6.12.77-rc1 review
Subsystems (10)
Greg Kroah-Hartman
maintainerPATCH 118/265 LoongArch/orc: Use RCU in all users of __module_address().
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit f99d27d9feb755aee9350fc89f57814d7e1b4880 ]
__module_address() can be invoked within a RCU section, there is no requirement to have preemption disabled.
Replace the preempt_disable() section around __module_address() with RCU.
Stable-dep-of: 055c7e75190e ("LoongArch: Handle percpu handler address for ORC unwinder")
--- arch/loongarch/kernel/unwind_orc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
arch/loongarch/kernel/unwind_orc.c +1 -3
@@ -399,7 +399,7 @@ bool unwind_next_frame(struct unwind_state *state)return false;/* Don't let modules unload while we're reading their ORC data. */ -preempt_disable (); +guard (rcu)();if (is_entry_func (state->pc)) goto end;
@@ -514,14 +514,12 @@ bool unwind_next_frame(struct unwind_state *state)if (!__kernel_text_address (state->pc)) goto err; -preempt_enable ();return true; err: state->error = true; end: -preempt_enable (); state->stack_info.type =STACK_TYPE_UNKNOWN ;return false; }
Signature · 1 line
2.51.0
Re: [PATCH 6.12 118/265] LoongArch/orc: Use RCU in all users of __module_address().
Hi all,
Quoted 41 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit
f99d27d9feb755aee9350fc89f57814d7e1b4880]
__module_address()can be invoked within a RCU section, there is no requirement to have preemption disabled.Replace the
preempt_disable()section around__module_address()with RCU.Cc Huacai Chen <[email protected]>Cc WANG Xuerui <[email protected]>Signed-off-by Sebastian Andrzej Siewior <[email protected]>Signed-off-by Petr Pavlu <[email protected]>Stable-dep-of:
055c7e75190e("LoongArch: Handle percpu handler address for ORC unwinder")Signed-off-by Sasha Levin <[email protected]>--- arch/loongarch/kernel/unwind_orc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)arch/loongarch/kernel/unwind_orc.c +1
-1@@ -399,7 +399,7 @@ bool unwind_next_frame(struct unwind_state *state)return false;/* Don't let modules unload while we're reading their ORC data. */ -preempt_disable (); +guard (rcu)();if (is_entry_func (state->pc)) goto end;
arch/loongarch/kernel/unwind_orc.c bool unwind_next_frame(struct unwind_state *state) · line 518
Quoted 6 lines
arch/loongarch/kernel/unwind_orc.c +0
-1@@ -514,14 +514,12 @@ bool unwind_next_frame(struct unwind_state *state)if (!__kernel_text_address (state->pc)) goto err; -preempt_enable ();return true;
Looks like this is dependent on commit: 7d9dda6f628f ("module: Allow __module_address() to be called from RCU section."), so I feel pulling in this patch without the mentioned missing prerequisite is wrong. Can you please help review this ?
This is also part of a feature series in https://lore.kernel.org/all/[email protected]/
Thanks,
Harshit
Quoted 8 lines
arch/loongarch/kernel/unwind_orc.c +0
-1err: state->error = true; end: -preempt_enable (); state->stack_info.type =STACK_TYPE_UNKNOWN ;return false; }
Huacai Chen
maintainerRe: [PATCH 6.12 118/265] LoongArch/orc: Use RCU in all users of __module_address().
Quoted 58 lines · Harshit Mogalapalli
Hi all,
Quoted 41 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit
f99d27d9feb755aee9350fc89f57814d7e1b4880]
__module_address()can be invoked within a RCU section, there is no requirement to have preemption disabled.Replace the
preempt_disable()section around__module_address()with RCU.Cc Huacai Chen <[email protected]>Cc WANG Xuerui <[email protected]>Signed-off-by Sebastian Andrzej Siewior <[email protected]>Signed-off-by Petr Pavlu <[email protected]>Stable-dep-of:
055c7e75190e("LoongArch: Handle percpu handler address for ORC unwinder")Signed-off-by Sasha Levin <[email protected]>--- arch/loongarch/kernel/unwind_orc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)arch/loongarch/kernel/unwind_orc.c +1
-1@@ -399,7 +399,7 @@ bool unwind_next_frame(struct unwind_state *state)return false;/* Don't let modules unload while we're reading their ORC data. */ -preempt_disable (); +guard (rcu)();if (is_entry_func (state->pc)) goto end;arch/loongarch/kernel/unwind_orc.c bool unwind_next_frame(struct unwind_state *state) · line 518
Quoted 6 lines
arch/loongarch/kernel/unwind_orc.c +0
-1@@ -514,14 +514,12 @@ bool unwind_next_frame(struct unwind_state *state)if (!__kernel_text_address (state->pc)) goto err; -preempt_enable ();return true;Looks like this is dependent on commit:
7d9dda6f628f("module: Allow__module_address()to be called from RCU section."), so I feel pulling in this patch without the mentioned missing prerequisite is wrong. Can you please help review this ?
Quoted 2 lines
This is also part of a feature series in
https://lore.kernel.org/all/[email protected]/
Yes, I have also asked about this:
https://lore.kernel.org/stable/CAAhV-H7GxtWRZyAT=kedLEMu=C5wH--NUzRjwi3DKXzUq+QZjA@mail.gmail.com/
However, no answer and no action for this. I don't know what happened to Greg and Sasha. Recently, similar accidents happen again and again.
Huacai
Quoted 13 lines
Thanks,
HarshitQuoted 8 lines
arch/loongarch/kernel/unwind_orc.c +0
-1err: state->error = true; end: -preempt_enable (); state->stack_info.type =STACK_TYPE_UNKNOWN ;return false; }
Sasha Levin
maintainerRe: [PATCH 6.12 118/265] LoongArch/orc: Use RCU in all users of __module_address().
Quoted 4 lines · Huacai Chen
Yes, I have also asked about this:
https://lore.kernel.org/stable/CAAhV-H7GxtWRZyAT=kedLEMu=C5wH--NUzRjwi3DKXzUq+QZjA@mail.gmail.com/However, no answer and no action for this.
Sorry about the delay on this. You're right that the prerequisite commit 7d9dda6f628f ("module: Allow __module_address() to be called from RCU section") was missing.
I've reverted the entire LoongArch/orc series from the 6.12 pending queue:
- 8eeb34ae9d4c7 LoongArch: Handle percpu handler address for ORC unwinder
- 5d8e3b81aee2c LoongArch: Remove unnecessary checks for ORC unwinder
- 2e6949777d1db LoongArch/orc: Use RCU in all users of __module_address()
These will need to be re-applied along with the missing prerequisite.
-- Sasha
Greg Kroah-Hartman
maintainerPATCH 119/265 LoongArch: Remove unnecessary checks for ORC unwinder
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tiezhu Yang <[email protected]>
[ Upstream commit 4cd641a79e69270a062777f64a0dd330abb9044a ]
According to the following function definitions, __kernel_text_address() already checks __module_text_address(), so it should remove the check of __module_text_address() in bt_address() at least.
int __kernel_text_address(unsigned long addr)
{
if (kernel_text_address(addr))
return 1;
...
return 0;
}int kernel_text_address(unsigned long addr)
{
bool no_rcu;
int ret = 1;
...
if (is_module_text_address(addr))
goto out;
...
return ret;
}bool is_module_text_address(unsigned long addr)
{
guard(rcu)();
return __module_text_address(addr) != NULL;
}Furthermore, there are two checks of __kernel_text_address(), one is in bt_address() and the other is after calling bt_address(), it looks like redundant.
Handle the exception address first and then use __kernel_text_address() to validate the calculated address for exception or the normal address in bt_address(), then it can remove the check of __kernel_text_address() after calling bt_address().
Just remove unnecessary checks, no functional changes intended.
Stable-dep-of: 055c7e75190e ("LoongArch: Handle percpu handler address for ORC unwinder")
--- arch/loongarch/kernel/unwind_orc.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)
arch/loongarch/kernel/unwind_orc.c +5 -11
@@ -359,12 +359,6 @@ static inline unsigned long bt_address(unsigned long ra) {extern unsigned long eentry; -if (__kernel_text_address (ra)) -return ra; - -if (__module_text_address (ra)) -return ra; -if (ra >= eentry && ra < eentry +EXCCODE_INT_END *VECSIZE ) {unsigned long func;unsigned long type = (ra - eentry) /VECSIZE ;
@@ -382,10 +376,13 @@ static inline unsigned long bt_address(unsigned long ra)break ; } -return func + offset; + ra = func + offset; } -return ra; +if (__kernel_text_address (ra)) +return ra; + +return 0 ; }bool unwind_next_frame (struct unwind_state *state)
@@ -511,9 +508,6 @@ bool unwind_next_frame(struct unwind_state *state) goto err; } -if (!__kernel_text_address (state->pc)) - goto err; -return true; err:
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 120/265 LoongArch: Handle percpu handler address for ORC unwinder
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tiezhu Yang <[email protected]>
[ Upstream commit 055c7e75190e0be43037bd663a3f6aced194416e ]
After commit 4cd641a79e69 ("LoongArch: Remove unnecessary checks for ORC unwinder"), the system can not boot normally under some configs (such as enable KASAN), there are many error messages "cannot find unwind pc".
The kernel boots normally with the defconfig, so no problem found out at the first time. Here is one way to reproduce:
cd linux make mrproper defconfig -j"$(nproc)" scripts/config -e KASAN make olddefconfig all -j"$(nproc)" sudo make modules_install sudo make install sudo reboot
The address that can not unwind is not a valid kernel address which is between "pcpu_handlers[cpu]" and "pcpu_handlers[cpu] + vec_sz" due to the code of eentry was copied to the new area of pcpu_handlers[cpu] in setup_tlb_handler(), handle this special case to get the valid address to unwind normally.
--- arch/loongarch/include/asm/setup.h | 3 +++ arch/loongarch/kernel/unwind_orc.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+)
arch/loongarch/include/asm/setup.h +3 -0
@@ -7,6 +7,7 @@#define _LOONGARCH_SETUP_H#include <linux/types.h> +#include <linux/threads.h> #include <asm/sections.h> #include <uapi/asm/setup.h>
@@ -14,6 +15,8 @@extern unsigned long eentry;extern unsigned long tlbrentry; +extern unsigned long pcpu_handlers[NR_CPUS ]; +extern long exception_handlers[VECSIZE *128 /sizeof (long )];extern char init_command_line[COMMAND_LINE_SIZE ];extern void tlb_init (int cpu);extern void cpu_cache_init (void );
arch/loongarch/kernel/unwind_orc.c +16 -0
@@ -359,6 +359,22 @@ static inline unsigned long bt_address(unsigned long ra) {extern unsigned long eentry; +#if defined(CONFIG_NUMA ) && !defined(CONFIG_PREEMPT_RT ) +int cpu; +int vec_sz =sizeof (exception_handlers); + +for_each_possible_cpu (cpu) { +if (!pcpu_handlers[cpu]) +continue ; + +if (ra >= pcpu_handlers[cpu] && + ra < pcpu_handlers[cpu] + vec_sz) { + ra = ra + eentry - pcpu_handlers[cpu]; +break ; + } + } +#endif +if (ra >= eentry && ra < eentry +EXCCODE_INT_END *VECSIZE ) {unsigned long func;unsigned long type = (ra - eentry) /VECSIZE ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 121/265 LoongArch: Remove some extern variables in source files
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tiezhu Yang <[email protected]>
[ Upstream commit 0e6f596d6ac635e80bb265d587b2287ef8fa1cd6 ]
There are declarations of the variable "eentry", "pcpu_handlers[]" and "exception_handlers[]" in asm/setup.h, the source files already include this header file directly or indirectly, so no need to declare them in the source files, just remove the code.
--- arch/loongarch/kernel/unwind_orc.c | 2 -- arch/loongarch/kernel/unwind_prologue.c | 4 ---- arch/loongarch/mm/tlb.c | 1 - 3 files changed, 7 deletions(-)
arch/loongarch/kernel/unwind_orc.c +0 -2
@@ -357,8 +357,6 @@ static bool is_entry_func(unsigned long addr)static inline unsigned long bt_address (unsigned long ra) { -extern unsigned long eentry; -#if defined(CONFIG_NUMA ) && !defined(CONFIG_PREEMPT_RT )int cpu;int vec_sz =sizeof (exception_handlers);
arch/loongarch/kernel/unwind_prologue.c +0 -4
@@ -22,10 +22,6 @@ extern const int unwind_hint_lasx;extern const int unwind_hint_lbt;extern const int unwind_hint_ri;extern const int unwind_hint_watch; -extern unsigned long eentry; -#ifdef CONFIG_NUMA -extern unsigned long pcpu_handlers[NR_CPUS ]; -#endif static inline bool scan_handlers (unsigned long entry_offset) {
arch/loongarch/mm/tlb.c +0 -1
@@ -260,7 +260,6 @@ static void output_pgtable_bits_defines(void)#ifdef CONFIG_NUMA unsigned long pcpu_handlers[NR_CPUS ];#endif -extern long exception_handlers[VECSIZE *128 /sizeof (long )];static void setup_tlb_handler (int cpu) {
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 122/265 ALSA: hda/realtek: Add quirk for Gigabyte G5 KF5 (2023)
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Naim <[email protected]>
[ Upstream commit 405d59fdd2038a65790eaad8c1013d37a2af6561 ]
Fixes microphone detection when a headset is connected to the audio jack using the ALC256.
--- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)
sound/pci/hda/patch_realtek.c +1 -0
@@ -11296,6 +11296,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {SND_PCI_QUIRK (0x144d ,0xc886 ,"Samsung Galaxy Book3 Pro (NP964XFG)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ),SND_PCI_QUIRK (0x144d ,0xc1ca ,"Samsung Galaxy Book3 Pro 360 (NP960QFG)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ),SND_PCI_QUIRK (0x144d ,0xc1cc ,"Samsung Galaxy Book3 Ultra (NT960XFH)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ), +SND_PCI_QUIRK (0x1458 ,0x900e ,"Gigabyte G5 KF5 (2023)" ,ALC2XX_FIXUP_HEADSET_MIC ),SND_PCI_QUIRK (0x1458 ,0xfa53 ,"Gigabyte BXBT-2807" ,ALC283_FIXUP_HEADSET_MIC ),SND_PCI_QUIRK (0x1462 ,0xb120 ,"MSI Cubi MS-B120" ,ALC283_FIXUP_HEADSET_MIC ), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 123/265 ALSA: hda/realtek: Add quirk for Samsung Galaxy Book3 Pro 360 (NP965QFG)
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lewis Mason <[email protected]>
[ Upstream commit 3a6b7dc431aab90744e973254604855e654294ae ]
The Samsung Galaxy Book3 Pro 360 NP965QFG (subsystem ID 0x144d:0xc1cb) uses the same Realtek ALC298 codec and amplifier configuration as the NP960QFG (0x144d:0xc1ca). Apply the same ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS fixup to enable the internal speakers.
--- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)
sound/pci/hda/patch_realtek.c +1 -0
@@ -11295,6 +11295,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {SND_PCI_QUIRK (0x144d ,0xc872 ,"Samsung Galaxy Book2 Pro (NP950XEE)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_2_AMPS ),SND_PCI_QUIRK (0x144d ,0xc886 ,"Samsung Galaxy Book3 Pro (NP964XFG)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ),SND_PCI_QUIRK (0x144d ,0xc1ca ,"Samsung Galaxy Book3 Pro 360 (NP960QFG)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ), +SND_PCI_QUIRK (0x144d ,0xc1cb ,"Samsung Galaxy Book3 Pro 360 (NP965QFG)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ),SND_PCI_QUIRK (0x144d ,0xc1cc ,"Samsung Galaxy Book3 Ultra (NT960XFH)" ,ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS ),SND_PCI_QUIRK (0x1458 ,0x900e ,"Gigabyte G5 KF5 (2023)" ,ALC2XX_FIXUP_HEADSET_MIC ), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 124/265 ALSA: hda/conexant: Fix headphone jack handling on Acer Swift SF314
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Takashi Iwai <[email protected]>
[ Upstream commit 7bc0df86c2384bc1e2012a2c946f82305054da64 ]
Acer Swift SF314 (SSID 1025:136d) needs a bit of tweaks of the pin configurations for NID 0x16 and 0x19 to make the headphone / headset jack working. NID 0x17 can remain as is for the working speaker, and the built-in mic is supported via SOF.
--- sound/pci/hda/patch_conexant.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
sound/pci/hda/patch_conexant.c +10 -0
@@ -308,6 +308,7 @@ enum {CXT_PINCFG_SWS_JS201D ,CXT_PINCFG_TOP_SPEAKER ,CXT_FIXUP_HP_A_U , + CXT_FIXUP_ACER_SWIFT_HP, };/* for hda_fixup_thinkpad_acpi() */
@@ -1024,6 +1025,14 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_hp_a_u, }, + [CXT_FIXUP_ACER_SWIFT_HP] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl []) { + {0x16 ,0x0321403f },/* Headphone */ + {0x19 ,0x40f001f0 },/* Mic */ + { } + }, + }, };static const struct hda_quirk cxt5045_fixups[] = {
@@ -1073,6 +1082,7 @@ static const struct hda_quirk cxt5066_fixups[] = {SND_PCI_QUIRK (0x1025 ,0x0543 ,"Acer Aspire One 522" ,CXT_FIXUP_STEREO_DMIC ),SND_PCI_QUIRK (0x1025 ,0x054c ,"Acer Aspire 3830TG" ,CXT_FIXUP_ASPIRE_DMIC ),SND_PCI_QUIRK (0x1025 ,0x054f ,"Acer Aspire 4830T" ,CXT_FIXUP_ASPIRE_DMIC ), +SND_PCI_QUIRK (0x1025 ,0x136d ,"Acer Swift SF314" ,CXT_FIXUP_ACER_SWIFT_HP ),SND_PCI_QUIRK (0x103c ,0x8079 ,"HP EliteBook 840 G3" ,CXT_FIXUP_HP_DOCK ),SND_PCI_QUIRK (0x103c ,0x807C ,"HP EliteBook 820 G3" ,CXT_FIXUP_HP_DOCK ), SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK),
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 125/265 net: arcnet: com20020-pci: fix support for 2.5Mbit cards
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ethan Nelson-Moore <[email protected]>
[ Upstream commit c7d9be66b71af490446127c6ffcb66d6bb71b8b9 ]
Commit 8c14f9c70327 ("ARCNET: add com20020 PCI IDs with metadata") converted the com20020-pci driver to use a card info structure instead of a single flag mask in driver_data. However, it failed to take into account that in the original code, driver_data of 0 indicates a card with no special flags, not a card that should not have any card info structure. This introduced a null pointer dereference when cards with no flags were probed.
Commit bd6f1fd5d33d ("net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe()") then papered over this issue by rejecting cards with no driver_data instead of resolving the problem at its source.
Fix the original issue by introducing a new card info structure for 2.5Mbit cards that does not set any flags and using it if no driver_data is present.
--- drivers/net/arcnet/com20020-pci.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/net/arcnet/com20020-pci.c +15 -1
@@ -115,6 +115,8 @@ static const struct attribute_group com20020_state_group = { .attrs = com20020_state_attrs, }; +static struct com20020_pci_card_info card_info_2p5mbit; +static void com20020pci_remove (struct pci_dev *pdev); static int com20020pci_probe(struct pci_dev *pdev,
@@ -140,7 +142,7 @@ static int com20020pci_probe(struct pci_dev *pdev, ci = (struct com20020_pci_card_info *)id->driver_data;if (!ci) -return -EINVAL ; + ci = &card_info_2p5mbit; priv->ci = ci; mm = &ci->misc_map;
@@ -347,6 +349,18 @@ static struct com20020_pci_card_info card_info_5mbit = { .flags = ARC_IS_5MBIT, }; +static struct com20020_pci_card_info card_info_2p5mbit = { + .name ="ARC-PCI" , + .devcount =1 , + .chan_map_tbl = { + { + .bar =2 , + .offset =0x00 , + .size =0x08 , + }, + }, +}; +static struct com20020_pci_card_info card_info_sohard = { .name ="SOHARD SH ARC-PCI" , .devcount =1 ,
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 126/265 eventpoll: Fix integer overflow in ep_loop_check_proc()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jann Horn <[email protected]>
commit fdcfce93073d990ed4b71752e31ad1c1d6e9d58b upstream.
If a recursive call to ep_loop_check_proc() hits the result = INT_MAX, an integer overflow will occur in the calling ep_loop_check_proc() at result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1), breaking the recursion depth check.
Fix it by using a different placeholder value that can't lead to an overflow.
--- fs/eventpoll.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
fs/eventpoll.c +3 -2
@@ -2012,7 +2012,8 @@ static int ep_poll(struct eventpoll *ep,* @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * -* Return: depth of the subtree, or INT_MAX if we found a loop or went too deep. +* Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found +* a loop or went too deep. */ static int ep_loop_check_proc (struct eventpoll *ep,int depth) {
@@ -2031,7 +2032,7 @@ static int ep_loop_check_proc(struct evestruct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data;if (ep_tovisit == inserting_into || depth >EP_MAX_NESTS ) - result =INT_MAX ; + result =EP_MAX_NESTS +1 ;else result =max (result,ep_loop_check_proc (ep_tovisit, depth +1 ) +1 );if (result >EP_MAX_NESTS )
Greg Kroah-Hartman
maintainerPATCH 127/265 namespace: fix proc mount iteration
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
commit 4a403d7aa9074f527f064ef0806aaab38d14b07c upstream.
The m->index isn't updated when m->show() overflows and retains its value before the current mount causing a restart to start at the same value. If that happens in short order to due a quickly expanding mount table this would cause the same mount to be shown again and again.
Ensure that *pos always equals the mount id of the mount that was returned by start/next. On restart after overflow mnt_find_id_at(*pos) finds the exact mount. This should avoid duplicates, avoid skips and should handle concurrent modification just fine.
