Levin" <ldv(a)strace.io>
Reviewed-by: Björn Töpel <bjorn(a)rivosinc.com>
Cc: stable(a)vger.kernel.org
Signed-off-by: Celeste Liu <CoelacanthusHex(a)gmail.com>
---
arch/riscv/kernel/traps.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 05a16b1f0aee..51ebfd23e007 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
regs->epc += 4;
regs->orig_a0 = regs->a0;
+ regs->a0 = -ENOSYS;
riscv_v_vstate_discard(regs);
@@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
if (syscall >= 0 && syscall < NR_syscalls)
syscall_handler(regs, syscall);
- else if (syscall != -1)
- regs->a0 = -ENOSYS;
+
/*
* Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
* so the maximum stack offset is 1k bytes (10 bits).
--
2.45.2
This reverts commit ad6bcdad2b6724e113f191a12f859a9e8456b26d. I had
nak'd it, and Greg said on the thread that it links that he wasn't going
to take it either, especially since it's not his code or his tree, but
then, seemingly accidentally, it got pushed up some months later, in
what looks like a mistake, with no further discussion in the linked
thread. So revert it, since it's clearly not intended.
Fixes: ad6bcdad2b67 ("vmgenid: emit uevent when VMGENID updates")
Cc: stable(a)vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Link: https://lore.kernel.org/r/20230531095119.11202-2-bchalios@amazon.es
Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com>
---
drivers/virt/vmgenid.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
index b67a28da4702..a1c467a0e9f7 100644
--- a/drivers/virt/vmgenid.c
+++ b/drivers/virt/vmgenid.c
@@ -68,7 +68,6 @@ static int vmgenid_add(struct acpi_device *device)
static void vmgenid_notify(struct acpi_device *device, u32 event)
{
struct vmgenid_state *state = acpi_driver_data(device);
- char *envp[] = { "NEW_VMGENID=1", NULL };
u8 old_id[VMGENID_SIZE];
memcpy(old_id, state->this_id, sizeof(old_id));
@@ -76,7 +75,6 @@ static void vmgenid_notify(struct acpi_device *device, u32 event)
if (!memcmp(old_id, state->this_id, sizeof(old_id)))
return;
add_vmfork_randomness(state->this_id, sizeof(state->this_id));
- kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp);
}
static const struct acpi_device_id vmgenid_ids[] = {
--
2.44.0
The test if a table is a permanently empty one, inspects the address of
the registered ctl_table argument.
However as sysctl_mount_point is an empty array and does not occupy and
space it can end up sharing an address with another object in memory.
If that other object itself is a "struct ctl_table" then registering
that table will fail as it's incorrectly recognized as permanently empty.
Avoid this issue by adding a dummy element to the array so that the
array is not empty anymore and the potential address sharing is avoided.
Explicitly register the table with zero elements as otherwise the dummy
element would be recognized as a sentinel element which would lead to a
runtime warning from the sysctl core.
While the issue seems unlikely to be encountered at this time, this
seems mostly be due to luck.
Also a future change, constifying sysctl_mount_point and root_table, can
reliably trigger this issue on clang 18.
Given that empty arrays are non-standard in the first place,
avoid them if possible.
Reported-by: kernel test robot <oliver.sang(a)intel.com>
Closes: https://lore.kernel.org/oe-lkp/202408051453.f638857e-lkp@intel.com
Fixes: 4a7b29f65094 ("sysctl: move sysctl type to ctl_table_header")
Fixes: a35dd3a786f5 ("sysctl: drop now unnecessary out-of-bounds check")
Cc: stable(a)vger.kernel.org
Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net>
---
This was originally part of a feature series [0], but is resubmitted on
its own to make it into v6.11To.
[0] https://lore.kernel.org/lkml/20240805-sysctl-const-api-v2-0-52c85f02ee5e@we…
---
fs/proc/proc_sysctl.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 9553e77c9d31..d11ebc055ce0 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -29,8 +29,13 @@ static const struct inode_operations proc_sys_inode_operations;
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
-/* Support for permanently empty directories */
-static struct ctl_table sysctl_mount_point[] = { };
+/*
+ * Support for permanently empty directories.
+ * Must be non-empty to avoid sharing an address with other tables.