Cc: <[email protected]>
Fixed: 2eea9ce4310d8 ("mounts: keep list of mounts in an rbtree")
--- fs/namespace.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-)
fs/namespace.c +15 -5
@@ -1590,23 +1590,33 @@ static struct mount *mnt_find_id_at_revestatic void *m_start (struct seq_file *m,loff_t *pos) {struct proc_mounts *p = m->private; +struct mount *mnt;down_read (&namespace_sem); -return mnt_find_id_at (p->ns, *pos); + mnt =mnt_find_id_at (p->ns, *pos); +if (mnt) + *pos = mnt->mnt_id_unique; +return mnt; }static void *m_next (struct seq_file *m,void *v,loff_t *pos) { -struct mount *next =NULL , *mnt = v; +struct mount *mnt = v;struct rb_node *node =rb_next (&mnt->mnt_node); - ++*pos;if (node) { - next =node_to_mount (node); +struct mount *next =node_to_mount (node); *pos = next->mnt_id_unique; +return next; } -return next; + +/* +* No more mounts. Set pos past current mount's ID so that if +* iteration restarts, mnt_find_id_at() returns NULL. +*/ + *pos = mnt->mnt_id_unique +1 ; +return NULL ; }static void m_stop (struct seq_file *m,void *v)
Greg Kroah-Hartman
maintainerPATCH 128/265 media: dvb-core: fix wrong reinitialization of ringbuffer on reopen
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jens Axboe <[email protected]>
commit bfbc0b5b32a8f28ce284add619bf226716a59bc0 upstream.
dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty.
Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}.
The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions.
Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.
--- drivers/media/dvb-core/dmxdev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/media/dvb-core/dmxdev.c +3 -1
@@ -168,7 +168,9 @@ static int dvb_dvr_open(struct inode *inmutex_unlock (&dmxdev->mutex);return -ENOMEM ; } -dvb_ringbuffer_init (&dmxdev->dvr_buffer, mem,DVR_BUFFER_SIZE ); + dmxdev->dvr_buffer.data = mem; + dmxdev->dvr_buffer.size =DVR_BUFFER_SIZE ; +dvb_ringbuffer_reset (&dmxdev->dvr_buffer);if (dmxdev->may_do_mmap)dvb_vb2_init (&dmxdev->dvr_vb2_ctx,"dvr" , file->f_flags &O_NONBLOCK );
Greg Kroah-Hartman
maintainerPATCH 129/265 nfc: pn533: properly drop the usb interface reference on disconnect
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 12133a483dfa832241fbbf09321109a0ea8a520e upstream.
When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.
--- drivers/nfc/pn533/usb.c | 1 + 1 file changed, 1 insertion(+)
drivers/nfc/pn533/usb.c +1 -0
@@ -628,6 +628,7 @@ static void pn533_usb_disconnect(structusb_free_urb (phy->out_urb);usb_free_urb (phy->ack_urb);kfree (phy->ack_buffer); +usb_put_dev (phy->udev);nfc_info (&interface->dev,"NXP PN533 NFC device disconnected\n" ); }
Greg Kroah-Hartman
maintainerPATCH 130/265 net: usb: kaweth: validate USB endpoints
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 4b063c002ca759d1b299988ee23f564c9609c875 upstream.
The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
--- drivers/net/usb/kaweth.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
drivers/net/usb/kaweth.c +13 -0
@@ -883,6 +883,13 @@ static int kaweth_probe(const eth_addr_t bcast_addr = {0xFF ,0xFF ,0xFF ,0xFF ,0xFF ,0xFF };int result =0 ;int rv = -EIO ; +static const u8 bulk_ep_addr[] = { +1 |USB_DIR_IN , +2 |USB_DIR_OUT , +0 }; +static const u8 int_ep_addr[] = { +3 |USB_DIR_IN , +0 }; dev_dbg(dev, "Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -896,6 +903,12 @@ static int kaweth_probe( (int )udev->descriptor.bLength, (int)udev->descriptor.bDescriptorType); +if (!usb_check_bulk_endpoints (intf, bulk_ep_addr) || + !usb_check_int_endpoints (intf, int_ep_addr)) { +dev_err (dev,"couldn't find required endpoints\n" ); +return -ENODEV ; + } + netdev =alloc_etherdev (sizeof (*kaweth));if (!netdev)return -ENOMEM ;
Greg Kroah-Hartman
maintainerPATCH 131/265 net: usb: kalmia: validate USB endpoints
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit c58b6c29a4c9b8125e8ad3bca0637e00b71e2693 upstream.
The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
--- drivers/net/usb/kalmia.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/net/usb/kalmia.c +7 -0
@@ -132,11 +132,18 @@ kalmia_bind(struct usbnet *dev, struct u {int status;u8 ethernet_addr[ETH_ALEN ]; +static const u8 ep_addr[] = { +1 |USB_DIR_IN , +2 |USB_DIR_OUT , +0 };/* Don't bind to AT command interface */ if (intf->cur_altsetting->desc.bInterfaceClass !=USB_CLASS_VENDOR_SPEC )return -EINVAL ; +if (!usb_check_bulk_endpoints (intf, ep_addr)) +return -ENODEV ; + dev->in =usb_rcvbulkpipe (dev->udev,0x81 &USB_ENDPOINT_NUMBER_MASK ); dev->out =usb_sndbulkpipe (dev->udev,0x02 &USB_ENDPOINT_NUMBER_MASK ); dev->status =NULL ;
Greg Kroah-Hartman
maintainerPATCH 132/265 net: usb: pegasus: validate USB endpoints
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 11de1d3ae5565ed22ef1f89d73d8f2d00322c699 upstream.
The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.
--- drivers/net/usb/pegasus.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
drivers/net/usb/pegasus.c +12 -1
@@ -815,8 +815,19 @@ static void unlink_all_urbs(pegasus_t *pstatic int alloc_urbs (pegasus_t *pegasus) { +static const u8 bulk_ep_addr[] = { +1 |USB_DIR_IN , +2 |USB_DIR_OUT , +0 }; +static const u8 int_ep_addr[] = { +3 |USB_DIR_IN , +0 };int res = -ENOMEM ; +if (!usb_check_bulk_endpoints (pegasus->intf, bulk_ep_addr) || + !usb_check_int_endpoints (pegasus->intf, int_ep_addr)) +return -ENODEV ; + pegasus->rx_urb =usb_alloc_urb (0 ,GFP_KERNEL );if (!pegasus->rx_urb) {return res;
@@ -1171,6 +1182,7 @@ static int pegasus_probe(struct usb_inte pegasus =netdev_priv (net); pegasus->dev_index = dev_index; + pegasus->intf = intf; res =alloc_urbs (pegasus);if (res <0 ) {
@@ -1182,7 +1194,6 @@ static int pegasus_probe(struct usb_inteINIT_DELAYED_WORK (&pegasus->carrier_check, check_carrier); - pegasus->intf = intf; pegasus->usb = dev; pegasus->net = net;
Greg Kroah-Hartman
maintainerPATCH 133/265 can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 38a01c9700b0dcafe97dfa9dc7531bf4a245deff upstream.
When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer.
When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.
--- drivers/net/can/usb/ems_usb.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/can/usb/ems_usb.c +6 -1
@@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(s start =CPC_HEADER_SIZE ;while (msg_count) { +if (start +CPC_MSG_HEADER_LEN > urb->actual_length) { +netdev_err (netdev,"format error\n" ); +break ; + } + msg = (struct ems_cpc_msg *)&ibuf[start];switch (msg->type) {
@@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(s start +=CPC_MSG_HEADER_LEN + msg->length; msg_count--; -if (start > urb->transfer_buffer_length) { +if (start > urb->actual_length) {netdev_err (netdev,"format error\n" );break ; }
Greg Kroah-Hartman
maintainerPATCH 134/265 can: usb: f81604: correctly anchor the urb in the read bulk callback
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 952caa5da10bed22be09612433964f6877ba0dde upstream.
When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.
--- drivers/net/can/usb/f81604.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)
drivers/net/can/usb/f81604.c +13 -2
@@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(st {struct f81604_can_frame *frame = urb->transfer_buffer;struct net_device *netdev = urb->context; +struct f81604_port_priv *priv =netdev_priv (netdev);int ret;if (!netif_device_present (netdev))
@@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(stf81604_process_rx_packet (netdev, frame); resubmit_urb: +usb_anchor_urb (urb, &priv->urbs_anchor); ret =usb_submit_urb (urb,GFP_ATOMIC ); +if (!ret) +return ; +usb_unanchor_urb (urb); +if (ret == -ENODEV )netif_device_detach (netdev); -else if (ret) +else netdev_err (netdev,"%s: failed to resubmit read bulk urb: %pe\n" , __func__,ERR_PTR (ret));
@@ -646,10 +652,15 @@ static void f81604_read_int_callback(strf81604_handle_tx (priv, data); resubmit_urb: +usb_anchor_urb (urb, &priv->urbs_anchor); ret =usb_submit_urb (urb,GFP_ATOMIC ); +if (!ret) +return ; +usb_unanchor_urb (urb); +if (ret == -ENODEV )netif_device_detach (netdev); -else if (ret) +else netdev_err (netdev,"%s: failed to resubmit int urb: %pe\n" , __func__,ERR_PTR (ret)); }
Greg Kroah-Hartman
maintainerPATCH 135/265 can: ucan: Fix infinite loop from zero-length messages
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 1e446fd0582ad8be9f6dafb115fc2e7245f9bea7 upstream.
If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one.
This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.
--- drivers/net/can/usb/ucan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/can/usb/ucan.c +1 -1
@@ -749,7 +749,7 @@ static void ucan_read_bulk_callback(stru len =le16_to_cpu (m->len);/* check sanity (length of content) */ -if (urb->actual_length - pos < len) { +if ((len ==0 ) || (urb->actual_length - pos < len)) {netdev_warn (up->netdev,"invalid message (short; no data; l:%d)\n" , urb->actual_length);
Greg Kroah-Hartman
maintainerPATCH 136/265 can: usb: etas_es58x: correctly anchor the urb in the read bulk callback
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 5eaad4f768266f1f17e01232ffe2ef009f8129b7 upstream.
When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.
--- drivers/net/can/usb/etas_es58x/es58x_core.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/net/can/usb/etas_es58x/es58x_core.c +7 -1
@@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(str } resubmit_urb: +usb_anchor_urb (urb, &es58x_dev->rx_urbs); ret =usb_submit_urb (urb,GFP_ATOMIC ); +if (!ret) +return ; + +usb_unanchor_urb (urb); +if (ret == -ENODEV ) {for (i =0 ; i < es58x_dev->num_can_ch; i++)if (es58x_dev->netdev[i])netif_device_detach (es58x_dev->netdev[i]); - }else if (ret) + }else dev_err_ratelimited (dev,"Failed resubmitting read bulk urb: %pe\n" ,ERR_PTR (ret));
Greg Kroah-Hartman
maintainerPATCH 137/265 can: usb: f81604: handle short interrupt urb messages properly
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 7299b1b39a255f6092ce4ec0b65f66e9d6a357af upstream.
If an interrupt urb is received that is not the correct length, properly detect it and don't attempt to treat the data as valid.
--- drivers/net/can/usb/f81604.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/net/can/usb/f81604.c +6 -0
@@ -626,6 +626,12 @@ static void f81604_read_int_callback(strnetdev_info (netdev,"%s: Int URB aborted: %pe\n" , __func__,ERR_PTR (urb->status)); +if (urb->actual_length <sizeof (*data)) { +netdev_warn (netdev,"%s: short int URB: %u < %zu\n" , + __func__, urb->actual_length,sizeof (*data)); + goto resubmit_urb; + } +switch (urb->status) {case 0 :/* success */ break ;
Greg Kroah-Hartman
maintainerPATCH 138/265 can: usb: f81604: handle bulk write errors properly
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit 51f94780720fa90c424f67e3e9784cb8ef8190e5 upstream.
If a write urb fails then more needs to be done other than just logging the message, otherwise the transmission could be stalled. Properly increment the error counters and wake up the queues so that data will continue to flow.
--- drivers/net/can/usb/f81604.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-)
drivers/net/can/usb/f81604.c +21 -3
@@ -891,9 +891,27 @@ static void f81604_write_bulk_callback(sif (!netif_device_present (netdev))return ; -if (urb->status) -netdev_info (netdev,"%s: Tx URB error: %pe\n" , __func__, -ERR_PTR (urb->status)); +if (!urb->status) +return ; + +switch (urb->status) { +case -ENOENT : +case -ECONNRESET : +case -ESHUTDOWN : +return ; +default : +break ; + } + +if (net_ratelimit ()) +netdev_err (netdev,"%s: Tx URB error: %pe\n" , __func__, +ERR_PTR (urb->status)); + +can_free_echo_skb (netdev,0 ,NULL ); + netdev->stats.tx_dropped++; + netdev->stats.tx_errors++; + +netif_wake_queue (netdev); }static void f81604_clear_reg_work (struct work_struct *work)
Greg Kroah-Hartman
maintainerPATCH 139/265 HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Greg Kroah-Hartman <[email protected]>
commit ecfa6f34492c493a9a1dc2900f3edeb01c79946b upstream.
In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system.
Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.
--- drivers/hid/hid-cmedia.c | 2 +- drivers/hid/hid-creative-sb0540.c | 2 +- drivers/hid/hid-zydacron.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-)
drivers/hid/hid-cmedia.c +1 -1
@@ -99,7 +99,7 @@ static int cmhid_raw_event(struct hid_de {struct cmhid *cm =hid_get_drvdata (hid); -if (len !=CM6533_JD_RAWEV_LEN ) +if (len !=CM6533_JD_RAWEV_LEN || !(hid->claimed &HID_CLAIMED_INPUT )) goto out;if (memcmp (data+CM6533_JD_SFX_OFFSET , ji_sfx,sizeof (ji_sfx))) goto out;
drivers/hid/hid-creative-sb0540.c +1 -1
@@ -153,7 +153,7 @@ static int creative_sb0540_raw_event(stru64 code, main_code;int key; -if (len !=6 ) +if (len !=6 || !(hid->claimed &HID_CLAIMED_INPUT ))return 0 ;/* From daemons/hw_hiddev.c sb0540_rec() in lirc */
drivers/hid/hid-zydacron.c +1 -1
@@ -114,7 +114,7 @@ static int zc_raw_event(struct hid_devicunsigned key;unsigned short index; -if (report->id == data[0 ]) { +if (report->id == data[0 ] && (hdev->claimed &HID_CLAIMED_INPUT )) {/* break keys */ for (index =0 ; index <4 ; index++) {
Greg Kroah-Hartman
maintainerPATCH 140/265 x86/efi: defer freeing of boot services memory
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mike Rapoport (Microsoft) <[email protected]>
commit a4b0bf6a40f3c107c67a24fbc614510ef5719980 upstream.
efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late().
There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area().
More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete.
Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM.
If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages.
Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map.
Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency.
More robust approach is to only defer freeing of the EFI boot services memory.
Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.
--- arch/x86/include/asm/efi.h | 2 - arch/x86/platform/efi/efi.c | 2 - arch/x86/platform/efi/quirks.c | 55 ++++++++++++++++++++++++++++++++++-- drivers/firmware/efi/mokvar-table.c | 2 - 4 files changed, 55 insertions(+), 6 deletions(-)
arch/x86/include/asm/efi.h +1 -1
@@ -138,7 +138,7 @@ extern void __init efi_apply_memmap_quirextern int __init efi_reuse_config (u64 tables,int nr_tables);extern void efi_delete_dummy_variable (void );extern void efi_crash_gracefully_on_page_fault (unsigned long phys_addr); -extern void efi_free_boot_services (void ); +extern void efi_unmap_boot_services (void );void arch_efi_call_virt_setup (void );void arch_efi_call_virt_teardown (void );
arch/x86/platform/efi/efi.c +1 -1
@@ -858,7 +858,7 @@ static void __init __efi_enter_virtual_m }efi_check_for_embedded_firmwares (); -efi_free_boot_services (); +efi_unmap_boot_services ();if (!efi_is_mixed ())efi_native_runtime_setup ();
arch/x86/platform/efi/quirks.c +52 -3
89 lines not on this page · raw message
drivers/firmware/efi/mokvar-table.c +1 -1
@@ -85,7 +85,7 @@ static struct kobject *mokvar_kobj;* as an alternative to ordinary EFI variables, due to platform-dependent * limitations. The memory occupied by this table is marked as reserved. * -* This routine must be called before efi_free_boot_services() in order +* This routine must be called before efi_unmap_boot_services() in order * to guarantee that it can mark the table as reserved. * * Implicit inputs:
Greg Kroah-Hartman
maintainerPATCH 141/265 platform/x86: dell-wmi-sysman: Dont hex dump plaintext password data
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thorsten Blum <[email protected]>
commit d1a196e0a6dcddd03748468a0e9e3100790fc85c upstream.
set_new_password() hex dumps the entire buffer, which contains plaintext password data, including current and new passwords. Remove the hex dump to avoid leaking credentials.
--- drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c | 1 - 1 file changed, 1 deletion(-)
drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c +0 -1
@@ -93,7 +93,6 @@ int set_new_password(const char *passworif (ret <0 ) goto out; -print_hex_dump_bytes ("set new password data: " ,DUMP_PREFIX_NONE , buffer, buffer_size); ret =call_password_interface (wmi_priv.password_attr_wdev, buffer, buffer_size);/* on success copy the new password to current password */ if (!ret)
Greg Kroah-Hartman
maintainerPATCH 142/265 platform/x86: dell-wmi: Add audio/mic mute key codes
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kurt Borja <[email protected]>
commit 26a7601471f62b95d56a81c3a8ccb551b5a6630f upstream.
Add audio/mic mute key codes found in Alienware m18 r1 AMD.
--- drivers/platform/x86/dell/dell-wmi-base.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/platform/x86/dell/dell-wmi-base.c +6 -0
@@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wstatic const struct key_entry dell_wmi_keymap_type_0000[] = { {KE_IGNORE ,0x003a , {KEY_CAPSLOCK } }, +/* Audio mute toggle */ + {KE_KEY ,0x0109 , {KEY_MUTE } }, + +/* Mic mute toggle */ + {KE_KEY ,0x0150 , {KEY_MICMUTE } }, +/* Meta key lock */ {KE_IGNORE ,0xe000 , {KEY_RIGHTMETA } },
Greg Kroah-Hartman
maintainerPATCH 143/265 ALSA: usb-audio: Use correct version for UAC3 header validation
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jun Seo <[email protected]>
commit 54f9d645a5453d0bfece0c465d34aaf072ea99fa upstream.
The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields.
The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.
--- sound/usb/validate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
sound/usb/validate.c +1 -1
@@ -281,7 +281,7 @@ static const struct usb_desc_validator a/* UAC_VERSION_2, UAC2_SAMPLE_RATE_CONVERTER: not implemented yet */ /* UAC3 */ - FIXED(UAC_VERSION_2, UAC_HEADER, struct uac3_ac_header_descriptor), + FIXED(UAC_VERSION_3, UAC_HEADER, struct uac3_ac_header_descriptor),FIXED (UAC_VERSION_3 ,UAC_INPUT_TERMINAL , struct uac3_input_terminal_descriptor), FIXED(UAC_VERSION_3, UAC_OUTPUT_TERMINAL,
Greg Kroah-Hartman
maintainerPATCH 144/265 wifi: radiotap: reject radiotap with unknown bits
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
commit c854758abe0b8d86f9c43dc060ff56a0ee5b31e0 upstream.
The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value.
Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.
--- net/wireless/radiotap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/wireless/radiotap.c +2 -2
@@ -239,14 +239,14 @@ int ieee80211_radiotap_iterator_next(default :if (!iterator->current_namespace || iterator->_arg_index >= iterator->current_namespace->n_bits) { -if (iterator->current_namespace == &radiotap_ns) -return -ENOENT ; align =0 ; }else { align = iterator->current_namespace->align_size[iterator->_arg_index].align; size = iterator->current_namespace->align_size[iterator->_arg_index].size; }if (!align) { +if (iterator->current_namespace == &radiotap_ns) +return -ENOENT ;/* skip all subsequent data */ iterator->_arg = iterator->_next_ns_data;/* give up on this namespace */
Greg Kroah-Hartman
maintainerPATCH 145/265 wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Daniil Dulov <[email protected]>
commit 767d23ade706d5fa51c36168e92a9c5533c351a1 upstream.
There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller:
BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220 Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326 CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: events cfg80211_rfkill_block_work Call Trace: <TASK> dump_stack_lvl+0x116/0x1f0 print_report+0xcd/0x630 kasan_report+0xe0/0x110 cfg80211_shutdown_all_interfaces+0x213/0x220 cfg80211_rfkill_block_work+0x1e/0x30 process_one_work+0x9cf/0x1b70 worker_thread+0x6c8/0xf10 kthread+0x3c5/0x780 ret_from_fork+0x56d/0x700 ret_from_fork_asm+0x1a/0x30 </TASK>
The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister().
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
--- net/wireless/core.c | 1 + 1 file changed, 1 insertion(+)
net/wireless/core.c +1 -0
@@ -1174,6 +1174,7 @@ void wiphy_unregister(struct wiphy *wiph/* this has nothing to do now but make sure it's gone */ cancel_work_sync (&rdev->wiphy_work); +cancel_work_sync (&rdev->rfkill_block);cancel_work_sync (&rdev->conn_work);flush_work (&rdev->event_work);cancel_delayed_work_sync (&rdev->dfs_update_channels_wk);
Greg Kroah-Hartman
maintainerPATCH 146/265 wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ariel Silver <[email protected]>
commit 162d331d833dc73a3e905a24c44dd33732af1fc5 upstream.
link_id is taken from the ML Reconfiguration element (control & 0x000f), so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS
(15) elements, so index 15 is out-of-bounds. Skip subelements with link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds write.
--- net/mac80211/mlme.c | 3 +++ 1 file changed, 3 insertions(+)
net/mac80211/mlme.c +3 -0
@@ -6256,6 +6256,9 @@ static void ieee80211_ml_reconfiguration control =le16_to_cpu (prof->control); link_id = control &IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID ; +if (link_id >=IEEE80211_MLD_MAX_NUM_LINKS ) +continue ; + removed_links |=BIT (link_id);/* the MAC address should not be included, but handle it */
Greg Kroah-Hartman
maintainerPATCH 147/265 wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vahagn Vardanian <[email protected]>
commit 017c1792525064a723971f0216e6ef86a8c7af11 upstream.
In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check:
ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
...
pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value);The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference.
A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required.
Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim:
BUG: kernel NULL pointer dereference, address: 0000000000000000 Oops: Oops: 0000 [#1] SMP NOPTI RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211] CR2: 0000000000000000
Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code.
The bug has been present since v3.13 (released 2014-01-19).
--- net/mac80211/mesh.c | 3 +++ 1 file changed, 3 insertions(+)
net/mac80211/mesh.c +3 -0
@@ -1631,6 +1631,9 @@ static void mesh_rx_csa_frame(struct ieeif (!mesh_matches_local (sdata, elems)) goto free; +if (!elems->mesh_chansw_params_ie) + goto free; + ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;if (!--ifmsh->chsw_ttl) fwd_csa = false;
Greg Kroah-Hartman
maintainerPATCH 148/265 IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jason Gunthorpe <[email protected]>
commit 117942ca43e2e3c3d121faae530989931b7f67e1 upstream.
Fix a user triggerable leak on the system call failure path.
--- drivers/infiniband/hw/mthca/mthca_provider.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/infiniband/hw/mthca/mthca_provider.c +3 -2
@@ -428,6 +428,8 @@ static int mthca_create_srq(struct ib_srif (context &&ib_copy_to_udata (udata, &srq->srqn,sizeof (__u32))) {mthca_free_srq (to_mdev (ibsrq->device), srq); +mthca_unmap_user_db (to_mdev (ibsrq->device), &context->uar, + context->db_tab, ucmd.db_index);return -EFAULT ; }
@@ -436,6 +438,7 @@ static int mthca_create_srq(struct ib_srstatic int mthca_destroy_srq (struct ib_srq *srq,struct ib_udata *udata) { +mthca_free_srq (to_mdev (srq->device),to_msrq (srq));if (udata) {struct mthca_ucontext *context = rdma_udata_to_drv_context(
@@ -446,8 +449,6 @@ static int mthca_destroy_srq(struct ib_smthca_unmap_user_db (to_mdev (srq->device), &context->uar, context->db_tab,to_msrq (srq)->db_index); } - -mthca_free_srq (to_mdev (srq->device),to_msrq (srq));return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 149/265 RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jason Gunthorpe <[email protected]>
commit 74586c6da9ea222a61c98394f2fc0a604748438c upstream.
struct irdma_create_ah_resp { // 8 bytes, no padding
__u32 ah_id; // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx)
__u8 rsvd[4]; // offset 4 - NEVER SET <- LEAK};
rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata().
The reserved members of the structure were not zeroed.
--- drivers/infiniband/hw/irdma/verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/irdma/verbs.c +1 -1
@@ -4589,7 +4589,7 @@ static int irdma_create_user_ah(struct i#define IRDMA_CREATE_AH_MIN_RESP_LEN offsetofend(struct irdma_create_ah_resp, rsvd) struct irdma_ah *ah = container_of(ibah, struct irdma_ah, ibah);struct irdma_device *iwdev =to_iwdev (ibah->pd->device); -struct irdma_create_ah_resp uresp; +struct irdma_create_ah_resp uresp = {};struct irdma_ah *parent_ah;int err;
Greg Kroah-Hartman
maintainerPATCH 150/265 net/sched: ets: fix divide by zero in the offload path
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Davide Caratti <[email protected]>
commit e35626f610f3d2b7953ccddf6a77453da22b3a9e upstream.
Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat:
Oops: divide error: 0000 [#1] SMP PTI CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G E 6.19.0-virtme #45 PREEMPT(full) Tainted: [E]=UNSIGNED_MODULE Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Call Trace: <TASK> ets_qdisc_change+0x870/0xf40 [sch_ets] qdisc_create+0x12b/0x540 tc_modify_qdisc+0x6d7/0xbd0 rtnetlink_rcv_msg+0x168/0x6b0 netlink_rcv_skb+0x5c/0x110 netlink_unicast+0x1d6/0x2b0 netlink_sendmsg+0x22e/0x470 ____sys_sendmsg+0x38a/0x3c0 ___sys_sendmsg+0x99/0xe0 __sys_sendmsg+0x8a/0xf0 do_syscall_64+0x111/0xf80 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f440b81c77e Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980 </TASK> Modules linked in: sch_ets(E) netdevsim(E) ---[ end trace 0000000000000000 ]--- RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets] Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000 FS: 00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]---
Fix this using 64-bit integers for 'q_sum' and 'q_psum'.
--- net/sched/sch_ets.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)
net/sched/sch_ets.c +8 -4
@@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdstruct ets_sched *q =qdisc_priv (sch);struct tc_ets_qopt_offload qopt;unsigned int w_psum_prev =0 ; -unsigned int q_psum =0 ; -unsigned int q_sum =0 ;unsigned int quantum;unsigned int w_psum;unsigned int weight;unsigned int i; +u64 q_psum =0 ; +u64 q_sum =0 ;if (!tc_can_offload (dev) || !dev->netdev_ops->ndo_setup_tc)return ;
@@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdfor (i =0 ; i < q->nbands; i++) { quantum = q->classes[i].quantum; - q_psum += quantum; - w_psum = quantum ? q_psum *100 / q_sum :0 ; +if (quantum) { + q_psum += quantum; + w_psum =div64_u64 (q_psum *100 , q_sum); + }else { + w_psum =0 ; + } weight = w_psum - w_psum_prev; w_psum_prev = w_psum;
Greg Kroah-Hartman
maintainerPATCH 151/265 nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit().
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
commit 1cb968a2013ffa8112d52ebe605009ea1c6a582c upstream.
syzbot reported memory leak of struct cred. [0]
nfsd_nl_threads_set_doit() passes get_current_cred() to nfsd_svc(), but put_cred() is not called after that.
The cred is finally passed down to _svc_xprt_create(), which calls get_cred() with the cred for struct svc_xprt.
The ownership of the refcount by get_current_cred() is not transferred to anywhere and is just leaked.
nfsd_svc() is also called from write_threads(), but it does not bump file->f_cred there.
nfsd_nl_threads_set_doit() is called from sendmsg() and current->cred does not go away.
Let's use current_cred() in nfsd_nl_threads_set_doit().
[0]:
BUG: memory leak
unreferenced object 0xffff888108b89480 (size 184):
comm "syz-executor", pid 5994, jiffies 4294943386
hex dump (first 32 bytes):
01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace (crc 369454a7):
kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline]
slab_post_alloc_hook mm/slub.c:4958 [inline]
slab_alloc_node mm/slub.c:5263 [inline]
kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270
prepare_creds+0x22/0x600 kernel/cred.c:185
copy_creds+0x44/0x290 kernel/cred.c:286
copy_process+0x7a7/0x2870 kernel/fork.c:2086
kernel_clone+0xac/0x6e0 kernel/fork.c:2651
__do_sys_clone+0x7f/0xb0 kernel/fork.c:2792
do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94
entry_SYSCALL_64_after_hwframe+0x77/0x7f--- fs/nfsd/nfsctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/nfsd/nfsctl.c +1 -1
@@ -1724,7 +1724,7 @@ int nfsd_nl_threads_set_doit(struct sk_b scope =nla_data (attr); } - ret =nfsd_svc (nrpools, nthreads, net,get_current_cred (), scope); + ret =nfsd_svc (nrpools, nthreads, net,current_cred (), scope);if (ret >0 ) ret =0 ; out_unlock:
Greg Kroah-Hartman
maintainerPATCH 152/265 tracing: Fix WARN_ON in tracing_buffers_mmap_close
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qing Wang <[email protected]>
commit e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e upstream.
When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON.
Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork.
Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback.
--- include/linux/ring_buffer.h | 1 + kernel/trace/ring_buffer.c | 21 +++++++++++++++++++++ kernel/trace/trace.c | 13 +++++++++++++ 3 files changed, 35 insertions(+)
include/linux/ring_buffer.h +1 -0
@@ -244,6 +244,7 @@ int trace_rb_cpu_prepare(unsigned int cpint ring_buffer_map (struct trace_buffer *buffer,int cpu,struct vm_area_struct *vma); +void ring_buffer_map_dup (struct trace_buffer *buffer,int cpu);int ring_buffer_unmap (struct trace_buffer *buffer,int cpu);int ring_buffer_map_get_reader (struct trace_buffer *buffer,int cpu);#endif /* _LINUX_RING_BUFFER_H */
kernel/trace/ring_buffer.c +21 -0
@@ -7154,6 +7154,27 @@ unlock:return err; } +/* +* This is called when a VMA is duplicated (e.g., on fork()) to increment +* the user_mapped counter without remapping pages. +*/ +void ring_buffer_map_dup (struct trace_buffer *buffer,int cpu) +{ +struct ring_buffer_per_cpu *cpu_buffer; + +if (WARN_ON (!cpumask_test_cpu (cpu, buffer->cpumask))) +return ; + + cpu_buffer = buffer->buffers[cpu]; + +guard (mutex)(&cpu_buffer->mapping_lock); + +if (cpu_buffer->user_mapped) +__rb_inc_dec_mapped (cpu_buffer, true); +else +WARN (1 ,"Unexpected buffer stat, it should be mapped" ); +} +int ring_buffer_unmap (struct trace_buffer *buffer,int cpu) {struct ring_buffer_per_cpu *cpu_buffer;
kernel/trace/trace.c +13 -0
@@ -8274,6 +8274,18 @@ static inline int get_snapshot_map(strucstatic inline void put_snapshot_map (struct trace_array *tr) { }#endif +/* +* This is called when a VMA is duplicated (e.g., on fork()) to increment +* the user_mapped counter without remapping pages. +*/ +static void tracing_buffers_mmap_open (struct vm_area_struct *vma) +{ +struct ftrace_buffer_info *info = vma->vm_file->private_data; +struct trace_iterator *iter = &info->iter; + +ring_buffer_map_dup (iter->array_buffer->buffer, iter->cpu_file); +} +static void tracing_buffers_mmap_close (struct vm_area_struct *vma) {struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8293,6 +8305,7 @@ static int tracing_buffers_may_split(str }static const struct vm_operations_struct tracing_buffers_vmops = { + .open = tracing_buffers_mmap_open, .close = tracing_buffers_mmap_close, .may_split = tracing_buffers_may_split, };
Greg Kroah-Hartman
maintainerPATCH 153/265 scsi: target: Fix recursive locking in __configfs_open_file()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Prithvi Tambewagh <[email protected]>
commit 14d4ac19d1895397532eec407433c5d74d9da53b upstream.
In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace:
down_read
__configfs_open_file
do_dentry_open
vfs_open
do_open
path_openat
do_filp_open
file_open_name
filp_open
target_core_item_dbroot_store
flush_write_buffer
configfs_write_iter
target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows:
db_root: not a directory: /sys/kernel/config/target/dbroot
indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking.
Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.
--- drivers/target/target_core_configfs.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-)
drivers/target/target_core_configfs.c +6 -9
@@ -108,8 +108,8 @@ static ssize_t target_core_item_dbroot_s const char *page, size_t count) { ssize_t read_bytes; -struct file *fp;ssize_t r = -EINVAL ; +struct path path = {};mutex_lock (&target_devices_lock);if (target_devices) {
@@ -131,17 +131,14 @@ static ssize_t target_core_item_dbroot_s db_root_stage[read_bytes -1 ] ='\0' ;/* validate new db root before accepting it */ - fp =filp_open (db_root_stage,O_RDONLY ,0 ); -if (IS_ERR (fp)) { + r =kern_path (db_root_stage,LOOKUP_FOLLOW |LOOKUP_DIRECTORY , &path); +if (r) {pr_err ("db_root: cannot open: %s\n" , db_root_stage); +if (r == -ENOTDIR ) +pr_err ("db_root: not a directory: %s\n" , db_root_stage); goto unlock; } -if (!S_ISDIR (file_inode (fp)->i_mode)) { -filp_close (fp,NULL ); -pr_err ("db_root: not a directory: %s\n" , db_root_stage); - goto unlock; - } -filp_close (fp,NULL ); +path_put (&path);strncpy (db_root, db_root_stage, read_bytes);pr_debug ("Target_Core_ConfigFS: db_root set to %s\n" , db_root);
Greg Kroah-Hartman
maintainerPATCH 154/265 Squashfs: check metadata block offset is within range
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phillip Lougher <[email protected]>
commit fdb24a820a5832ec4532273282cbd4f22c291a0d upstream.
Syzkaller reports a "general protection fault in squashfs_copy_data"
This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset.
This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access.
The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.
--- fs/squashfs/cache.c | 3 +++ 1 file changed, 3 insertions(+)
fs/squashfs/cache.c +3 -0
@@ -340,6 +340,9 @@ int squashfs_read_metadata(struct super_if (unlikely (length <0 ))return -EIO ; +if (unlikely (*offset <0 || *offset >=SQUASHFS_METADATA_SIZE )) +return -EIO ; +while (length) { entry =squashfs_cache_get (sb, msblk->block_cache, *block,0 );if (entry->error) {
Greg Kroah-Hartman
maintainerPATCH 155/265 drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lars Ellenberg <[email protected]>
commit ab140365fb62c0bdab22b2f516aff563b2559e3b upstream.
Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing.
If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error.
The rest of the code now assumed that this request has references for the relevant activity log extents.
The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case.
Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put().
Fix:
Do not crash the kernel for a condition that is harmless during normal
operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n".
And do not try to be smart and "guess" whether something will work, then be surprised when it does not.
Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock().
A latter call for the same request will then resume from where we left off.
--- drivers/block/drbd/drbd_actlog.c | 53 ++++++++++++++++--------------------- drivers/block/drbd/drbd_interval.h | 5 ++- 2 files changed, 27 insertions(+), 31 deletions(-)
drivers/block/drbd/drbd_actlog.c +23 -30
@@ -483,38 +483,20 @@ void drbd_al_begin_io(struct drbd_deviceint drbd_al_begin_io_nonblock (struct drbd_device *device,struct drbd_interval *i) { -struct lru_cache *al = device->act_log;/* for bios crossing activity log extent boundaries, * we may need to activate two extents in one go */ unsigned first = i->sector >> (AL_EXTENT_SHIFT -9 );unsigned last = i->size ==0 ? first : (i->sector + (i->size >>9 ) -1 ) >> (AL_EXTENT_SHIFT -9 ); -unsigned nr_al_extents; -unsigned available_update_slots;unsigned enr; -D_ASSERT (device, first <= last); - - nr_al_extents =1 + last - first;/* worst case: all touched extends are cold. */ - available_update_slots =min (al->nr_elements - al->used, - al->max_pending_changes - al->pending_changes); - -/* We want all necessary updates for a given request within the same transaction -* We could first check how many updates are *actually* needed, -* and use that instead of the worst-case nr_al_extents */ -if (available_update_slots < nr_al_extents) { -/* Too many activity log extents are currently "hot". -* -* If we have accumulated pending changes already, -* we made progress. -* -* If we cannot get even a single pending change through, -* stop the fast path until we made some progress, -* or requests to "cold" extents could be starved. */ -if (!al->pending_changes) -__set_bit (__LC_STARVING, &device->act_log->flags); -return -ENOBUFS ; +if (i->partially_in_al_next_enr) { +D_ASSERT (device, first < i->partially_in_al_next_enr); +D_ASSERT (device, last >= i->partially_in_al_next_enr); + first = i->partially_in_al_next_enr; } +D_ASSERT (device, first <= last); +/* Is resync active in this area? */ for (enr = first; enr <= last; enr++) {struct lc_element *tmp;
@@ -529,14 +511,21 @@ int drbd_al_begin_io_nonblock(struct drb } } -/* Checkout the refcounts. -* Given that we checked for available elements and update slots above, -* this has to be successful. */ +/* Try to checkout the refcounts. */ for (enr = first; enr <= last; enr++) {struct lc_element *al_ext; al_ext =lc_get_cumulative (device->act_log, enr); -if (!al_ext) -drbd_info (device,"LOGIC BUG for enr=%u\n" , enr); + +if (!al_ext) { +/* Did not work. We may have exhausted the possible +* changes per transaction. Or raced with someone +* "locking" it against changes. +* Remember where to continue from. +*/ +if (enr > first) + i->partially_in_al_next_enr = enr; +return -ENOBUFS ; + } }return 0 ; }
@@ -556,7 +545,11 @@ void drbd_al_complete_io(struct drbd_devfor (enr = first; enr <= last; enr++) { extent =lc_find (device->act_log, enr); -if (!extent) { +/* Yes, this masks a bug elsewhere. However, during normal +* operation this is harmless, so no need to crash the kernel +* by the BUG_ON(refcount == 0) in lc_put(). +*/ +if (!extent || extent->refcnt ==0 ) {drbd_err (device,"al_complete_io() called on inactive extent %u\n" , enr);continue ; }
drivers/block/drbd/drbd_interval.h +4 -1
@@ -8,12 +8,15 @@struct drbd_interval {struct rb_node rb;sector_t sector;/* start sector of the interval */ -unsigned int size;/* size in bytes */ sector_t end;/* highest interval end in subtree */ +unsigned int size;/* size in bytes */ unsigned int local:1 /* local or remote request? */ ;unsigned int waiting:1 ;/* someone is waiting for completion */ unsigned int completed:1 ;/* this has been completed already; * ignore for conflict detection */ + +/* to resume a partially successful drbd_al_begin_io_nonblock(); */ +unsigned int partially_in_al_next_enr; };static inline void drbd_clear_interval (struct drbd_interval *i)
Greg Kroah-Hartman
maintainerPATCH 156/265 drbd: fix null-pointer dereference on local read error
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christoph Böhmwalder <[email protected]>
commit 0d195d3b205ca90db30d70d09d7bb6909aac178f upstream.
In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to __req_mod() with a NULL peer_device:
__req_mod(req, what, NULL, &m);
The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this NULL peer_device to drbd_set_out_of_sync(), which dereferences it, causing a null-pointer dereference.
Fix this by obtaining the peer_device via first_peer_device(device), matching how drbd_req_destroy() handles the same situation.
--- drivers/block/drbd/drbd_req.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/block/drbd/drbd_req.c +2 -1
@@ -621,7 +621,8 @@ int __req_mod(struct drbd_request *req,break ;case READ_COMPLETED_WITH_ERROR : -drbd_set_out_of_sync (peer_device, req->i.sector, req->i.size); +drbd_set_out_of_sync (first_peer_device (device), + req->i.sector, req->i.size);drbd_report_io_error (device, req);__drbd_chk_io_error (device,DRBD_READ_ERROR ); fallthrough;
Greg Kroah-Hartman
maintainerPATCH 157/265 smb: client: fix cifs_pick_channel when channels are equally loaded
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Henrique Carvalho <[email protected]>
commit 663c28469d3274d6456f206a6671c91493d85ff1 upstream.
cifs_pick_channel uses (start % chan_count) when channels are equally loaded, but that can return a channel that failed the eligibility checks.
Drop the fallback and return the scan-selected channel instead. If none is eligible, keep the existing behavior of using the primary channel.
--- fs/smb/client/transport.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-)
fs/smb/client/transport.c +10 -11
@@ -1026,16 +1026,21 @@ cifs_cancelled_callback(struct mid_q_ent }/* -* Return a channel (master if none) of @ses that can be used to send -* regular requests. +* cifs_pick_channel - pick an eligible channel for network operations * -* If we are currently binding a new channel (negprot/sess.setup), -* return the new incomplete channel. +* @ses: session reference +* +* Select an eligible channel (not terminating and not marked as needing +* reconnect), preferring the least loaded one. If no eligible channel is +* found, fall back to the primary channel (index 0). +* +* Return: TCP_Server_Info pointer for the chosen channel, or NULL if @ses is +* NULL. */ struct TCP_Server_Info *cifs_pick_channel (struct cifs_ses *ses) {uint index =0 ; -unsigned int min_in_flight =UINT_MAX , max_in_flight =0 ; +unsigned int min_in_flight =UINT_MAX ;struct TCP_Server_Info *server =NULL ;int i, start, cur;
@@ -1065,14 +1070,8 @@ struct TCP_Server_Info *cifs_pick_channe min_in_flight = server->in_flight; index = cur; } -if (server->in_flight > max_in_flight) - max_in_flight = server->in_flight; } -/* if all channels are equally loaded, fall back to round-robin */ -if (min_in_flight == max_in_flight) - index = (uint )start % ses->chan_count; - server = ses->chans[index].server;spin_unlock (&ses->chan_lock);
Greg Kroah-Hartman
maintainerPATCH 158/265 smb: client: fix broken multichannel with krb5+signing
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Paulo Alcantara <[email protected]>
commit d9d1e319b39ea685ede59319002d567c159d23c3 upstream.
When mounting a share with 'multichannel,max_channels=n,sec=krb5i', the client was duplicating signing key for all secondary channels, thus making the server fail all commands sent from secondary channels due to bad signatures.
Every channel has its own signing key, so when establishing a new channel with krb5 auth, make sure to use the new session key as the derived key to generate channel's signing key in SMB2_auth_kerberos().
Repro:
$ mount.cifs //srv/share /mnt -o multichannel,max_channels=4,sec=krb5i $ sleep 5 $ umount /mnt $ dmesg ... CIFS: VFS: sign fail cmd 0x5 message id 0x2 CIFS: VFS: \\srv SMB signature verification returned error = -13 CIFS: VFS: sign fail cmd 0x5 message id 0x2 CIFS: VFS: \\srv SMB signature verification returned error = -13 CIFS: VFS: sign fail cmd 0x4 message id 0x2 CIFS: VFS: \\srv SMB signature verification returned error = -13
--- fs/smb/client/smb2pdu.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-)
fs/smb/client/smb2pdu.c +10 -12
@@ -1666,19 +1666,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data is_binding = (ses->ses_status ==SES_GOOD );spin_unlock (&ses->ses_lock); -/* keep session key if binding */ -if (!is_binding) { -kfree_sensitive (ses->auth_key.response); - ses->auth_key.response =kmemdup (msg->data, msg->sesskey_len, -GFP_KERNEL ); -if (!ses->auth_key.response) { -cifs_dbg (VFS ,"Kerberos can't allocate (%u bytes) memory\n" , - msg->sesskey_len); - rc = -ENOMEM ; - goto out_put_spnego_key; - } - ses->auth_key.len = msg->sesskey_len; +kfree_sensitive (ses->auth_key.response); + ses->auth_key.response =kmemdup (msg->data, + msg->sesskey_len, +GFP_KERNEL ); +if (!ses->auth_key.response) { +cifs_dbg (VFS ,"%s: can't allocate (%u bytes) memory\n" , + __func__, msg->sesskey_len); + rc = -ENOMEM ; + goto out_put_spnego_key; } + ses->auth_key.len = msg->sesskey_len; sess_data->iov[1 ].iov_base = msg->data + msg->sesskey_len; sess_data->iov[1 ].iov_len = msg->secblob_len;
Greg Kroah-Hartman
maintainerPATCH 159/265 smb: client: Dont log plaintext credentials in cifs_set_cifscreds
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thorsten Blum <[email protected]>
commit 2f37dc436d4e61ff7ae0b0353cf91b8c10396e4d upstream.