+ */
+static struct ctl_table sysctl_mount_point[] = {
+ { }
+};
/**
* register_sysctl_mount_point() - registers a sysctl mount point
@@ -42,7 +47,7 @@ static struct ctl_table sysctl_mount_point[] = { };
*/
struct ctl_table_header *register_sysctl_mount_point(const char *path)
{
- return register_sysctl(path, sysctl_mount_point);
+ return register_sysctl_sz(path, sysctl_mount_point, 0);
}
EXPORT_SYMBOL(register_sysctl_mount_point);
---
base-commit: 3e9bff3bbe1355805de919f688bef4baefbfd436
change-id: 20240827-sysctl-const-shared-identity-9ab816e5fdfb
Best regards,
--
Thomas Weißschuh <linux(a)weissschuh.net>
Hello,
This series is based on commit
3e9bff3bbe13 Merge tag 'vfs-6.11-rc6.fixes' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs
of Mainline Linux.
The first patch fixes conversion to "devm_request_threaded_irq()" where
the IRQF_ONESHOT flag should have been added since the handler is NULL.
The second patch fixes the error handling when IRQ request fails in the
probe function. The existing error handling doesn't cleanup the changes
performed prior to the IRQ request invocation.
Regards,
Siddharth.
Siddharth Vadapalli (2):
PCI: dra7xx: Fix threaded IRQ request for "dra7xx-pcie-main" IRQ
PCI: dra7xx: Fix error handling when IRQ request fails in probe
drivers/pci/controller/dwc/pci-dra7xx.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
--
2.40.1
The return value of drm_atomic_get_crtc_state() needs to be
checked. To avoid use of error pointer 'crtc_state' in case
of the failure.
Cc: stable(a)vger.kernel.org
Fixes: dec92020671c ("drm: Use the state pointer directly in planes atomic_check")
Signed-off-by: Ma Ke <make24(a)iscas.ac.cn>
---
drivers/gpu/drm/sti/sti_cursor.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index db0a1eb53532..e460f5ba2d87 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -200,6 +200,8 @@ static int sti_cursor_atomic_check(struct drm_plane *drm_plane,
return 0;
crtc_state = drm_atomic_get_crtc_state(state, crtc);
+ if (IS_ERR(crtc_state))
+ return PTR_ERR(crtc_state);
mode = &crtc_state->mode;
dst_x = new_plane_state->crtc_x;
dst_y = new_plane_state->crtc_y;
--
2.25.1
Call work_on_cpu(cpu, fn, arg) in pci_call_probe() while the argument
@cpu is a offline cpu would cause system stuck forever.
This can be happen if a node is online while all its CPUs are
offline (We can use "maxcpus=1" without "nr_cpus=1" to reproduce it).
So, in the above case, let pci_call_probe() call local_pci_probe()
instead of work_on_cpu() when the best selected cpu is offline.
Fixes: 69a18b18699b ("PCI: Restrict probe functions to housekeeping CPUs")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn>
Signed-off-by: Hongchen Zhang <zhanghongchen(a)loongson.cn>
---
v2 -> v3: Modify commit message according to Markus's suggestion
v1 -> v2: Add a method to reproduce the problem
---
drivers/pci/pci-driver.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index af2996d0d17f..32a99828e6a3 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -386,7 +386,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
free_cpumask_var(wq_domain_mask);
}
- if (cpu < nr_cpu_ids)
+ if ((cpu < nr_cpu_ids) && cpu_online(cpu))
error = work_on_cpu(cpu, local_pci_probe, &ddi);
else
error = local_pci_probe(&ddi);
--
2.33.0
It is possible that the usb power_supply is registered after the probe
of dwc3. In this case, trying to get the usb power_supply during the
probe will fail and there is no chance to try again. Also the usb
power_supply might be unregistered at anytime so that the handle of it
in dwc3 would become invalid. To fix this, get the handle right before
calling to power_supply functions and put it afterward.
Fixes: 6f0764b5adea ("usb: dwc3: add a power supply for current control")
Cc: stable(a)vger.kernel.org
Signed-off-by: Kyle Tso <kyletso(a)google.com>
---
drivers/usb/dwc3/core.c | 25 +++++--------------------
drivers/usb/dwc3/core.h | 4 ++--
drivers/usb/dwc3/gadget.c | 19 ++++++++++++++-----
3 files changed, 21 insertions(+), 27 deletions(-)
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 734de2a8bd21..ab563edd9b4c 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1631,8 +1631,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
u8 tx_thr_num_pkt_prd = 0;
u8 tx_max_burst_prd = 0;
u8 tx_fifo_resize_max_num;
- const char *usb_psy_name;
- int ret;
/* default to highest possible threshold */
lpm_nyet_threshold = 0xf;
@@ -1667,12 +1665,7 @@ static void dwc3_get_properties(struct dwc3 *dwc)
dwc->sys_wakeup = device_may_wakeup(dwc->sysdev);
- ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name);
- if (ret >= 0) {
- dwc->usb_psy = power_supply_get_by_name(usb_psy_name);
- if (!dwc->usb_psy)
- dev_err(dev, "couldn't get usb power supply\n");
- }
+ device_property_read_string(dev, "usb-psy-name", &dwc->usb_psy_name);
dwc->has_lpm_erratum = device_property_read_bool(dev,
"snps,has-lpm-erratum");
@@ -2133,18 +2126,16 @@ static int dwc3_probe(struct platform_device *pdev)
dwc3_get_software_properties(dwc);
dwc->reset = devm_reset_control_array_get_optional_shared(dev);
- if (IS_ERR(dwc->reset)) {
- ret = PTR_ERR(dwc->reset);
- goto err_put_psy;
- }
+ if (IS_ERR(dwc->reset))
+ return PTR_ERR(dwc->reset);
ret = dwc3_get_clocks(dwc);
if (ret)
- goto err_put_psy;
+ return ret;
ret = reset_control_deassert(dwc->reset);
if (ret)
- goto err_put_psy;
+ return ret;
ret = dwc3_clk_enable(dwc);
if (ret)
@@ -2245,9 +2236,6 @@ static int dwc3_probe(struct platform_device *pdev)
dwc3_clk_disable(dwc);
err_assert_reset:
reset_control_assert(dwc->reset);
-err_put_psy:
- if (dwc->usb_psy)
- power_supply_put(dwc->usb_psy);
return ret;
}
@@ -2276,9 +2264,6 @@ static void dwc3_remove(struct platform_device *pdev)
pm_runtime_set_suspended(&pdev->dev);
dwc3_free_event_buffers(dwc);
-
- if (dwc->usb_psy)
- power_supply_put(dwc->usb_psy);
}
#ifdef CONFIG_PM
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 1e561fd8b86e..ecfe2cc224f7 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1045,7 +1045,7 @@ struct dwc3_scratchpad_array {
* @role_sw: usb_role_switch handle
* @role_switch_default_mode: default operation mode of controller while
* usb role is USB_ROLE_NONE.
- * @usb_psy: pointer to power supply interface.
+ * @usb_psy_name: name of the usb power supply interface.
* @usb2_phy: pointer to USB2 PHY
* @usb3_phy: pointer to USB3 PHY
* @usb2_generic_phy: pointer to array of USB2 PHYs
@@ -1223,7 +1223,7 @@ struct dwc3 {
struct usb_role_switch *role_sw;
enum usb_dr_mode role_switch_default_mode;
- struct power_supply *usb_psy;
+ const char *usb_psy_name;
u32 fladj;
u32 ref_clk_per;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 89fc690fdf34..c89b5b5a64cf 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3049,20 +3049,29 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g,
static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA)
{
- struct dwc3 *dwc = gadget_to_dwc(g);
+ struct dwc3 *dwc = gadget_to_dwc(g);
+ struct power_supply *usb_psy;
union power_supply_propval val = {0};
int ret;
if (dwc->usb2_phy)
return usb_phy_set_power(dwc->usb2_phy, mA);
- if (!dwc->usb_psy)
+ if (!dwc->usb_psy_name)
return -EOPNOTSUPP;
- val.intval = 1000 * mA;
- ret = power_supply_set_property(dwc->usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val);
+ usb_psy = power_supply_get_by_name(dwc->usb_psy_name);
+ if (usb_psy) {
+ val.intval = 1000 * mA;
+ ret = power_supply_set_property(usb_psy, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT,
+ &val);
+ power_supply_put(usb_psy);
+ return ret;
+ }
- return ret;
+ dev_err(dwc->dev, "couldn't get usb power supply\n");
+
+ return -EOPNOTSUPP;
}
/**
--
2.45.2.993.g49e7a77208-goog