When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.
--- fs/smb/client/connect.c | 1 - 1 file changed, 1 deletion(-)
fs/smb/client/connect.c +0 -1
@@ -2197,7 +2197,6 @@ cifs_set_cifscreds(struct smb3_fs_contex/* find first : in payload */ payload = upayload->data; delim =strnchr (payload, upayload->datalen,':' ); -cifs_dbg (FYI ,"payload=%s\n" , payload);if (!delim) {cifs_dbg (FYI ,"Unable to find ':' in payload (datalen=%d)\n" , upayload->datalen);
Greg Kroah-Hartman
maintainerPATCH 160/265 scsi: core: Fix refcount leak for tagset_refcnt
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Junxiao Bi <[email protected]>
commit 1ac22c8eae81366101597d48360718dff9b9d980 upstream.
This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace:
[130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured
PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid"
#0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4
#1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f
#2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0
#3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f
#4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b
#5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6
#9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef
--- drivers/scsi/scsi_scan.c | 1 + 1 file changed, 1 insertion(+)
drivers/scsi/scsi_scan.c +1 -0
@@ -354,6 +354,7 @@ static struct scsi_device *scsi_alloc_sd* since we use this queue depth most of times. */ if (scsi_realloc_sdev_budget_map (sdev, depth)) { +kref_put (&sdev->host->tagset_refcnt, scsi_mq_free_tags);put_device (&starget->dev);kfree (sdev); goto out;
Greg Kroah-Hartman
maintainerPATCH 161/265 selftests: mptcp: more stable simult_flows tests
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Paolo Abeni <[email protected]>
commit 8c09412e584d9bcc0e71d758ec1008d1c8d1a326 upstream.
By default, the netem qdisc can keep up to 1000 packets under its belly to deal with the configured rate and delay. The simult flows test-case simulates very low speed links, to avoid problems due to slow CPUs and the TCP stack tend to transmit at a slightly higher rate than the (virtual) link constraints.
All the above causes a relatively large amount of packets being enqueued in the netem qdiscs - the longer the transfer, the longer the queue - producing increasingly high TCP RTT samples and consequently increasingly larger receive buffer size due to DRS.
When the receive buffer size becomes considerably larger than the needed size, the tests results can flake, i.e. because minimal inaccuracy in the pacing rate can lead to a single subflow usage towards the end of the connection for a considerable amount of data.
Address the issue explicitly setting netem limits suitable for the configured link speeds and unflake all the affected tests.
--- tools/testing/selftests/net/mptcp/simult_flows.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
tools/testing/selftests/net/mptcp/simult_flows.sh +7 -4
@@ -226,10 +226,13 @@ run_test() for dev in ns2eth1 ns2eth2; do tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 done - tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 - tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # keep the queued pkts number low, or the RTT estimator will see + # increasing latency over time. + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50 # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%)
Greg Kroah-Hartman
maintainerPATCH 162/265 selftests: mptcp: join: check removing signal+subflow endp
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
commit 1777f349ff41b62dfe27454b69c27b0bc99ffca5 upstream.
This validates the previous commit: endpoints with both the signal and subflow flags should always be marked as used even if it was not possible to create new subflows due to the MPTCP PM limits.
For this test, an extra endpoint is created with both the signal and the subflow flags, and limits are set not to create extra subflows. In this case, an ADD_ADDR is sent, but no subflows are created. Still, the local endpoint is marked as used, and no warning is fired when removing the endpoint, after having sent a RM_ADDR.
The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID.
--- tools/testing/selftests/net/mptcp/mptcp_join.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+)
tools/testing/selftests/net/mptcp/mptcp_join.sh +13 -0
@@ -2384,6 +2384,19 @@ remove_tests() chk_rst_nr 0 0 fi + # signal+subflow with limits, remove + if reset "remove signal+subflow with limits"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow + pm_nl_set_limits $ns2 0 0 + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 + fi + # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3
Matthieu Baerts
maintainerRe: [PATCH 6.12 162/265] selftests: mptcp: join: check removing signal+subflow endp
Hi Greg,
Quoted 11 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
commit
1777f349ff41b62dfe27454b69c27b0bc99ffca5upstream.This validates the previous commit: endpoints with both the signal and subflow flags should always be marked as used even if it was not possible to create new subflows due to the MPTCP PM limits.
FYI, this patch adds a new subtest in the MPTCP selftests to validate that the upstream parent commit -- 579a752464a6 ("mptcp: pm: in-kernel:
always mark signal+subflow endp as used") -- fixes a warning. Except that this commit had a conflict and is currently not in v6.12. Sasha sent a version without the conflict (BTW, thank you for that!):
https://lore.kernel.org/[email protected]
I guess that's probably fine like that because the issue exposed by this new test is not new, and it will be fixed by the missing patch soon I suppose. Probably no need to modify this RC, and the fix can wait the next version, but I prefer to send this message just in case people hit the issue.
Cheers,
Matt
Signature · 1 line
Sponsored by the NGI0 Core fund.
Greg Kroah-Hartman
maintainerRe: [PATCH 6.12 162/265] selftests: mptcp: join: check removing signal+subflow endp
Quoted 21 lines · Matthieu Baerts
Hi Greg,
Quoted 11 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
commit
1777f349ff41b62dfe27454b69c27b0bc99ffca5upstream.This validates the previous commit: endpoints with both the signal and subflow flags should always be marked as used even if it was not possible to create new subflows due to the MPTCP PM limits.
FYI, this patch adds a new subtest in the MPTCP selftests to validate that the upstream parent commit --
579a752464a6("mptcp: pm: in-kernel:
always mark signal+subflow endp as used") -- fixes a warning. Except that this commit had a conflict and is currently not in v6.12. Sasha sent a version without the conflict (BTW, thank you for that!):
Quoted 7 lines
https://lore.kernel.org/[email protected]
I guess that's probably fine like that because the issue exposed by this new test is not new, and it will be fixed by the missing patch soon I suppose. Probably no need to modify this RC, and the fix can wait the next version, but I prefer to send this message just in case people hit the issue.
Thanks for the info, I'll queue up that other patch for the next round of stable releases, sorry I didn't get to it at this point in time.
greg k-h
Matthieu Baerts
maintainerRe: [PATCH 6.12 162/265] selftests: mptcp: join: check removing signal+subflow endp
Quoted 24 lines · Greg Kroah-Hartman
Quoted 23 lines · Matthieu Baerts
Hi Greg,
Quoted 11 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
commit
1777f349ff41b62dfe27454b69c27b0bc99ffca5upstream.This validates the previous commit: endpoints with both the signal and subflow flags should always be marked as used even if it was not possible to create new subflows due to the MPTCP PM limits.
FYI, this patch adds a new subtest in the MPTCP selftests to validate that the upstream parent commit --
579a752464a6("mptcp: pm: in-kernel:
always mark signal+subflow endp as used") -- fixes a warning. Except that this commit had a conflict and is currently not in v6.12. Sasha sent a version without the conflict (BTW, thank you for that!):
Quoted 8 lines
Quoted 5 lines
I guess that's probably fine like that because the issue exposed by this new test is not new, and it will be fixed by the missing patch soon I suppose. Probably no need to modify this RC, and the fix can wait the next version, but I prefer to send this message just in case people hit the issue.
Thanks for the info, I'll queue up that other patch for the next round of stable releases
Thank you!
Quoted 1 line
sorry I didn't get to it at this point in time.
No need to apologise, I understand, no hurry :)
Cheers,
Matt
Signature · 1 line
Sponsored by the NGI0 Core fund.
Greg Kroah-Hartman
maintainerPATCH 163/265 xattr: switch to CLASS(fd)
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Al Viro <[email protected]>
commit a71874379ec8c6e788a61d71b3ad014a8d9a5c08 upstream.
--- fs/xattr.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-)
fs/xattr.c +14 -21
@@ -697,9 +697,9 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, consint error;CLASS (fd, f)(fd); -if (!fd_file (f)) -return -EBADF ; +if (fd_empty (f)) +return -EBADF ;audit_file (fd_file (f)); error =setxattr_copy (name, &ctx);if (error)
@@ -809,16 +809,13 @@ SYSCALL_DEFINE4(lgetxattr, const char __ SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { -struct fd f =fdget (fd); -ssize_t error = -EBADF ; +CLASS (fd, f)(fd); -if (!fd_file (f)) -return error; +if (fd_empty (f)) +return -EBADF ;audit_file (fd_file (f)); - error =getxattr (file_mnt_idmap (fd_file (f)),fd_file (f)->f_path.dentry, +return getxattr (file_mnt_idmap (fd_file (f)),fd_file (f)->f_path.dentry, name, value, size); -fdput (f); -return error; }/*
@@ -885,15 +882,12 @@ SYSCALL_DEFINE3(llistxattr, const char _ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { -struct fd f =fdget (fd); -ssize_t error = -EBADF ; +CLASS (fd, f)(fd); -if (!fd_file (f)) -return error; +if (fd_empty (f)) +return -EBADF ;audit_file (fd_file (f)); - error =listxattr (fd_file (f)->f_path.dentry, list, size); -fdput (f); -return error; +return listxattr (fd_file (f)->f_path.dentry, list, size); }/*
@@ -950,12 +944,12 @@ SYSCALL_DEFINE2(lremovexattr, const char SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { -struct fd f =fdget (fd); +CLASS (fd, f)(fd);char kname[XATTR_NAME_MAX +1 ]; -int error = -EBADF ; +int error; -if (!fd_file (f)) -return error; +if (fd_empty (f)) +return -EBADF ;audit_file (fd_file (f)); error =strncpy_from_user (kname, name,sizeof (kname));
@@ -970,7 +964,6 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, c fd_file(f)->f_path.dentry, kname);mnt_drop_write_file (fd_file (f)); } -fdput (f);return error; }
Greg Kroah-Hartman
maintainerPATCH 164/265 ARM: clean up the memset64() C wrapper
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thomas Weißschuh <[email protected]>
commit b52343d1cb47bb27ca32a3f4952cc2fd3cd165bf upstream.
The current logic to split the 64-bit argument into its 32-bit halves is byte-order specific and a bit clunky. Use a union instead which is easier to read and works in all cases.
GCC still generates the same machine code.
While at it, rename the arguments of the __memset64() prototype to actually reflect their semantics.
--- arch/arm/include/asm/string.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)
arch/arm/include/asm/string.h +9 -5
@@ -39,13 +39,17 @@ static inline void *memset32(uint32_t *p }#define __HAVE_ARCH_MEMSET64 -extern void *__memset64 (uint64_t *,uint32_t low,__kernel_size_t ,uint32_t hi); +extern void *__memset64 (uint64_t *,uint32_t first,__kernel_size_t ,uint32_t second);static inline void *memset64 (uint64_t *p,uint64_t v,__kernel_size_t n) { -if (IS_ENABLED (CONFIG_CPU_LITTLE_ENDIAN )) -return __memset64 (p, v, n *8 , v >>32 ); -else -return __memset64 (p, v >>32 , n *8 , v); +union { +uint64_t val; +struct { +uint32_t first, second; + }; + } word = { .val = v }; + +return __memset64 (p, word.first, n *8 , word.second); }/*
Greg Kroah-Hartman
maintainerPATCH 165/265 net: stmmac: dwmac-loongson: Set clk_csr_i to 100-150MHz
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Huacai Chen <[email protected]>
commit e1aa5ef892fb4fa9014a25e87b64b97347919d37 upstream.
Current clk_csr_i setting of Loongson STMMAC (including LS7A1000/2000 and LS2K1000/2000/3000) are copy & paste from other drivers. In fact, Loongson STMMAC use 125MHz clocks and need 62 freq division to within 2.5MHz, meeting most PHY MDC requirement. So fix by setting clk_csr_i to 100-150MHz, otherwise some PHYs may link fail.
--- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +1 -1
@@ -86,7 +86,7 @@ static void loongson_default_data(struct/* Get bus_id, this can be overwritten later */ plat->bus_id =pci_dev_id (pdev); - plat->clk_csr =2 ;/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ + plat->clk_csr =1 ;/* clk_csr_i = 100-150MHz & MDC = clk_csr_i/62 */ plat->has_gmac =1 ; plat->force_sf_dma_mode =1 ;
Greg Kroah-Hartman
maintainerPATCH 166/265 btrfs: always fallback to buffered write if the inode requires checksum
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qu Wenruo <[email protected]>
commit 968f19c5b1b7d5595423b0ac0020cc18dfed8cb5 upstream.
[BUG]
It is a long known bug that VM image on btrfs can lead to data csum mismatch, if the qemu is using direct-io for the image (this is commonly known as cache mode 'none').
[CAUSE]
Inside the VM, if the fs is EXT4 or XFS, or even NTFS from Windows, the fs is allowed to dirty/modify the folio even if the folio is under writeback (as long as the address space doesn't have AS_STABLE_WRITES flag inherited from the block device).
This is a valid optimization to improve the concurrency, and since these filesystems have no extra checksum on data, the content change is not a problem at all.
But the final write into the image file is handled by btrfs, which needs the content not to be modified during writeback, or the checksum will not match the data (checksum is calculated before submitting the bio).
So EXT4/XFS/NTRFS assume they can modify the folio under writeback, but btrfs requires no modification, this leads to the false csum mismatch.
This is only a controlled example, there are even cases where multi-thread programs can submit a direct IO write, then another thread modifies the direct IO buffer for whatever reason.
For such cases, btrfs has no sane way to detect such cases and leads to false data csum mismatch.
[FIX]
I have considered the following ideas to solve the problem:
- Make direct IO to always skip data checksum
This not only requires a new incompatible flag, as it breaks the current per-inode NODATASUM flag.
But also requires extra handling for no csum found cases.
And this also reduces our checksum protection.
- Let hardware handle all the checksum
AKA, just nodatasum mount option.
That requires trust for hardware (which is not that trustful in a lot of cases), and it's not generic at all.
- Always fallback to buffered write if the inode requires checksum This was suggested by Christoph, and is the solution utilized by this patch.
The cost is obvious, the extra buffer copying into page cache, thus it reduces the performance.
But at least it's still user configurable, if the end user still wants the zero-copy performance, just set NODATASUM flag for the inode (which is a common practice for VM images on btrfs).
Since we cannot trust user space programs to keep the buffer consistent during direct IO, we have no choice but always falling back to buffered IO. At least by this, we avoid the more deadly false data checksum mismatch error.
--- fs/btrfs/direct-io.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
fs/btrfs/direct-io.c +16 -0
@@ -868,6 +868,22 @@ relock:btrfs_inode_unlock (BTRFS_I (inode), ilock_flags); goto buffered; } +/* +* We can't control the folios being passed in, applications can write +* to them while a direct IO write is in progress. This means the +* content might change after we calculated the data checksum. +* Therefore we can end up storing a checksum that doesn't match the +* persisted data. +* +* To be extra safe and avoid false data checksum mismatch, if the +* inode requires data checksum, just fallback to buffered IO. +* For buffered IO we have full control of page cache and can ensure +* no one is modifying the content during writeback. +*/ +if (!(BTRFS_I (inode)->flags &BTRFS_INODE_NODATASUM )) { +btrfs_inode_unlock (BTRFS_I (inode), ilock_flags); + goto buffered; + }/* * The iov_iter can be mapped to the same file range we are writing to.
Greg Kroah-Hartman
maintainerPATCH 167/265 ACPI: APEI: GHES: Disable KASAN instrumentation when compile testing with clang < 18
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nathan Chancellor <[email protected]>
[ Upstream commit b584bfbd7ec417f257f651cc00a90c66e31dfbf1 ]
After a recent innocuous change to drivers/acpi/apei/ghes.c, building ARCH=arm64 allmodconfig with clang-17 or older (which has both CONFIG_KASAN=y and CONFIG_WERROR=y) fails with:
drivers/acpi/apei/ghes.c:902:13: error: stack frame size (2768) exceeds limit (2048) in 'ghes_do_proc' [-Werror,-Wframe-larger-than]
902 | static void ghes_do_proc(struct ghes *ghes,
| ^
A KASAN pass that removes unneeded stack instrumentation, enabled by default in clang-18 [1], drastically improves stack usage in this case.
To avoid the warning in the common allmodconfig case when it can break the build, disable KASAN for ghes.o when compile testing with clang-17 and older. Disabling KASAN outright may hide legitimate runtime issues, so live with the warning in that case; the user can either increase the frame warning limit or disable -Werror, which they should probably do when debugging with KASAN anyways.
--- drivers/acpi/apei/Makefile | 4 ++++ 1 file changed, 4 insertions(+)
drivers/acpi/apei/Makefile +4 -0
@@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ACPI_APEI) += apei.o obj-$(CONFIG_ACPI_APEI_GHES) += ghes.o +# clang versions prior to 18 may blow out the stack with KASAN +ifeq ($(CONFIG_COMPILE_TEST)_$(CONFIG_CC_IS_CLANG)_$(call clang-min-version, 180000),y_y_) +KASAN_SANITIZE_ghes.o := n +endif obj-$(CONFIG_ACPI_APEI_EINJ) += einj.o einj-y := einj-core.o einj-$(CONFIG_ACPI_APEI_EINJ_CXL) += einj-cxl.o
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 168/265 nvme: fix admin queue leak on controller reset
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ming Lei <[email protected]>
[ Upstream commit b84bb7bd913d8ca2f976ee6faf4a174f91c02b8d ]
When nvme_alloc_admin_tag_set() is called during a controller reset, a previous admin queue may still exist. Release it properly before allocating a new one to avoid orphaning the old queue.
This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").
--- drivers/nvme/host/core.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +7 -0
@@ -4609,6 +4609,13 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,if (ret)return ret; +/* +* If a previous admin queue exists (e.g., from before a reset), +* put it now before allocating a new one to avoid orphaning it. +*/ +if (ctrl->admin_q) +blk_put_queue (ctrl->admin_q); + ctrl->admin_q =blk_mq_alloc_queue (set, &lim,NULL );if (IS_ERR (ctrl->admin_q)) { ret =PTR_ERR (ctrl->admin_q);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 169/265 hwmon: (aht10) Add support for dht20
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Akhilesh Patil <[email protected]>
[ Upstream commit 3eaf1b631506e8de2cb37c278d5bc042521e82c1 ]
Add support for dht20 temperature and humidity sensor from Aosong. Modify aht10 driver to handle different init command for dht20 sensor by adding init_cmd entry in the driver data. dht20 sensor is compatible with aht10 hwmon driver with this change.
Tested on TI am62x SK board with dht20 sensor connected at i2c-2 port.
Stable-dep-of: b7497b5a99f5 ("hwmon: (aht10) Fix initialization commands for AHT20")
--- Documentation/hwmon/aht10.rst | 10 +++++++++- drivers/hwmon/Kconfig | 6 +++--- drivers/hwmon/aht10.c | 19 ++++++++++++++++--- 3 files changed, 28 insertions(+), 7 deletions(-)
Documentation/hwmon/aht10.rst +9 -1
@@ -20,6 +20,14 @@ Supported chips: English: http://www.aosong.com/userfiles/files/media/Data%20Sheet%20AHT20.pdf + * Aosong DHT20 + + Prefix: 'dht20' + + Addresses scanned: None + + Datasheet: https://www.digikey.co.nz/en/htmldatasheets/production/9184855/0/0/1/101020932 + Author: Johannes Cornelis Draaijer <[email protected]>
@@ -33,7 +41,7 @@ The address of this i2c device may only be 0x38 Special Features ---------------- -AHT20 has additional CRC8 support which is sent as the last byte of the sensor +AHT20, DHT20 has additional CRC8 support which is sent as the last byte of the sensor values. Usage Notes
drivers/hwmon/Kconfig +3 -3
@@ -245,12 +245,12 @@ config SENSORS_ADT7475 will be called adt7475. config SENSORS_AHT10 - tristate "Aosong AHT10, AHT20" + tristate "Aosong AHT10, AHT20, DHT20" depends on I2C select CRC8 help - If you say yes here, you get support for the Aosong AHT10 and AHT20 - temperature and humidity sensors + If you say yes here, you get support for the Aosong AHT10, AHT20 and + DHT20 temperature and humidity sensors This driver can also be built as a module. If so, the module will be called aht10.
drivers/hwmon/aht10.c +16 -3
@@ -37,6 +37,8 @@#define AHT10_CMD_MEAS 0b10101100#define AHT10_CMD_RST 0b10111010 +#define DHT20_CMD_INIT 0x71 +/* * Flags in the answer byte/command */
@@ -48,11 +50,12 @@#define AHT10_MAX_POLL_INTERVAL_LEN 30 -enum aht10_variant { aht10, aht20 }; +enum aht10_variant { aht10, aht20, dht20};static const struct i2c_device_id aht10_id[] = { {"aht10" , aht10 }, {"aht20" , aht20 }, + {"dht20" , dht20 }, { }, };MODULE_DEVICE_TABLE (i2c, aht10_id);
@@ -77,6 +80,7 @@ MODULE_DEVICE_TABLE(i2c, aht10_id);* AHT10/AHT20 * @crc8: crc8 support flag * @meas_size: measurements data size +* @init_cmd: Initialization command */ struct aht10_data {
@@ -92,6 +96,7 @@ struct aht10_data {int humidity;bool crc8;unsigned int meas_size; +u8 init_cmd; };/**
@@ -101,13 +106,13 @@ struct aht10_data {*/ static int aht10_init (struct aht10_data *data) { -const u8 cmd_init[] = {AHT10_CMD_INIT ,AHT10_CAL_ENABLED |AHT10_MODE_CYC , +const u8 cmd_init[] = {data->init_cmd,AHT10_CAL_ENABLED |AHT10_MODE_CYC ,0x00 };int res;u8 status;struct i2c_client *client = data->client; - res =i2c_master_send (client, cmd_init,3 ); + res =i2c_master_send (client, cmd_init,sizeof (cmd_init));if (res <0 )return res;
@@ -352,9 +357,17 @@ static int aht10_probe(struct i2c_client *client) data->meas_size =AHT20_MEAS_SIZE ; data->crc8 = true;crc8_populate_msb (crc8_table,AHT20_CRC8_POLY ); + data->init_cmd =AHT10_CMD_INIT ; +break ; +case dht20: + data->meas_size =AHT20_MEAS_SIZE ; + data->crc8 = true; +crc8_populate_msb (crc8_table,AHT20_CRC8_POLY ); + data->init_cmd =DHT20_CMD_INIT ;break ;default : data->meas_size =AHT10_MEAS_SIZE ; + data->init_cmd =AHT10_CMD_INIT ;break ; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 170/265 hwmon: (aht10) Fix initialization commands for AHT20
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hao Yu <[email protected]>
[ Upstream commit b7497b5a99f54ab8dcda5b14a308385b2fb03d8d ]
According to the AHT20 datasheet (updated to V1.0 after the 2023.09 version), the initialization command for AHT20 is 0b10111110 (0xBE). The previous sequence (0xE1) used in earlier versions is no longer compatible with newer AHT20 sensors. Update the initialization command to ensure the sensor is properly initialized.
While at it, use binary notation for DHT20_CMD_INIT to match the notation used in the datasheet.
--- drivers/hwmon/aht10.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/hwmon/aht10.c +4 -2
@@ -37,7 +37,9 @@#define AHT10_CMD_MEAS 0b10101100#define AHT10_CMD_RST 0b10111010 -#define DHT20_CMD_INIT 0x71 +#define AHT20_CMD_INIT 0b10111110 + +#define DHT20_CMD_INIT 0b01110001/* * Flags in the answer byte/command
@@ -357,7 +359,7 @@ static int aht10_probe(struct i2c_client *client) data->meas_size =AHT20_MEAS_SIZE ; data->crc8 = true;crc8_populate_msb (crc8_table,AHT20_CRC8_POLY ); - data->init_cmd =AHT10_CMD_INIT ; + data->init_cmd =AHT20_CMD_INIT ;break ;case dht20: data->meas_size =AHT20_MEAS_SIZE ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 171/265 pinctrl: equilibrium: rename irq_chip function callbacks
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Eckert <[email protected]>
[ Upstream commit 1f96b84835eafb3e6f366dc3a66c0e69504cec9d ]
Renaming of the irq_chip callback functions to improve clarity.
Stable-dep-of: 3e00b1b332e5 ("pinctrl: equilibrium: fix warning trace on load")
--- drivers/pinctrl/pinctrl-equilibrium.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)
drivers/pinctrl/pinctrl-equilibrium.c +12 -12
@@ -22,7 +22,7 @@#define PIN_NAME_LEN 10#define PAD_REG_OFF 0x100 -static void eqbr_gpio_disable_irq (struct irq_data *d) +static void eqbr_irq_mask (struct irq_data *d) {struct gpio_chip *gc =irq_data_get_irq_chip_data (d);struct eqbr_gpio_ctrl *gctrl =gpiochip_get_data (gc);
@@ -35,7 +35,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d)gpiochip_disable_irq (gc, offset); } -static void eqbr_gpio_enable_irq (struct irq_data *d) +static void eqbr_irq_unmask (struct irq_data *d) {struct gpio_chip *gc =irq_data_get_irq_chip_data (d);struct eqbr_gpio_ctrl *gctrl =gpiochip_get_data (gc);
@@ -49,7 +49,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d)raw_spin_unlock_irqrestore (&gctrl->lock, flags); } -static void eqbr_gpio_ack_irq (struct irq_data *d) +static void eqbr_irq_ack (struct irq_data *d) {struct gpio_chip *gc =irq_data_get_irq_chip_data (d);struct eqbr_gpio_ctrl *gctrl =gpiochip_get_data (gc);
@@ -61,10 +61,10 @@ static void eqbr_gpio_ack_irq(struct irq_data *d)raw_spin_unlock_irqrestore (&gctrl->lock, flags); } -static void eqbr_gpio_mask_ack_irq (struct irq_data *d) +static void eqbr_irq_mask_ack (struct irq_data *d) { -eqbr_gpio_disable_irq (d); -eqbr_gpio_ack_irq (d); +eqbr_irq_mask (d); +eqbr_irq_ack (d); } static inline void eqbr_cfg_bit(void __iomem *addr,
@@ -91,7 +91,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type,return 0 ; } -static int eqbr_gpio_set_irq_type (struct irq_data *d,unsigned int type) +static int eqbr_irq_set_type (struct irq_data *d,unsigned int type) {struct gpio_chip *gc =irq_data_get_irq_chip_data (d);struct eqbr_gpio_ctrl *gctrl =gpiochip_get_data (gc);
@@ -165,11 +165,11 @@ static void eqbr_irq_handler(struct irq_desc *desc)static const struct irq_chip eqbr_irq_chip = { .name ="gpio_irq" , - .irq_mask = eqbr_gpio_disable_irq, - .irq_unmask = eqbr_gpio_enable_irq, - .irq_ack = eqbr_gpio_ack_irq, - .irq_mask_ack = eqbr_gpio_mask_ack_irq, - .irq_set_type = eqbr_gpio_set_irq_type, + .irq_ack = eqbr_irq_ack, + .irq_mask = eqbr_irq_mask, + .irq_mask_ack = eqbr_irq_mask_ack, + .irq_unmask = eqbr_irq_unmask, + .irq_set_type = eqbr_irq_set_type, .flags =IRQCHIP_IMMUTABLE ,GPIOCHIP_IRQ_RESOURCE_HELPERS , };
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 172/265 pinctrl: equilibrium: fix warning trace on load
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Eckert <[email protected]>
[ Upstream commit 3e00b1b332e54ba50cca6691f628b9c06574024f ]
The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also called in the callback function 'eqbr_irq_mask_ack()'. This is done to avoid source code duplication. The problem, is that in the function 'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()'
This generates the following warning trace in the log for every gpio on load.
[ 6.088111] ------------[ cut here ]------------ [ 6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50 [ 6.097847] Modules linked in: [ 6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W 6.12.59+ #0 [ 6.097847] Tainted: [W]=WARN [ 6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50 [ 6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 [ 6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046 [ 6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008 [ 6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0 [ 6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000 [ 6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514 [ 6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000 [ 6.097847] FS: 0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000 [ 6.097847] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0 [ 6.097847] Call Trace: [ 6.097847] <TASK> [ 6.097847] ? eqbr_irq_mask+0x63/0x70 [ 6.097847] ? no_action+0x10/0x10 [ 6.097847] eqbr_irq_mask_ack+0x11/0x60
In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the interrupt is not disabled here.
To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()' function. Implement instead this directly without disabling the interrupts.
--- drivers/pinctrl/pinctrl-equilibrium.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/pinctrl/pinctrl-equilibrium.c +9 -2
@@ -63,8 +63,15 @@ static void eqbr_irq_ack(struct irq_data *d)static void eqbr_irq_mask_ack (struct irq_data *d) { -eqbr_irq_mask (d); -eqbr_irq_ack (d); +struct gpio_chip *gc =irq_data_get_irq_chip_data (d); +struct eqbr_gpio_ctrl *gctrl =gpiochip_get_data (gc); +unsigned int offset =irqd_to_hwirq (d); +unsigned long flags; + +raw_spin_lock_irqsave (&gctrl->lock, flags); +writel (BIT (offset), gctrl->membase +GPIO_IRNENCLR ); +writel (BIT (offset), gctrl->membase +GPIO_IRNCR ); +raw_spin_unlock_irqrestore (&gctrl->lock, flags); } static inline void eqbr_cfg_bit(void __iomem *addr,
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 173/265 platform/x86: thinkpad_acpi: Fix errors reading battery thresholds
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jonathan Teh <[email protected]>
[ Upstream commit 53e977b1d50c46f2c4ec3865cd13a822f58ad3cd ]
Check whether the battery supports the relevant charge threshold before reading the value to silence these errors:
thinkpad_acpi: acpi_evalf(BCTG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCTG: evaluate failedthinkpad_acpi: acpi_evalf(BCSG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCSG: evaluate failed
when reading the charge thresholds via sysfs on platforms that do not support them such as the ThinkPad T400.
--- drivers/platform/x86/thinkpad_acpi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/platform/x86/thinkpad_acpi.c +4 -2
@@ -9499,14 +9499,16 @@ static int tpacpi_battery_get(int what, int battery, int *ret) {switch (what) {case THRESHOLD_START : - if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery)) +if (!battery_info.batteries[battery].start_support || +ACPI_FAILURE (tpacpi_battery_acpi_eval (GET_START , ret, battery)))return -ENODEV ;/* The value is in the low 8 bits of the response */ *ret = *ret &0xFF ;return 0 ;case THRESHOLD_STOP : - if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery)) +if (!battery_info.batteries[battery].stop_support || +ACPI_FAILURE (tpacpi_battery_acpi_eval (GET_STOP , ret, battery)))return -ENODEV ;/* Value is in lower 8 bits */ *ret = *ret &0xFF ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 174/265 HID: multitouch: Get the contact ID from HID_DG_TRANSDUCER_INDEX fields in case of Apple Touch Bar
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kerem Karabay <[email protected]>
[ Upstream commit f41d736acc039d86512951f4e874b0f5e666babf ]
In Apple Touch Bar, the contact ID is contained in fields with the HID_DG_TRANSDUCER_INDEX usage rather than HID_DG_CONTACTID, thus differing from the HID spec. Add a quirk for the same.
Stable-dep-of: a2e70a89fa58 ("HID: multitouch: new class MT_CLS_EGALAX_P80H84")
--- drivers/hid/hid-multitouch.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/hid/hid-multitouch.c +15 -1
@@ -72,6 +72,7 @@ MODULE_LICENSE("GPL");#define MT_QUIRK_FORCE_MULTI_INPUT BIT(20)#define MT_QUIRK_DISABLE_WAKEUP BIT(21)#define MT_QUIRK_ORIENTATION_INVERT BIT(22) +#define MT_QUIRK_APPLE_TOUCHBAR BIT(23)#define MT_INPUTMODE_TOUCHSCREEN 0x02#define MT_INPUTMODE_TOUCHPAD 0x03
@@ -621,6 +622,7 @@ static struct mt_application *mt_find_application(struct mt_device *td,static struct mt_report_data *mt_allocate_report_data (struct mt_device *td,struct hid_report *report) { +struct mt_class *cls = &td->mtclass;struct mt_report_data *rdata;struct hid_field *field;int r, n;
@@ -645,7 +647,11 @@ static struct mt_report_data *mt_allocate_report_data(struct mt_device *td,if (field->logical ==HID_DG_FINGER || td->hdev->group !=HID_GROUP_MULTITOUCH_WIN_8 ) {for (n =0 ; n < field->report_count; n++) { -if (field->usage[n].hid ==HID_DG_CONTACTID ) { +unsigned int hid = field->usage[n].hid; + +if (hid ==HID_DG_CONTACTID || + (cls->quirks &MT_QUIRK_APPLE_TOUCHBAR && + hid ==HID_DG_TRANSDUCER_INDEX )) { rdata->is_mt_collection = true;break ; }
@@ -823,6 +829,14 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, EV_KEY, BTN_TOUCH);MT_STORE_FIELD (tip_state);return 1 ; +case HID_DG_TRANSDUCER_INDEX : +/* +* Contact ID in case of Apple Touch Bars is contained +* in fields with HID_DG_TRANSDUCER_INDEX usage. +*/ +if (!(cls->quirks &MT_QUIRK_APPLE_TOUCHBAR )) +return 0 ; + fallthrough;case HID_DG_CONTACTID :MT_STORE_FIELD (contactid); app->touches_by_report++;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 175/265 HID: multitouch: add device ID for Apple Touch Bar
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kerem Karabay <[email protected]>
[ Upstream commit 2c31ec923c323229566d799267000f8123af4449 ]
This patch adds the device ID of Apple Touch Bar found on x86 MacBook Pros to the hid-multitouch driver.
Note that this is device ID is for T2 Macs. Testing on T1 Macs would be appreciated.
Stable-dep-of: a2e70a89fa58 ("HID: multitouch: new class MT_CLS_EGALAX_P80H84")
--- drivers/hid/Kconfig | 1 + drivers/hid/hid-multitouch.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+)
drivers/hid/Kconfig +1 -0
@@ -730,6 +730,7 @@ config HID_MULTITOUCH Say Y here if you have one of the following devices: - 3M PCT touch screens - ActionStar dual touch panels + - Apple Touch Bar on x86 MacBook Pros - Atmel panels - Cando dual touch panels - Chunghwa panels
drivers/hid/hid-multitouch.c +17 -0
@@ -216,6 +216,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);#define MT_CLS_GOOGLE 0x0111#define MT_CLS_RAZER_BLADE_STEALTH 0x0112#define MT_CLS_SMART_TECH 0x0113 +#define MT_CLS_APPLE_TOUCHBAR 0x0114#define MT_CLS_SIS 0x0457#define MT_DEFAULT_MAXCONTACT 10
@@ -402,6 +403,12 @@ static const struct mt_class mt_classes[] = {MT_QUIRK_CONTACT_CNT_ACCURATE |MT_QUIRK_SEPARATE_APP_REPORT , }, + { .name = MT_CLS_APPLE_TOUCHBAR, + .quirks = MT_QUIRK_HOVERING | +MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE | +MT_QUIRK_APPLE_TOUCHBAR , + .maxcontacts = 11, + }, { .name = MT_CLS_SIS, .quirks = MT_QUIRK_NOT_SEEN_MEANS_UP | MT_QUIRK_ALWAYS_VALID |
@@ -1842,6 +1849,11 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)if (ret !=0 )return ret; +if (mtclass->name ==MT_CLS_APPLE_TOUCHBAR && + !hid_find_field (hdev,HID_INPUT_REPORT , +HID_DG_TOUCHPAD ,HID_DG_TRANSDUCER_INDEX )) +return -ENODEV ; +if (mtclass->quirks &MT_QUIRK_FIX_CONST_CONTACT_ID )mt_fix_const_fields (hdev,HID_DG_CONTACTID );
@@ -2332,6 +2344,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR2) }, +/* Apple Touch Bar */ + { .driver_data = MT_CLS_APPLE_TOUCHBAR, +HID_USB_DEVICE (USB_VENDOR_ID_APPLE , + USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY) }, + /* Google MT devices */ { .driver_data = MT_CLS_GOOGLE, HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_GOOGLE,
Signature · 1 line
2.51.0
Re: [PATCH 6.12 175/265] HID: multitouch: add device ID for Apple Touch Bar
This patch is not needed to be applied to 6.12 as necessary drivers for the touchbar to work are starting from 6.15.
Quoted 93 lines · Greg Kroah-Hartman
6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kerem Karabay <[email protected]>
[ Upstream commit
2c31ec923c323229566d799267000f8123af4449]This patch adds the device ID of Apple Touch Bar found on x86 MacBook Pros to the hid-multitouch driver.
Note that this is device ID is for T2 Macs. Testing on T1 Macs would be appreciated.
Signed-off-by Kerem Karabay <[email protected]>Co-developed-by Aditya Garg <[email protected]>Signed-off-by Aditya Garg <[email protected]>Signed-off-by Jiri Kosina <[email protected]>Stable-dep-of:
a2e70a89fa58("HID: multitouch: new classMT_CLS_EGALAX_P80H84")Signed-off-by Sasha Levin <[email protected]>---
drivers/hid/Kconfig| 1 +drivers/hid/hid-multitouch.c| 17 +++++++++++++++++2 files changed, 18 insertions(+)drivers/hid/Kconfig +1
-0@@ -730,6 +730,7 @@ config HID_MULTITOUCH Say Y here if you have one of the following devices: - 3M PCT touch screens - ActionStar dual touch panels + - Apple Touch Bar on x86 MacBook Pros - Atmel panels - Cando dual touch panels - Chunghwa panelsdrivers/hid/hid-multitouch.c +17
-1@@ -216,6 +216,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);#define MT_CLS_GOOGLE 0x0111#define MT_CLS_RAZER_BLADE_STEALTH 0x0112#define MT_CLS_SMART_TECH 0x0113 +#define MT_CLS_APPLE_TOUCHBAR 0x0114#define MT_CLS_SIS 0x0457#define MT_DEFAULT_MAXCONTACT 10@@ -402,6 +403,12 @@ static const struct mt_class mt_classes[] = {MT_QUIRK_CONTACT_CNT_ACCURATE |MT_QUIRK_SEPARATE_APP_REPORT , }, + { .name = MT_CLS_APPLE_TOUCHBAR, + .quirks = MT_QUIRK_HOVERING | +MT_QUIRK_SLOT_IS_CONTACTID_MINUS_ONE | +MT_QUIRK_APPLE_TOUCHBAR , + .maxcontacts = 11, + }, { .name = MT_CLS_SIS, .quirks = MT_QUIRK_NOT_SEEN_MEANS_UP | MT_QUIRK_ALWAYS_VALID |@@ -1842,6 +1849,11 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)if (ret !=0 )return ret; +if (mtclass->name ==MT_CLS_APPLE_TOUCHBAR && + !hid_find_field (hdev,HID_INPUT_REPORT , +HID_DG_TOUCHPAD ,HID_DG_TRANSDUCER_INDEX )) +return -ENODEV ; +if (mtclass->quirks &MT_QUIRK_FIX_CONST_CONTACT_ID )mt_fix_const_fields (hdev,HID_DG_CONTACTID );@@ -2332,6 +2344,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_XIROKU, USB_DEVICE_ID_XIROKU_CSR2) }, +/* Apple Touch Bar */ + { .driver_data = MT_CLS_APPLE_TOUCHBAR, +HID_USB_DEVICE (USB_VENDOR_ID_APPLE , + USB_DEVICE_ID_APPLE_TOUCHBAR_DISPLAY) }, + /* Google MT devices */ { .driver_data = MT_CLS_GOOGLE, HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_GOOGLE, --2.51.0
Greg Kroah-Hartman
maintainerRe: [PATCH 6.12 175/265] HID: multitouch: add device ID for Apple Touch Bar
Quoted 1 line · Aditya Garg
This patch is not needed to be applied to 6.12 as necessary drivers for the touchbar to work are starting from 6.15.
Now dropped, thanks.
greg k-h
Greg Kroah-Hartman
maintainerPATCH 176/265 HID: multitouch: add quirks for Lenovo Yoga Book 9i
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Brian Howard <[email protected]>
[ Upstream commit 822bc5b3744b0b2c2c9678aa1d80b2cf04fdfabf ]
The Lenovo Yoga Book 9i is a dual-screen laptop, with a single composite USB device providing both touch and tablet interfaces for both screens. All inputs report through a single device, differentiated solely by report numbers. As there is no way for udev to differentiate the inputs based on USB vendor/product ID or interface numbers, custom naming is required to match against for downstream configuration. A firmware bug also results in an erroneous InRange message report being received after the stylus leaves proximity, blocking later touch events. Add required quirks for Gen 8 to Gen 10 models, including a new quirk providing for custom input device naming and dropping erroneous InRange reports.
Stable-dep-of: a2e70a89fa58 ("HID: multitouch: new class MT_CLS_EGALAX_P80H84")
--- drivers/hid/hid-ids.h | 1 + drivers/hid/hid-multitouch.c | 72 ++++++++++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+)
drivers/hid/hid-ids.h +1 -0
@@ -832,6 +832,7 @@#define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5#define USB_DEVICE_ID_LENOVO_X12_TAB 0x60fe#define USB_DEVICE_ID_LENOVO_X12_TAB2 0x61ae +#define USB_DEVICE_ID_LENOVO_YOGABOOK9I 0x6161#define USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E 0x600e#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d#define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019
drivers/hid/hid-multitouch.c +72 -0
108 lines not on this page · raw message
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 177/265 HID: multitouch: new class MT_CLS_EGALAX_P80H84
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Ray <[email protected]>
[ Upstream commit a2e70a89fa58133521b2deae4427d35776bda935 ]
--- drivers/hid/hid-multitouch.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/hid/hid-multitouch.c +9 -2
@@ -219,6 +219,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);#define MT_CLS_SMART_TECH 0x0113#define MT_CLS_APPLE_TOUCHBAR 0x0114#define MT_CLS_YOGABOOK9I 0x0115 +#define MT_CLS_EGALAX_P80H84 0x0116#define MT_CLS_SIS 0x0457#define MT_DEFAULT_MAXCONTACT 10
@@ -424,6 +425,11 @@ static const struct mt_class mt_classes[] = { MT_QUIRK_YOGABOOK9I, .export_all_inputs = true }, + { .name = MT_CLS_EGALAX_P80H84, + .quirks =MT_QUIRK_ALWAYS_VALID | +MT_QUIRK_IGNORE_DUPLICATES | + MT_QUIRK_CONTACT_CNT_ACCURATE, + }, { } };
@@ -2121,8 +2127,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_EGALAX_SERIAL,MT_USB_DEVICE (USB_VENDOR_ID_DWAV , USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C000) }, - { .driver_data = MT_CLS_EGALAX, -MT_USB_DEVICE (USB_VENDOR_ID_DWAV , + { .driver_data = MT_CLS_EGALAX_P80H84, +HID_DEVICE (HID_BUS_ANY ,HID_GROUP_MULTITOUCH_WIN_8 , +USB_VENDOR_ID_DWAV , USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },/* Elan devices */
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 178/265 pinctrl: cirrus: cs42l43: Fix double-put in cs42l43_pin_probe()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Felix Gu <[email protected]>
[ Upstream commit fd5bed798f45eb3a178ad527b43ab92705faaf8a ]
devm_add_action_or_reset() already invokes the action on failure, so the explicit put causes a double-put.
--- drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/pinctrl/cirrus/pinctrl-cs42l43.c +2 -3
@@ -569,10 +569,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev)if (child) { ret =devm_add_action_or_reset (&pdev->dev, cs42l43_fwnode_put, child); -if (ret) { -fwnode_handle_put (child); +if (ret)return ret; - } +if (!child->dev) child->dev = priv->dev; fwnode = child;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 179/265 hwmon: (it87) Check the it87_lock() return value
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bart Van Assche <[email protected]>
[ Upstream commit 07ed4f05bbfd2bc014974dcc4297fd3aa1cb88c0 ]
Return early in it87_resume() if it87_lock() fails instead of ignoring the return value of that function. This patch suppresses a Clang thread-safety warning.
--- drivers/hwmon/it87.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/hwmon/it87.c +4 -1
@@ -3590,10 +3590,13 @@ static int it87_resume(struct device *dev) {struct platform_device *pdev =to_platform_device (dev);struct it87_data *data =dev_get_drvdata (dev); +int err;it87_resume_sio (pdev); -it87_lock (data); + err =it87_lock (data); +if (err) +return err;it87_check_pwm (dev);it87_check_limit_regs (data);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 180/265 idpf: change IRQ naming to match netdev and ethtool queue numbering
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Brian Vazquez <[email protected]>
[ Upstream commit 1500a8662d2d41d6bb03e034de45ddfe6d7d362d ]
The code uses the vidx for the IRQ name but that doesn't match ethtool reporting nor netdev naming, this makes it hard to tune the device and associate queues with IRQs. Sequentially requesting irqs starting from '0' makes the output consistent.
This commit changes the interrupt numbering but preserves the name format, maintaining ABI compatibility. Existing tools relying on the old numbering are already non-functional, as they lack a useful correlation to the interrupts.
Before:
ethtool -L eth1 tx 1 combined 3
grep . /proc/irq/*/*idpf*/../smp_affinity_list /proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167 /proc/irq/68/idpf-eth1-TxRx-1/../smp_affinity_list:0 /proc/irq/70/idpf-eth1-TxRx-3/../smp_affinity_list:1 /proc/irq/71/idpf-eth1-TxRx-4/../smp_affinity_list:2 /proc/irq/72/idpf-eth1-Tx-5/../smp_affinity_list:3
ethtool -S eth1 | grep -v ': 0'
NIC statistics:
tx_q-0_pkts: 1002
tx_q-1_pkts: 2679
tx_q-2_pkts: 1113
tx_q-3_pkts: 1192 <----- tx_q-3 vs idpf-eth1-Tx-5
rx_q-0_pkts: 1143
rx_q-1_pkts: 3172
rx_q-2_pkts: 1074After:
ethtool -L eth1 tx 1 combined 3
grep . /proc/irq/*/*idpf*/../smp_affinity_list
/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167 /proc/irq/68/idpf-eth1-TxRx-0/../smp_affinity_list:0 /proc/irq/70/idpf-eth1-TxRx-1/../smp_affinity_list:1 /proc/irq/71/idpf-eth1-TxRx-2/../smp_affinity_list:2 /proc/irq/72/idpf-eth1-Tx-3/../smp_affinity_list:3
ethtool -S eth1 | grep -v ': 0'
NIC statistics:
tx_q-0_pkts: 118
tx_q-1_pkts: 134
tx_q-2_pkts: 228
tx_q-3_pkts: 138 <--- tx_q-3 matches idpf-eth1-Tx-3
rx_q-0_pkts: 111
rx_q-1_pkts: 366
rx_q-2_pkts: 120--- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/idpf/idpf_txrx.c +1 -1
@@ -3477,7 +3477,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)continue ; name =kasprintf (GFP_KERNEL ,"%s-%s-%s-%d" , drv_name, if_name, - vec_name, vidx); + vec_name, vector); err =request_irq (irq_num, idpf_vport_intr_clean_queues,0 , name, q_vector);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 181/265 i40e: Fix preempt count leak in napi poll tracepoint
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thomas Gleixner <[email protected]>
[ Upstream commit 4b3d54a85bd37ebf2d9836f0d0de775c0ff21af9 ]
Using get_cpu() in the tracepoint assignment causes an obvious preempt count leak because nothing invokes put_cpu() to undo it:
softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101?
This clearly has seen a lot of testing in the last 3+ years...
Use smp_processor_id() instead.
--- drivers/net/ethernet/intel/i40e/i40e_trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/i40e/i40e_trace.h +1 -1
@@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll, __entry->rx_clean_complete = rx_clean_complete; __entry->tx_clean_complete = tx_clean_complete; __entry->irq_num = q->irq_num; - __entry->curr_cpu =get_cpu (); + __entry->curr_cpu =smp_processor_id ();__assign_str (qname);__assign_str (dev_name); __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask),
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 182/265 e1000e: clear DPG_EN after reset to avoid autonomous power-gating
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vitaly Lifshits <[email protected]>
[ Upstream commit 0942fc6d324eb9c6b16187b2aa994c0823557f06 ]
Panther Lake systems introduced an autonomous power gating feature for the integrated Gigabit Ethernet in shutdown state (S5) state. As part of it, the reset value of DPG_EN bit was changed to 1. Clear this bit after performing hardware reset to avoid errors such as Tx/Rx hangs, or packet loss/corruption.
--- drivers/net/ethernet/intel/e1000e/defines.h | 1 + drivers/net/ethernet/intel/e1000e/ich8lan.c | 9 +++++++++ 2 files changed, 10 insertions(+)
drivers/net/ethernet/intel/e1000e/defines.h +1 -0
@@ -33,6 +33,7 @@/* Extended Device Control */ #define E1000_CTRL_EXT_LPCD 0x00000004/* LCD Power Cycle Done */ +#define E1000_CTRL_EXT_DPG_EN 0x00000008/* Dynamic Power Gating Enable */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080/* Value of SW Definable Pin 3 */ #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800/* Force SMBus mode */ #define E1000_CTRL_EXT_EE_RST 0x00002000/* Reinitialize from EEPROM */
drivers/net/ethernet/intel/e1000e/ich8lan.c +9 -0
@@ -4925,6 +4925,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) reg |=E1000_KABGTXD_BGSQLBIAS ;ew32 (KABGTXD , reg); +/* The hardware reset value of the DPG_EN bit is 1. +* Clear DPG_EN to prevent unexpected autonomous power gating. +*/ +if (hw->mac.type >= e1000_pch_ptp) { + reg =er32 (CTRL_EXT ); + reg &= ~E1000_CTRL_EXT_DPG_EN ; +ew32 (CTRL_EXT , reg); + } +return 0 ; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 183/265 drm/solomon: Fix page start when updating rectangle in page addressing mode
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Francesco Lavra <[email protected]>
[ Upstream commit 36d9579fed6c9429aa172f77bd28c58696ce8e2b ]
In page addressing mode, the pixel values of a dirty rectangle must be sent to the display controller one page at a time. The range of pages corresponding to a given rectangle is being incorrectly calculated as if the Y value of the top left coordinate of the rectangle was 0. This can result in rectangle updates being displayed on wrong parts of the screen.
Fix the above issue by consolidating the start page calculation in a single place at the beginning of the update_rect function, and using the calculated value for all addressing modes.
--- drivers/gpu/drm/solomon/ssd130x.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
drivers/gpu/drm/solomon/ssd130x.c +2 -4
@@ -736,6 +736,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,unsigned int height =drm_rect_height (rect);unsigned int line_length =DIV_ROUND_UP (width,8 );unsigned int page_height =SSD130X_PAGE_HEIGHT ; +u8 page_start = ssd130x->page_offset + y / page_height;unsigned int pages =DIV_ROUND_UP (height, page_height);struct drm_device *drm = &ssd130x->drm;u32 array_idx =0 ;
@@ -773,14 +774,11 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,*/ if (!ssd130x->page_address_mode) { -u8 page_start; -/* Set address range for horizontal addressing mode */ ret =ssd130x_set_col_range (ssd130x, ssd130x->col_offset + x, width);if (ret <0 )return ret; - page_start = ssd130x->page_offset + y / page_height; ret =ssd130x_set_page_range (ssd130x, page_start, pages);if (ret <0 )return ret;
@@ -812,7 +810,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,*/ if (ssd130x->page_address_mode) { ret =ssd130x_set_page_pos (ssd130x, - ssd130x->page_offset + i, + page_start + i, ssd130x->col_offset + x);if (ret <0 )return ret;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 184/265 net: ethernet: ti: am65-cpsw-nuss/cpsw-ale: Fix multicast entry handling in ALE table
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chintan Vankar <[email protected]>
[ Upstream commit be11a537224d72b906db6b98510619770298c8a4 ]
In the current implementation, flushing multicast entries in MAC mode incorrectly deletes entries for all ports instead of only the target port, disrupting multicast traffic on other ports. The cause is adding multicast entries by setting only host port bit, and not setting the MAC port bits.
Fix this by setting the MAC port's bit in the port mask while adding the multicast entry. Also fix the flush logic to preserve the host port bit during removal of MAC port and free ALE entries when mask contains only host port.
--- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/ethernet/ti/cpsw_ale.c | 9 ++++----- 2 files changed, 5 insertions(+), 6 deletions(-)
drivers/net/ethernet/ti/am65-cpsw-nuss.c +1 -1
@@ -290,7 +290,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev)cpsw_ale_set_allmulti (common->ale, ndev->flags &IFF_ALLMULTI , port->port_id); - port_mask =ALE_PORT_HOST ; + port_mask =BIT (port->port_id) |ALE_PORT_HOST ;/* Clear all mcast from ALE */ cpsw_ale_flush_multicast (common->ale, port_mask,-1 );
drivers/net/ethernet/ti/cpsw_ale.c +4 -5
@@ -443,14 +443,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, ale->port_mask_bits);if ((mask & port_mask) ==0 )return ;/* ports dont intersect, not interested */ - mask &= ~port_mask; + mask &= (~port_mask |ALE_PORT_HOST ); -/* free if only remaining port is host port */ -if (mask) +if (mask ==0x0 || mask ==ALE_PORT_HOST ) +cpsw_ale_set_entry_type (ale_entry,ALE_TYPE_FREE ); +else cpsw_ale_set_port_mask (ale_entry, mask, ale->port_mask_bits); -else -cpsw_ale_set_entry_type (ale_entry,ALE_TYPE_FREE ); }int cpsw_ale_flush_multicast (struct cpsw_ale *ale,int port_mask,int vid)
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 185/265 xsk: Get rid of xdp_buff_xsk::xskb_list_node
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Maciej Fijalkowski <[email protected]>
[ Upstream commit b692bf9a7543af7ad11a59d182a3757578f0ba53 ]
Let's bring xdp_buff_xsk back to occupying 2 cachelines by removing xskb_list_node - for the purpose of gathering the xskb frags free_list_node can be used, head of the list (xsk_buff_pool::xskb_list) stays as-is, just reuse the node ptr.
It is safe to do as a single xdp_buff_xsk can never reside in two pool's lists simultaneously.
Stable-dep-of: f7387d6579d6 ("xsk: Fix zero-copy AF_XDP fragment drop")
--- include/net/xdp_sock_drv.h | 14 +++++++------- include/net/xsk_buff_pool.h | 1 - net/xdp/xsk.c | 4 ++-- net/xdp/xsk_buff_pool.c | 1 - 4 files changed, 9 insertions(+), 11 deletions(-)
include/net/xdp_sock_drv.h +7 -7
@@ -126,8 +126,8 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)if (likely (!xdp_buff_has_frags (xdp))) goto out; -list_for_each_entry_safe (pos, tmp, xskb_list, xskb_list_node) { -list_del (&pos->xskb_list_node); +list_for_each_entry_safe (pos, tmp, xskb_list, free_list_node) { +list_del (&pos->free_list_node);xp_free (pos); }
@@ -140,7 +140,7 @@ static inline void xsk_buff_add_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); -list_add_tail (&frag->xskb_list_node, &frag->pool->xskb_list); +list_add_tail (&frag->free_list_node, &frag->pool->xskb_list); }static inline struct xdp_buff *xsk_buff_get_frag (struct xdp_buff *first)
@@ -150,9 +150,9 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)struct xdp_buff_xsk *frag; frag =list_first_entry_or_null (&xskb->pool->xskb_list, - struct xdp_buff_xsk, xskb_list_node); + struct xdp_buff_xsk, free_list_node);if (frag) { -list_del (&frag->xskb_list_node); +list_del (&frag->free_list_node); ret = &frag->xdp; }
@@ -163,7 +163,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail) { struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); -list_del (&xskb->xskb_list_node); +list_del (&xskb->free_list_node); }static inline struct xdp_buff *xsk_buff_get_tail (struct xdp_buff *first)
@@ -172,7 +172,7 @@ static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)struct xdp_buff_xsk *frag; frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk, - xskb_list_node); + free_list_node);return &frag->xdp; }
include/net/xsk_buff_pool.h +0 -1
@@ -30,7 +30,6 @@ struct xdp_buff_xsk {struct xsk_buff_pool *pool;u64 orig_addr;struct list_head free_list_node; -struct list_head xskb_list_node; };#define XSK_CHECK_PRIV_TYPE (t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
net/xdp/xsk.c +2 -2
@@ -171,14 +171,14 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)return 0 ; xskb_list = &xskb->pool->xskb_list; -list_for_each_entry_safe (pos, tmp, xskb_list, xskb_list_node) { +list_for_each_entry_safe (pos, tmp, xskb_list, free_list_node) {if (list_is_singular (xskb_list)) contd =0 ; len = pos->xdp.data_end - pos->xdp.data; err =__xsk_rcv_zc (xs, pos, len, contd);if (err) goto err; -list_del (&pos->xskb_list_node); +list_del (&pos->free_list_node); }return 0 ;
net/xdp/xsk_buff_pool.c +0 -1
@@ -103,7 +103,6 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, xskb->pool = pool; xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;INIT_LIST_HEAD (&xskb->free_list_node); -INIT_LIST_HEAD (&xskb->xskb_list_node);if (pool->unaligned) pool->free_heads[i] = xskb;else
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 186/265 xsk: s/free_list_node/list_node/
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Maciej Fijalkowski <[email protected]>
[ Upstream commit 30ec2c1baaead43903ad63ff8e3083949059083c ]
Now that free_list_node's purpose is two-folded, make it just a 'list_node'.
Stable-dep-of: f7387d6579d6 ("xsk: Fix zero-copy AF_XDP fragment drop")
--- include/net/xdp_sock_drv.h | 14 +++++++------- include/net/xsk_buff_pool.h | 2 +- net/xdp/xsk.c | 4 ++-- net/xdp/xsk_buff_pool.c | 14 +++++++------- 4 files changed, 17 insertions(+), 17 deletions(-)
include/net/xdp_sock_drv.h +7 -7
@@ -126,8 +126,8 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)if (likely (!xdp_buff_has_frags (xdp))) goto out; -list_for_each_entry_safe (pos, tmp, xskb_list, free_list_node) { -list_del (&pos->free_list_node); +list_for_each_entry_safe (pos, tmp, xskb_list, list_node) { +list_del (&pos->list_node);xp_free (pos); }
@@ -140,7 +140,7 @@ static inline void xsk_buff_add_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp); -list_add_tail (&frag->free_list_node, &frag->pool->xskb_list); +list_add_tail (&frag->list_node, &frag->pool->xskb_list); }static inline struct xdp_buff *xsk_buff_get_frag (struct xdp_buff *first)
@@ -150,9 +150,9 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)struct xdp_buff_xsk *frag; frag =list_first_entry_or_null (&xskb->pool->xskb_list, - struct xdp_buff_xsk, free_list_node); + struct xdp_buff_xsk, list_node);if (frag) { -list_del (&frag->free_list_node); +list_del (&frag->list_node); ret = &frag->xdp; }
@@ -163,7 +163,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail) { struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); -list_del (&xskb->free_list_node); +list_del (&xskb->list_node); }static inline struct xdp_buff *xsk_buff_get_tail (struct xdp_buff *first)
@@ -172,7 +172,7 @@ static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)struct xdp_buff_xsk *frag; frag = list_last_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk, - free_list_node); + list_node);return &frag->xdp; }
include/net/xsk_buff_pool.h +1 -1
@@ -29,7 +29,7 @@ struct xdp_buff_xsk {dma_addr_t frame_dma;struct xsk_buff_pool *pool;u64 orig_addr; -struct list_head free_list_node; +struct list_head list_node; };#define XSK_CHECK_PRIV_TYPE (t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
net/xdp/xsk.c +2 -2
@@ -171,14 +171,14 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)return 0 ; xskb_list = &xskb->pool->xskb_list; -list_for_each_entry_safe (pos, tmp, xskb_list, free_list_node) { +list_for_each_entry_safe (pos, tmp, xskb_list, list_node) {if (list_is_singular (xskb_list)) contd =0 ; len = pos->xdp.data_end - pos->xdp.data; err =__xsk_rcv_zc (xs, pos, len, contd);if (err) goto err; -list_del (&pos->free_list_node); +list_del (&pos->list_node); }return 0 ;
net/xdp/xsk_buff_pool.c +7 -7
@@ -102,7 +102,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, xskb = &pool->heads[i]; xskb->pool = pool; xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; -INIT_LIST_HEAD (&xskb->free_list_node); +INIT_LIST_HEAD (&xskb->list_node);if (pool->unaligned) pool->free_heads[i] = xskb;else
@@ -549,8 +549,8 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) }else { pool->free_list_cnt--; xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, - free_list_node); -list_del_init (&xskb->free_list_node); + list_node); +list_del_init (&xskb->list_node); } xskb->xdp.data = xskb->xdp.data_hard_start +XDP_PACKET_HEADROOM ;
@@ -616,8 +616,8 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3 i = nb_entries;while (i--) { - xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); -list_del_init (&xskb->free_list_node); + xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, list_node); +list_del_init (&xskb->list_node); *xdp = &xskb->xdp; xdp++;
@@ -687,11 +687,11 @@ EXPORT_SYMBOL(xp_can_alloc);void xp_free (struct xdp_buff_xsk *xskb) { -if (!list_empty (&xskb->free_list_node)) +if (!list_empty (&xskb->list_node))return ; xskb->pool->free_list_cnt++; -list_add (&xskb->free_list_node, &xskb->pool->free_list); +list_add (&xskb->list_node, &xskb->pool->free_list); }EXPORT_SYMBOL (xp_free);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 187/265 xsk: Fix fragment node deletion to prevent buffer leak
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nikhil P. Rao <[email protected]>
[ Upstream commit 60abb0ac11dccd6b98fd9182bc5f85b621688861 ]
After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"), the list_node field is reused for both the xskb pool list and the buffer free list, this causes a buffer leak as described below.
xp_free() checks if a buffer is already on the free list using list_empty(&xskb->list_node). When list_del() is used to remove a node from the xskb pool list, it doesn't reinitialize the node pointers. This means list_empty() will return false even after the node has been removed, causing xp_free() to incorrectly skip adding the buffer to the free list.
Fix this by using list_del_init() instead of list_del() in all fragment handling paths, this ensures the list node is reinitialized after removal, allowing the list_empty() to work correctly.
Stable-dep-of: f7387d6579d6 ("xsk: Fix zero-copy AF_XDP fragment drop")
--- include/net/xdp_sock_drv.h | 6 +++--- net/xdp/xsk.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-)
include/net/xdp_sock_drv.h +3 -3
@@ -127,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) goto out;list_for_each_entry_safe (pos, tmp, xskb_list, list_node) { -list_del (&pos->list_node); +list_del_init (&pos->list_node);xp_free (pos); }
@@ -152,7 +152,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first) frag =list_first_entry_or_null (&xskb->pool->xskb_list, struct xdp_buff_xsk, list_node);if (frag) { -list_del (&frag->list_node); +list_del_init (&frag->list_node); ret = &frag->xdp; }
@@ -163,7 +163,7 @@ static inline void xsk_buff_del_tail(struct xdp_buff *tail) { struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp); -list_del (&xskb->list_node); +list_del_init (&xskb->list_node); }static inline struct xdp_buff *xsk_buff_get_tail (struct xdp_buff *first)
net/xdp/xsk.c +1 -1
@@ -178,7 +178,7 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) err =__xsk_rcv_zc (xs, pos, len, contd);if (err) goto err; -list_del (&pos->list_node); +list_del_init (&pos->list_node); }return 0 ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 188/265 xsk: Fix zero-copy AF_XDP fragment drop
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nikhil P. Rao <[email protected]>
[ Upstream commit f7387d6579d65efd490a864254101cb665f2e7a7 ]
AF_XDP should ensure that only a complete packet is sent to application. In the zero-copy case, if the Rx queue gets full as fragments are being enqueued, the remaining fragments are dropped.
For the multi-buffer case, add a check to ensure that the Rx queue has enough space for all fragments of a packet before starting to enqueue them.
--- net/xdp/xsk.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
net/xdp/xsk.c +15 -9
@@ -159,25 +159,31 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)struct xdp_buff_xsk *pos, *tmp;struct list_head *xskb_list;u32 contd =0 ; +u32 num_desc;int err; -if (frags) - contd =XDP_PKT_CONTD ; +if (likely (!frags)) { + err =__xsk_rcv_zc (xs, xskb, len, contd); +if (err) + goto err; +return 0 ; + } - err =__xsk_rcv_zc (xs, xskb, len, contd); -if (err) + contd =XDP_PKT_CONTD ; + num_desc =xdp_get_shared_info_from_buff (xdp)->nr_frags +1 ; +if (xskq_prod_nb_free (xs->rx, num_desc) < num_desc) { + xs->rx_queue_full++; + err = -ENOBUFS ; goto err; -if (likely (!frags)) -return 0 ; + } +__xsk_rcv_zc (xs, xskb, len, contd); xskb_list = &xskb->pool->xskb_list;list_for_each_entry_safe (pos, tmp, xskb_list, list_node) {if (list_is_singular (xskb_list)) contd =0 ; len = pos->xdp.data_end - pos->xdp.data; - err =__xsk_rcv_zc (xs, pos, len, contd); -if (err) - goto err; +__xsk_rcv_zc (xs, pos, len, contd);list_del_init (&pos->list_node); }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 189/265 dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ handler
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guenter Roeck <[email protected]>
[ Upstream commit 74badb9c20b1a9c02a95c735c6d3cd6121679c93 ]
Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler") introduces a range check for if_id to avoid an out-of-bounds access. If an out-of-bounds if_id is detected, the interrupt status is not cleared. This may result in an interrupt storm.
Clear the interrupt status after detecting an out-of-bounds if_id to avoid the problem.
Found by an experimental AI code review agent at Google.
--- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +2 -1
@@ -1532,7 +1532,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) if_id = (status &0xFFFF0000 ) >>16 ;if (if_id >= ethsw->sw_attr.num_ifs) {dev_err (dev,"Invalid if_id %d in IRQ status\n" , if_id); - goto out; + goto out_clear; } port_priv = ethsw->ports[if_id];
@@ -1552,6 +1552,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)dpaa2_switch_port_connect_mac (port_priv); } +out_clear: err =dpsw_clear_irq_status (ethsw->mc_io,0 , ethsw->dpsw_handle,DPSW_IRQ_INDEX_IF , status);if (err)
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 190/265 atm: lec: fix null-ptr-deref in lec_arp_clear_vccs
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiayuan Chen <[email protected]>
[ Upstream commit 101bacb303e89dc2e0640ae6a5e0fb97c4eb45bb ]
syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer.
In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry.
For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables:
1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL.
2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via vcc->pop = vpriv->old_pop, leading to a null-ptr-deref crash.
Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers.
The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket.
The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.
--- net/atm/lec.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-)
net/atm/lec.c +15 -11
@@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)struct lec_vcc_priv *vpriv =LEC_VCC_PRIV (vcc);struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; -if (vpriv->xoff) -netif_wake_queue (dev); -kfree (vpriv); - vcc->user_back =NULL ; - vcc->push = entry->old_push; -vcc_release_async (vcc, -EPIPE ); +if (vpriv) { + vcc->pop = vpriv->old_pop; +if (vpriv->xoff) +netif_wake_queue (dev); +kfree (vpriv); + vcc->user_back =NULL ; + vcc->push = entry->old_push; +vcc_release_async (vcc, -EPIPE ); + } entry->vcc =NULL ; }if (entry->recv_vcc) {struct atm_vcc *vcc = entry->recv_vcc;struct lec_vcc_priv *vpriv =LEC_VCC_PRIV (vcc); -kfree (vpriv); - vcc->user_back =NULL ; +if (vpriv) { +kfree (vpriv); + vcc->user_back =NULL ; - entry->recv_vcc->push = entry->old_recv_push; -vcc_release_async (entry->recv_vcc, -EPIPE ); + entry->recv_vcc->push = entry->old_recv_push; +vcc_release_async (entry->recv_vcc, -EPIPE ); + } entry->recv_vcc =NULL ; } }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 191/265 net: ti: icssg-prueth: Fix ping failure after offload mode setup when link speed is not 1G
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: MD Danish Anwar <[email protected]>
[ Upstream commit 147792c395db870756a0dc87ce656c75ae7ab7e8 ]
When both eth interfaces with links up are added to a bridge or hsr interface, ping fails if the link speed is not 1Gbps (e.g., 100Mbps).
The issue is seen because when switching to offload (bridge/hsr) mode, prueth_emac_restart() restarts the firmware and clears DRAM with memset_io(), setting all memory to 0. This includes PORT_LINK_SPEED_OFFSET which firmware reads for link speed. The value 0 corresponds to FW_LINK_SPEED_1G (0x00), so for 1Gbps links the default value is correct and ping works. For 100Mbps links, the firmware needs FW_LINK_SPEED_100M (0x01) but gets 0 instead, causing ping to fail. The function emac_adjust_link() is called to reconfigure, but it detects no state change (emac->link is still 1, speed/duplex match PHY) so new_state remains false and icssg_config_set_speed() is never called to correct the firmware speed value.
The fix resets emac->link to 0 before calling emac_adjust_link() in prueth_emac_common_start(). This forces new_state=true, ensuring icssg_config_set_speed() is called to write the correct speed value to firmware memory.
--- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/net/ethernet/ti/icssg/icssg_prueth.c +8 -0
@@ -307,6 +307,14 @@ static int prueth_emac_common_start(struct prueth *prueth)if (ret) goto disable_class; +/* Reset link state to force reconfiguration in +* emac_adjust_link(). Without this, if the link was already up +* before restart, emac_adjust_link() won't detect any state +* change and will skip critical configuration like writing +* speed to firmware. +*/ + emac->link =0 ; +mutex_lock (&emac->ndev->phydev->lock);emac_adjust_link (emac->ndev);mutex_unlock (&emac->ndev->phydev->lock);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 192/265 amd-xgbe: fix MAC_TCR_SS register width for 2.5G and 10M speeds
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Raju Rangoju <[email protected]>
[ Upstream commit 9439a661c2e80485406ce2c90b107ca17858382d ]
Extend the MAC_TCR_SS (Speed Select) register field width from 2 bits to 3 bits to properly support all speed settings.
The MAC_TCR register's SS field encoding requires 3 bits to represent all supported speeds:
- 0x00: 10Gbps (XGMII)
- 0x02: 2.5Gbps (GMII) / 100Mbps
- 0x03: 1Gbps / 10Mbps
- 0x06: 2.5Gbps (XGMII) - P100a only
With only 2 bits, values 0x04-0x07 cannot be represented, which breaks 2.5G XGMII mode on newer platforms and causes incorrect speed select values to be programmed.
--- drivers/net/ethernet/amd/xgbe/xgbe-common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/amd/xgbe/xgbe-common.h +1 -1
@@ -514,7 +514,7 @@#define MAC_SSIR_SSINC_INDEX 16#define MAC_SSIR_SSINC_WIDTH 8#define MAC_TCR_SS_INDEX 29 -#define MAC_TCR_SS_WIDTH 2 +#define MAC_TCR_SS_WIDTH 3#define MAC_TCR_TE_INDEX 0#define MAC_TCR_TE_WIDTH 1#define MAC_TCR_VNE_INDEX 24
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 193/265 can: bcm: fix locking for bcm_op runtime updates
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Oliver Hartkopp <[email protected]>
[ Upstream commit c35636e91e392e1540949bbc67932167cb48bc3a ]
Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup().
Usually the RX_SETUP only handles and filters incoming traffic with one
exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.
--- net/can/bcm.c | 1 + 1 file changed, 1 insertion(+)
net/can/bcm.c +1 -0
@@ -1170,6 +1170,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,if (!op)return -ENOMEM ; +spin_lock_init (&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz =CFSIZ (msg_head->flags);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 194/265 can: mcp251x: fix deadlock in error path of mcp251x_open
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alban Bedel <[email protected]>
[ Upstream commit ab3f894de216f4a62adc3b57e9191888cbf26885 ]
The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish.
This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can:
mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path.
To solve this issue move the call to free_irq() after the lock is released. Setting priv->force_quit = 1 beforehand ensure that the IRQ handler will exit right away once it acquired the lock.
--- drivers/net/can/spi/mcp251x.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)
drivers/net/can/spi/mcp251x.c +14 -1
@@ -1201,6 +1201,7 @@ static int mcp251x_open(struct net_device *net) {struct mcp251x_priv *priv =netdev_priv (net);struct spi_device *spi = priv->spi; +bool release_irq = false;unsigned long flags =0 ;int ret;
@@ -1244,12 +1245,24 @@ static int mcp251x_open(struct net_device *net)return 0 ; out_free_irq: -free_irq (spi->irq, priv); +/* The IRQ handler might be running, and if so it will be waiting +* for the lock. But free_irq() must wait for the handler to finish +* so calling it here would deadlock. +* +* Setting priv->force_quit will let the handler exit right away +* without any access to the hardware. This make it safe to call +* free_irq() after the lock is released. +*/ + priv->force_quit =1 ; + release_irq = true; +mcp251x_hw_sleep (spi); out_close:mcp251x_power_enable (priv->transceiver,0 );close_candev (net);mutex_unlock (&priv->mcp_lock); +if (release_irq) +free_irq (spi->irq, priv);return ret; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 195/265 wifi: rsi: Dont default to -EOPNOTSUPP in rsi_mac80211_config
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sebastian Krzyszkowiak <[email protected]>
[ Upstream commit d973b1039ccde6b241b438d53297edce4de45b5c ]
This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected behavior from the driver - other drivers default to 0 too.
--- drivers/net/wireless/rsi/rsi_91x_mac80211.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/rsi/rsi_91x_mac80211.c +1 -1
@@ -666,7 +666,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,struct rsi_hw *adapter = hw->priv;struct rsi_common *common = adapter->priv;struct ieee80211_conf *conf = &hw->conf; -int status = -EOPNOTSUPP ; +int status =0 ;mutex_lock (&common->mutex);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 196/265 drm/xe: Do not preempt fence signaling CS instructions
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthew Brost <[email protected]>
[ Upstream commit cdc8a1e11f4d5b480ec750e28010c357185b95a6 ]
If a batch buffer is complete, it makes little sense to preempt the fence signaling instructions in the ring, as the largest portion of the work (the batch buffer) is already done and fence signaling consists of only a few instructions. If these instructions are preempted, the GuC would need to perform a context switch just to signal the fence, which is costly and delays fence signaling. Avoid this scenario by disabling preemption immediately after the BB start instruction and re-enabling it after executing the fence signaling instructions.
--- drivers/gpu/drm/xe/xe_ring_ops.c | 9 +++++++++ 1 file changed, 9 insertions(+)
drivers/gpu/drm/xe/xe_ring_ops.c +9 -0
@@ -259,6 +259,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc i =emit_bb_start (batch_addr, ppgtt_flag, dw, i); +/* Don't preempt fence signaling */ + dw[i++] =MI_ARB_ON_OFF |MI_ARB_DISABLE ; +if (job->user_fence.used) { i =emit_flush_dw (dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -322,6 +325,9 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i =emit_bb_start (batch_addr, ppgtt_flag, dw, i); +/* Don't preempt fence signaling */ + dw[i++] =MI_ARB_ON_OFF |MI_ARB_DISABLE ; +if (job->user_fence.used) { i =emit_flush_dw (dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -371,6 +377,9 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, i =emit_bb_start (batch_addr, ppgtt_flag, dw, i); +/* Don't preempt fence signaling */ + dw[i++] =MI_ARB_ON_OFF |MI_ARB_DISABLE ; + i =emit_render_cache_flush (job, dw, i);if (job->user_fence.used)
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 197/265 rust: kunit: fix warning when !CONFIG_PRINTK
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexandre Courbot <[email protected]>
[ Upstream commit 7dd34dfc8dfa92a7244242098110388367996ac3 ]
If CONFIG_PRINTK is not set, then the following warnings are issued during build:
warning: unused variable: args
--> ../rust/kernel/kunit.rs:16:12
| 16 | pub fn err(args: fmt::Arguments<'_>) {
| ^^^^ help: if this is intentional, prefix it with an underscore: _args
|
= note: #[warn(unused_variables)] (part of #[warn(unused)]) on by default
warning: unused variable: args
--> ../rust/kernel/kunit.rs:32:13
| 32 | pub fn info(args: fmt::Arguments<'_>) {
| ^^^^ help: if this is intentional, prefix it with an underscore: _args
Fix this by adding a no-op assignment using args when CONFIG_PRINTK is not set.
--- rust/kernel/kunit.rs | 8 ++++++++ 1 file changed, 8 insertions(+)
rust/kernel/kunit.rs +8 -0
@@ -13,6 +13,10 @@/// Public but hidden since it should only be used from KUnit generated code. #[doc(hidden)] pub fn err (args: fmt::Arguments <'_>) { +// `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning. +#[cfg(not( CONFIG_PRINTK ))] +let _ = args; +// SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we // are passing. #[cfg( CONFIG_PRINTK )]
@@ -29,6 +33,10 @@ pub fn err(args: fmt::Arguments<'_>) {/// Public but hidden since it should only be used from KUnit generated code. #[doc(hidden)] pub fn info (args: fmt::Arguments <'_>) { +// `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning. +#[cfg(not( CONFIG_PRINTK ))] +let _ = args; +// SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we // are passing. #[cfg( CONFIG_PRINTK )]
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 198/265 kunit: tool: copy caller args in run_kernel to prevent mutation
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shuvam Pandey <[email protected]>
[ Upstream commit 40804c4974b8df2adab72f6475d343eaff72b7f6 ]
run_kernel() appended KUnit flags directly to the caller-provided args list. When exec_tests() calls run_kernel() repeatedly (e.g. with --run_isolated), each call mutated the same list, causing later runs to inherit stale filter_glob values and duplicate kunit.enable flags.
Fix this by copying args at the start of run_kernel(). Add a regression test that calls run_kernel() twice with the same list and verifies the original remains unchanged.
--- tools/testing/kunit/kunit_kernel.py | 6 ++++-- tools/testing/kunit/kunit_tool_test.py | 26 ++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 2 deletions(-)
tools/testing/kunit/kunit_kernel.py +4 -2
@@ -333,8 +333,10 @@ class LinuxSourceTree: return self.validate_config(build_dir) def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]: - if not args: - args = [] + # Copy to avoid mutating the caller-supplied list. exec_tests() reuses + # the same args across repeated run_kernel() calls (e.g. --run_isolated), + # so appending to the original would accumulate stale flags on each call. + args = list(args) if args else [] if filter_glob: args.append('kunit.filter_glob=' + filter_glob) if filter:
tools/testing/kunit/kunit_tool_test.py +26 -0
@@ -477,6 +477,32 @@ class LinuxSourceTreeTest(unittest.TestCase): with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile: self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output') + def test_run_kernel_args_not_mutated(self): + """Verify run_kernel() copies args so callers can reuse them.""" + start_calls = [] + + def fake_start(start_args, unused_build_dir): + start_calls.append(list(start_args)) + return subprocess.Popen(['printf', 'KTAP version 1\n'], + text=True, stdout=subprocess.PIPE) + + with tempfile.TemporaryDirectory('') as build_dir: + tree = kunit_kernel.LinuxSourceTree(build_dir, + kunitconfig_paths=[os.devnull]) + with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \ + mock.patch.object(kunit_kernel.subprocess, 'call'): + kernel_args = ['mem=1G'] + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test1'): + pass + for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir, + filter_glob='suite.test2'): + pass + self.assertEqual(kernel_args, ['mem=1G'], + 'run_kernel() should not modify caller args') + self.assertIn('kunit.filter_glob=suite.test1', start_calls[0]) + self.assertIn('kunit.filter_glob=suite.test2', start_calls[1]) + def test_build_reconfig_no_config(self): with tempfile.TemporaryDirectory('') as build_dir: with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f:
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 199/265 net: dsa: realtek: rtl8365mb: fix rtl8365mb_phy_ocp_write return value
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mieczyslaw Nalewaj <[email protected]>
[ Upstream commit 7cbe98f7bef965241a5908d50d557008cf998aee ]
Function rtl8365mb_phy_ocp_write() always returns 0, even when an error occurs during register access. This patch fixes the return value to propagate the actual error code from regmap operations.
--- drivers/net/dsa/realtek/rtl8365mb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/dsa/realtek/rtl8365mb.c +1 -1
@@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, out:rtl83xx_unlock (priv); -return 0 ; +return ret; }static int rtl8365mb_phy_read (struct realtek_priv *priv,int phy,int regnum)
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 200/265 bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiayuan Chen <[email protected]>
[ Upstream commit 479d589b40b836442bbdadc3fdb37f001bb67f26 ]
bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard.
For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can:
1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3).
2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.
This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering:
WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL))
Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode.
commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set().
Note:
commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.
--- drivers/net/bonding/bond_main.c | 9 +++++++-- drivers/net/bonding/bond_options.c | 2 ++ include/net/bonding.h | 1 + 3 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/bonding/bond_main.c +7 -2
@@ -322,7 +322,7 @@ static bool bond_sk_check(struct bonding *bond) } } -bool bond_xdp_check (struct bonding *bond,int mode) +bool __bond_xdp_check (int mode,int xmit_policy) {switch (mode) {case BOND_MODE_ROUNDROBIN :
@@ -333,7 +333,7 @@ bool bond_xdp_check(struct bonding *bond, int mode)/* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ -if (bond->params.xmit_policy !=BOND_XMIT_POLICY_VLAN_SRCMAC ) +if (xmit_policy !=BOND_XMIT_POLICY_VLAN_SRCMAC )return true; fallthrough;default :
@@ -341,6 +341,11 @@ bool bond_xdp_check(struct bonding *bond, int mode) } } +bool bond_xdp_check (struct bonding *bond,int mode) +{ +return __bond_xdp_check (mode, bond->params.xmit_policy); +} +/*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
drivers/net/bonding/bond_options.c +2 -0
@@ -1546,6 +1546,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond,static int bond_option_xmit_hash_policy_set (struct bonding *bond,const struct bond_opt_value *newval) { +if (bond->xdp_prog && !__bond_xdp_check (BOND_MODE (bond), newval->value)) +return -EOPNOTSUPP ;netdev_dbg (bond->dev,"Setting xmit hash policy to %s (%llu)\n" , newval->string, newval->value); bond->params.xmit_policy = newval->value;
include/net/bonding.h +1 -0
@@ -696,6 +696,7 @@ void bond_debug_register(struct bonding *bond);void bond_debug_unregister (struct bonding *bond);void bond_debug_reregister (struct bonding *bond);const char *bond_mode_name (int mode); +bool __bond_xdp_check (int mode,int xmit_policy);bool bond_xdp_check (struct bonding *bond,int mode);void bond_setup (struct net_device *bond_dev);unsigned int bond_get_num_tx_queues (void );
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 201/265 octeon_ep: Relocate counter updates before NAPI
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vimlesh Kumar <[email protected]>
[ Upstream commit 18c04a808c436d629d5812ce883e3822a5f5a47f ]
Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion, and replace napi_complete with napi_complete_done.
Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly synchronized.napi_complete_done (vs napi_complete) allows for better interrupt coalescing.
--- .../ethernet/marvell/octeon_ep/octep_main.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)
drivers/net/ethernet/marvell/octeon_ep/octep_main.c +15 -4
@@ -555,12 +555,12 @@ static void octep_clean_irqs(struct octep_device *oct) }/** -* octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. +* octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_enable_ioq_irq (struct octep_iq *iq,struct octep_oq *oq) +static void octep_update_pkt (struct octep_iq *iq,struct octep_oq *oq) {u32 pkts_pend = oq->pkts_pending;
@@ -576,7 +576,17 @@ static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) }/* Flush the previous wrties before writing to RESEND bit */ -wmb (); +smp_wmb (); +} + +/** +* octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. +* +* @iq: Octeon Tx queue data structure. +* @oq: Octeon Rx queue data structure. +*/ +static void octep_enable_ioq_irq (struct octep_iq *iq,struct octep_oq *oq) +{writeq (1UL <<OCTEP_OQ_INTR_RESEND_BIT , oq->pkts_sent_reg);writeq (1UL <<OCTEP_IQ_INTR_RESEND_BIT , iq->inst_cnt_reg); }
@@ -602,7 +612,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget)if (tx_pending || rx_done >= budget)return budget; -napi_complete (napi); +octep_update_pkt (ioq_vector->iq, ioq_vector->oq); +napi_complete_done (napi, rx_done);octep_enable_ioq_irq (ioq_vector->iq, ioq_vector->oq);return rx_done; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 202/265 octeon_ep: avoid compiler and IQ/OQ reordering
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vimlesh Kumar <[email protected]>
[ Upstream commit 43b3160cb639079a15daeb5f080120afbfbfc918 ]
Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx variable access to prevent compiler optimization and reordering. Additionally, ensure IO queue OUT/IN_CNT registers are flushed by performing a read-back after writing.
The compiler could reorder reads/writes to pkts_pending, last_pkt_count, etc., causing stale values to be used when calculating packets to process or register updates to send to hardware. The Octeon hardware requires a read-back after writing to OUT_CNT/IN_CNT registers to ensure the write has been flushed through any posted write buffers before the interrupt resend bit is set. Without this, we have observed cases where the hardware didn't properly update its internal state.
wmb/rmb only provides ordering guarantees but doesn't prevent the compiler from performing optimizations like caching in registers, load tearing etc.
--- .../ethernet/marvell/octeon_ep/octep_main.c | 21 +++++++++------ .../net/ethernet/marvell/octeon_ep/octep_rx.c | 27 +++++++++++++------ 2 files changed, 32 insertions(+), 16 deletions(-)
drivers/net/ethernet/marvell/octeon_ep/octep_main.c +13 -8
@@ -562,17 +562,22 @@ static void octep_clean_irqs(struct octep_device *oct)*/ static void octep_update_pkt (struct octep_iq *iq,struct octep_oq *oq) { -u32 pkts_pend = oq->pkts_pending; +u32 pkts_pend =READ_ONCE (oq->pkts_pending); +u32 last_pkt_count =READ_ONCE (oq->last_pkt_count); +u32 pkts_processed =READ_ONCE (iq->pkts_processed); +u32 pkt_in_done =READ_ONCE (iq->pkt_in_done);netdev_dbg (iq->netdev,"enabling intr for Q-%u\n" , iq->q_no); -if (iq->pkts_processed) { -writel (iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed =0 ; +if (pkts_processed) { +writel (pkts_processed, iq->inst_cnt_reg); +readl (iq->inst_cnt_reg); +WRITE_ONCE (iq->pkt_in_done, (pkt_in_done - pkts_processed)); +WRITE_ONCE (iq->pkts_processed,0 ); } -if (oq->last_pkt_count - pkts_pend) { -writel (oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; +if (last_pkt_count - pkts_pend) { +writel (last_pkt_count - pkts_pend, oq->pkts_sent_reg); +readl (oq->pkts_sent_reg); +WRITE_ONCE (oq->last_pkt_count, pkts_pend); }/* Flush the previous wrties before writing to RESEND bit */
drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +19 -8
@@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, struct octep_oq *oq) {u32 pkt_count, new_pkts; +u32 last_pkt_count, pkts_pending; pkt_count =readl (oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count =READ_ONCE (oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; +if (pkt_count < last_pkt_count) { +dev_err (oq->dev,"OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n" , + oq->q_no, pkt_count, last_pkt_count); + }/* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and * reached half its max value.
@@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, pkt_count =readl (oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; +WRITE_ONCE (oq->last_pkt_count, pkt_count); + pkts_pending =READ_ONCE (oq->pkts_pending); +WRITE_ONCE (oq->pkts_pending, (pkts_pending + new_pkts));return new_pkts; }
@@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,u16 rx_ol_flags;u32 read_idx; - read_idx = oq->host_read_idx; + read_idx =READ_ONCE (oq->host_read_idx); rx_bytes =0 ; desc_used =0 ;for (pkt =0 ; pkt < pkts_to_process; pkt++) {
@@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,napi_gro_receive (oq->napi, skb); } - oq->host_read_idx = read_idx; +WRITE_ONCE (oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes;
@@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget) {u32 pkts_available, pkts_processed, total_pkts_processed;struct octep_device *oct = oq->octep_dev; +u32 pkts_pending; pkts_available =0 ; pkts_processed =0 ; total_pkts_processed =0 ;while (total_pkts_processed < budget) {/* update pending count only when current one exhausted */ -if (oq->pkts_pending ==0 ) + pkts_pending =READ_ONCE (oq->pkts_pending); +if (pkts_pending ==0 )octep_oq_check_hw_for_pkts (oct, oq); + pkts_pending =READ_ONCE (oq->pkts_pending); pkts_available =min (budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending);if (!pkts_available)break ; pkts_processed =__octep_oq_process_rx (oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending =READ_ONCE (oq->pkts_pending); +WRITE_ONCE (oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 203/265 octeon_ep_vf: Relocate counter updates before NAPI
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vimlesh Kumar <[email protected]>
[ Upstream commit 2ae7d20fb24f598f60faa8f6ecc856dac782261a ]
Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion. Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly synchronized.
--- .../marvell/octeon_ep_vf/octep_vf_main.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +15 -2
@@ -288,12 +288,13 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct) }/** -* octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. +* octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_vf_enable_ioq_irq (struct octep_vf_iq *iq,struct octep_vf_oq *oq) + +static void octep_vf_update_pkt (struct octep_vf_iq *iq,struct octep_vf_oq *oq) {u32 pkts_pend = oq->pkts_pending;
@@ -310,6 +311,17 @@ static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq */* Flush the previous wrties before writing to RESEND bit */ smp_wmb (); +} + +/** +* octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. +* +* @iq: Octeon Tx queue data structure. +* @oq: Octeon Rx queue data structure. +*/ +static void octep_vf_enable_ioq_irq (struct octep_vf_iq *iq, +struct octep_vf_oq *oq) +{writeq (1UL <<OCTEP_VF_OQ_INTR_RESEND_BIT , oq->pkts_sent_reg);writeq (1UL <<OCTEP_VF_IQ_INTR_RESEND_BIT , iq->inst_cnt_reg); }
@@ -335,6 +347,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget)if (tx_pending || rx_done >= budget)return budget; +octep_vf_update_pkt (ioq_vector->iq, ioq_vector->oq);if (likely (napi_complete_done (napi, rx_done)))octep_vf_enable_ioq_irq (ioq_vector->iq, ioq_vector->oq);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 204/265 octeon_ep_vf: avoid compiler and IQ/OQ reordering
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vimlesh Kumar <[email protected]>
[ Upstream commit 6c73126ecd1080351b468fe43353b2f705487f44 ]
Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx variable access to prevent compiler optimization and reordering. Additionally, ensure IO queue OUT/IN_CNT registers are flushed by performing a read-back after writing.
The compiler could reorder reads/writes to pkts_pending, last_pkt_count, etc., causing stale values to be used when calculating packets to process or register updates to send to hardware. The Octeon hardware requires a read-back after writing to OUT_CNT/IN_CNT registers to ensure the write has been flushed through any posted write buffers before the interrupt resend bit is set. Without this, we have observed cases where the hardware didn't properly update its internal state.
wmb/rmb only provides ordering guarantees but doesn't prevent the compiler from performing optimizations like caching in registers, load tearing etc.
--- .../marvell/octeon_ep_vf/octep_vf_main.c | 21 ++++++++------ .../marvell/octeon_ep_vf/octep_vf_rx.c | 28 +++++++++++++------ 2 files changed, 33 insertions(+), 16 deletions(-)
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +13 -8
@@ -296,17 +296,22 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)static void octep_vf_update_pkt (struct octep_vf_iq *iq,struct octep_vf_oq *oq) { -u32 pkts_pend = oq->pkts_pending; +u32 pkts_pend =READ_ONCE (oq->pkts_pending); +u32 last_pkt_count =READ_ONCE (oq->last_pkt_count); +u32 pkts_processed =READ_ONCE (iq->pkts_processed); +u32 pkt_in_done =READ_ONCE (iq->pkt_in_done);netdev_dbg (iq->netdev,"enabling intr for Q-%u\n" , iq->q_no); -if (iq->pkts_processed) { -writel (iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed =0 ; +if (pkts_processed) { +writel (pkts_processed, iq->inst_cnt_reg); +readl (iq->inst_cnt_reg); +WRITE_ONCE (iq->pkt_in_done, (pkt_in_done - pkts_processed)); +WRITE_ONCE (iq->pkts_processed,0 ); } -if (oq->last_pkt_count - pkts_pend) { -writel (oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; +if (last_pkt_count - pkts_pend) { +writel (last_pkt_count - pkts_pend, oq->pkts_sent_reg); +readl (oq->pkts_sent_reg); +WRITE_ONCE (oq->last_pkt_count, pkts_pend); }/* Flush the previous wrties before writing to RESEND bit */
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +20 -8
@@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, struct octep_vf_oq *oq) {u32 pkt_count, new_pkts; +u32 last_pkt_count, pkts_pending; pkt_count =readl (oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count =READ_ONCE (oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + +if (pkt_count < last_pkt_count) { +dev_err (oq->dev,"OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n" , + oq->q_no, pkt_count, last_pkt_count); + }/* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and
@@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, pkt_count =readl (oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; +WRITE_ONCE (oq->last_pkt_count, pkt_count); + pkts_pending =READ_ONCE (oq->pkts_pending); +WRITE_ONCE (oq->pkts_pending, (pkts_pending + new_pkts));return new_pkts; }
@@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,struct sk_buff *skb;u32 read_idx; - read_idx = oq->host_read_idx; + read_idx =READ_ONCE (oq->host_read_idx); rx_bytes =0 ; desc_used =0 ;for (pkt =0 ; pkt < pkts_to_process; pkt++) {
@@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,napi_gro_receive (oq->napi, skb); } - oq->host_read_idx = read_idx; +WRITE_ONCE (oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes;
@@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget) {u32 pkts_available, pkts_processed, total_pkts_processed;struct octep_vf_device *oct = oq->octep_vf_dev; +u32 pkts_pending; pkts_available =0 ; pkts_processed =0 ; total_pkts_processed =0 ;while (total_pkts_processed < budget) {/* update pending count only when current one exhausted */ -if (oq->pkts_pending ==0 ) + pkts_pending =READ_ONCE (oq->pkts_pending); +if (pkts_pending ==0 )octep_vf_oq_check_hw_for_pkts (oct, oq); + pkts_pending =READ_ONCE (oq->pkts_pending); pkts_available =min (budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending);if (!pkts_available)break ; pkts_processed =__octep_vf_oq_process_rx (oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending =READ_ONCE (oq->pkts_pending); +WRITE_ONCE (oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 205/265 wifi: cw1200: Fix locking in error paths
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bart Van Assche <[email protected]>
[ Upstream commit d98c24617a831e92e7224a07dcaed2dd0b02af96 ]
cw1200_wow_suspend() must only return with priv->conf_mutex locked if it returns zero. This mutex must be unlocked if an error is returned. Add mutex_unlock() calls to the error paths from which that call is missing. This has been detected by the Clang thread-safety analyzer.
--- drivers/net/wireless/st/cw1200/pm.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/net/wireless/st/cw1200/pm.c +2 -0
@@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)wiphy_err (priv->hw->wiphy,"PM request failed: %d. WoW is disabled.\n" , ret);cw1200_wow_resume (hw); +mutex_unlock (&priv->conf_mutex);return -EBUSY ; }/* Force resume if event is coming from the device. */ if (atomic_read (&priv->bh_rx)) {cw1200_wow_resume (hw); +mutex_unlock (&priv->conf_mutex);return -EAGAIN ; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 206/265 wifi: wlcore: Fix a locking bug
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bart Van Assche <[email protected]>
[ Upstream commit 72c6df8f284b3a49812ce2ac136727ace70acc7c ]
Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.
--- drivers/net/wireless/ti/wlcore/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/ti/wlcore/main.c +2 -2
@@ -1879,6 +1879,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) wl->wow_enabled);WARN_ON (!wl->wow_enabled); +mutex_lock (&wl->mutex); + ret =pm_runtime_force_resume (wl->dev);if (ret <0 ) {wl1271_error ("ELP wakeup failure!" );
@@ -1895,8 +1897,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) run_irq_work = true;spin_unlock_irqrestore (&wl->wl_lock, flags); -mutex_lock (&wl->mutex); -/* test the recovery flag before calling any SDIO functions */ pending_recovery =test_bit (WL1271_FLAG_RECOVERY_IN_PROGRESS , &wl->flags);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 207/265 wifi: mt76: mt7996: Fix possible oob access in mt7996_mac_write_txwi_80211()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lorenzo Bianconi <[email protected]>
[ Upstream commit 60862846308627e9e15546bb647a00de44deb27b ]
Check frame length before accessing the mgmt fields in mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.
--- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/wireless/mediatek/mt76/mt7996/mac.c +1 -0
@@ -759,6 +759,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,u32 val;if (ieee80211_is_action (fc) && + skb->len >=IEEE80211_MIN_ACTION_SIZE +1 && mgmt->u.action.category ==WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code ==WLAN_ACTION_ADDBA_REQ ) tid =MT_TX_ADDBA ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 208/265 wifi: mt76: mt7925: Fix possible oob access in mt7925_mac_write_txwi_80211()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lorenzo Bianconi <[email protected]>
[ Upstream commit c41a9abd6ae31d130e8f332e7c8800c4c866234b ]
Check frame length before accessing the mgmt fields in mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.
--- drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/wireless/mediatek/mt76/mt7925/mac.c +1 -0
@@ -671,6 +671,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,u32 val;if (ieee80211_is_action (fc) && + skb->len >=IEEE80211_MIN_ACTION_SIZE +1 && mgmt->u.action.category ==WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code ==WLAN_ACTION_ADDBA_REQ ) tid =MT_TX_ADDBA ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 209/265 wifi: mt76: Fix possible oob access in mt76_connac2_mac_write_txwi_80211()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lorenzo Bianconi <[email protected]>
[ Upstream commit 4e10a730d1b511ff49723371ed6d694dd1b2c785 ]
Check frame length before accessing the mgmt fields in mt76_connac2_mac_write_txwi_80211 in order to avoid a possible oob access.
[fix check to also cover mgmt->u.action.u.addba_req.capab, correct Fixes tag]
--- drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +1 -0
@@ -396,6 +396,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,u32 val;if (ieee80211_is_action (fc) && + skb->len >=IEEE80211_MIN_ACTION_SIZE +1 +1 +2 && mgmt->u.action.category ==WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code ==WLAN_ACTION_ADDBA_REQ ) {u16 capab =le16_to_cpu (mgmt->u.action.u.addba_req.capab);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 210/265 indirect_call_wrapper: do not reevaluate function pointer
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit 710f5c76580306cdb9ec51fac8fcf6a8faff7821 ]
We have an increasing number of READ_ONCE(xxx->function) combined with INDIRECT_CALL_[1234]() helpers.
Unfortunately this forces INDIRECT_CALL_[1234]() to read xxx->function many times, which is not what we wanted.
Fix these macros so that xxx->function value is not reloaded.
$ scripts/bloat-o-meter -t vmlinux.0 vmlinux add/remove: 0/0 grow/shrink: 1/65 up/down: 122/-1084 (-962) Function old new delta ip_push_pending_frames 59 181 +122 ip6_finish_output 687 681 -6 __udp_enqueue_schedule_skb 1078 1072 -6 ioam6_output 2319 2312 -7 xfrm4_rcv_encap_finish2 64 56 -8 xfrm4_output 297 289 -8 vrf_ip_local_out 278 270 -8 vrf_ip6_local_out 278 270 -8 seg6_input_finish 64 56 -8 rpl_output 700 692 -8 ipmr_forward_finish 124 116 -8 ip_forward_finish 143 135 -8 ip6mr_forward2_finish 100 92 -8 ip6_forward_finish 73 65 -8 input_action_end_bpf 1091 1083 -8 dst_input 52 44 -8 __xfrm6_output 801 793 -8 __xfrm4_output 83 75 -8 bpf_input 500 491 -9 __tcp_check_space 530 521 -9 input_action_end_dt6 291 280 -11 vti6_tnl_xmit 1634 1622 -12 bpf_xmit 1203 1191 -12 rpl_input 497 483 -14 rawv6_send_hdrinc 1355 1341 -14 ndisc_send_skb 1030 1016 -14 ipv6_srh_rcv 1377 1363 -14 ip_send_unicast_reply 1253 1239 -14 ip_rcv_finish 226 212 -14 ip6_rcv_finish 300 286 -14 input_action_end_x_core 205 191 -14 input_action_end_x 355 341 -14 input_action_end_t 205 191 -14 input_action_end_dx6_finish 127 113 -14 input_action_end_dx4_finish 373 359 -14 input_action_end_dt4 426 412 -14 input_action_end_core 186 172 -14 input_action_end_b6_encap 292 278 -14 input_action_end_b6 198 184 -14 igmp6_send 1332 1318 -14 ip_sublist_rcv 864 848 -16 ip6_sublist_rcv 1091 1075 -16 ipv6_rpl_srh_rcv 1937 1920 -17 xfrm_policy_queue_process 1246 1228 -18 seg6_output_core 903 885 -18 mld_sendpack 856 836 -20 NF_HOOK 756 736 -20 vti_tunnel_xmit 1447 1426 -21 input_action_end_dx6 664 642 -22 input_action_end 1502 1480 -22 sock_sendmsg_nosec 134 111 -23 ip6mr_forward2 388 364 -24 sock_recvmsg_nosec 134 109 -25 seg6_input_core 836 810 -26 ip_send_skb 172 146 -26 ip_local_out 140 114 -26 ip6_local_out 140 114 -26 __sock_sendmsg 162 136 -26 __ip_queue_xmit 1196 1170 -26 __ip_finish_output 405 379 -26 ipmr_queue_fwd_xmit 373 346 -27 sock_recvmsg 173 145 -28 ip6_xmit 1635 1607 -28 xfrm_output_resume 1418 1389 -29 ip_build_and_send_pkt 625 591 -34 dst_output 504 432 -72 Total: Before=25217686, After=25216724, chg -0.00%
--- include/linux/indirect_call_wrapper.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-)
include/linux/indirect_call_wrapper.h +11 -7
@@ -16,22 +16,26 @@*/ #define INDIRECT_CALL_1 (f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ })#define INDIRECT_CALL_2 (f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ })#define INDIRECT_CALL_3 (f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ })#define INDIRECT_CALL_4 (f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ })#define INDIRECT_CALLABLE_DECLARE (f) f
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 211/265 net/rds: Fix circular locking dependency in rds_tcp_tune
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Allison Henderson <[email protected]>
[ Upstream commit 6a877ececd6daa002a9a0002cd0fbca6592a9244 ]
syzbot reported a circular locking dependency in rds_tcp_tune() where sk_net_refcnt_upgrade() is called while holding the socket lock:
======================================================
WARNING: possible circular locking dependency detected
======================================================
kworker/u10:8/15040 is trying to acquire lock:ffffffff8e9aaf80 (fs_reclaim){+.+.}-{0:0},
at: __kmalloc_cache_noprof+0x4b/0x6f0
but task is already holding lock:ffff88805a3c1ce0 (k-sk_lock-AF_INET6){+.+.}-{0:0},
at: rds_tcp_tune+0xd7/0x930
The issue occurs because sk_net_refcnt_upgrade() performs memory allocation (via get_net_track() -> ref_tracker_alloc()) while the socket lock is held, creating a circular dependency with fs_reclaim.
Fix this by moving sk_net_refcnt_upgrade() outside the socket lock critical section. This is safe because the fields modified by the sk_net_refcnt_upgrade() call (sk_net_refcnt, ns_tracker) are not accessed by any concurrent code path at this point.
v2:
- Corrected fixes tag
- check patch line wrap nits
- ai commentary nits
--- net/rds/tcp.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
net/rds/tcp.c +10 -4
@@ -495,18 +495,24 @@ bool rds_tcp_tune(struct socket *sock)struct rds_tcp_net *rtn;tcp_sock_set_nodelay (sock->sk); -lock_sock (sk);/* TCP timer functions might access net namespace even after * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { -if (!maybe_get_net (net)) { -release_sock (sk); +if (!maybe_get_net (net))return false; - } +/* +* sk_net_refcnt_upgrade() must be called before lock_sock() +* because it does a GFP_KERNEL allocation, which can trigger +* fs_reclaim and create a circular lock dependency with the +* socket lock. The fields it modifies (sk_net_refcnt, +* ns_tracker) are not accessed by any concurrent code path +* at this point. +*/ sk_net_refcnt_upgrade (sk);put_net (net); } +lock_sock (sk); rtn =net_generic (net, rds_tcp_netid);if (rtn->sndbuf_size >0 ) { sk->sk_sndbuf = rtn->sndbuf_size;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 212/265 xen/acpi-processor: fix _CST detection using undersized evaluation buffer
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Thomson <[email protected]>
[ Upstream commit 8b57227d59a86fc06d4f09de08f98133680f2cae ]
read_acpi_id() attempts to evaluate _CST using a stack buffer of sizeof(union acpi_object) (48 bytes), but _CST returns a nested Package of sub-Packages (one per C-state, each containing a register descriptor, type, latency, and power) requiring hundreds of bytes. The evaluation always fails with AE_BUFFER_OVERFLOW.
On modern systems using FFH/MWAIT entry (where pblk is zero), this causes the function to return before setting the acpi_id_cst_present bit. In check_acpi_ids(), flags.power is then zero for all Phase 2 CPUs (physical CPUs beyond dom0's vCPU count), so push_cxx_to_hypervisor() is never called for them.
On a system with dom0_max_vcpus=2 and 8 physical CPUs, only PCPUs 0-1 receive C-state data. PCPUs 2-7 are stuck in C0/C1 idle, unable to enter C2/C3. This costs measurable wall power (4W observed on an Intel Core Ultra 7 265K with Xen 4.20).
The function never uses the _CST return value -- it only needs to know whether _CST exists. Replace the broken acpi_evaluate_object() call with acpi_has_method(), which correctly detects _CST presence using acpi_get_handle() without any buffer allocation. This brings C-state detection to parity with the P-state path, which already works correctly for Phase 2 CPUs.
Message-ID: <[email protected]>
--- drivers/xen/xen-acpi-processor.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
drivers/xen/xen-acpi-processor.c +2 -5
@@ -379,11 +379,8 @@ read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv) acpi_psd[acpi_id].domain); } - status =acpi_evaluate_object (handle,"_CST" ,NULL , &buffer); -if (ACPI_FAILURE (status)) { -if (!pblk) -return AE_OK ; - } +if (!pblk && !acpi_has_method (handle,"_CST" )) +return AE_OK ;/* .. and it has a C-state */ __set_bit (acpi_id, acpi_id_cst_present);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 213/265 iavf: fix netdev->max_mtu to respect actual hardware limit
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kohei Enju <[email protected]>
[ Upstream commit b84852170153671bb0fa6737a6e48370addd8e1a ]
iavf sets LIBIE_MAX_MTU as netdev->max_mtu, ignoring vf_res->max_mtu from PF [1]. This allows setting an MTU beyond the actual hardware limit, causing TX queue timeouts [2].
Set correct netdev->max_mtu using vf_res->max_mtu from the PF.
Note that currently PF drivers such as ice/i40e set the frame size in vf_res->max_mtu, not MTU. Convert vf_res->max_mtu to MTU before setting netdev->max_mtu.
[1]
# ip -j -d link show $DEV | jq '.[0].max_mtu' 16356
[2]
iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 1: transmit queue 0 timed out 5692 ms iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex iavf 0000:00:05.0 enp0s5: NETDEV WATCHDOG: CPU: 6: transmit queue 3 timed out 5312 ms iavf 0000:00:05.0 enp0s5: NIC Link is Up Speed is 10 Gbps Full Duplex
...
--- drivers/net/ethernet/intel/iavf/iavf_main.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-)
drivers/net/ethernet/intel/iavf/iavf_main.c +16 -1
@@ -2630,7 +2630,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netdev->watchdog_timeo =5 *HZ ; netdev->min_mtu =ETH_MIN_MTU ; - netdev->max_mtu =LIBIE_MAX_MTU ; + +/* PF/VF API: vf_res->max_mtu is max frame size (not MTU). +* Convert to MTU. +*/ +if (!adapter->vf_res->max_mtu) { + netdev->max_mtu =LIBIE_MAX_MTU ; + }else if (adapter->vf_res->max_mtu <LIBETH_RX_LL_LEN +ETH_MIN_MTU || + adapter->vf_res->max_mtu > +LIBETH_RX_LL_LEN +LIBIE_MAX_MTU ) { +netdev_warn_once (adapter->netdev, +"invalid max frame size %d from PF, using default MTU %d" , + adapter->vf_res->max_mtu,LIBIE_MAX_MTU ); + netdev->max_mtu =LIBIE_MAX_MTU ; + }else { + netdev->max_mtu = adapter->vf_res->max_mtu -LIBETH_RX_LL_LEN ; + }if (!is_valid_ether_addr (adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 214/265 bpf: Fix a UAF issue in bpf_trampoline_link_cgroup_shim
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lang Xu <[email protected]>
[ Upstream commit 56145d237385ca0e7ca9ff7b226aaf2eb8ef368b ]
The root cause of this bug is that when 'bpf_link_put' reduces the refcount of 'shim_link->link.link' to zero, the resource is considered released but may still be referenced via 'tr->progs_hlist' in 'cgroup_shim_find'. The actual cleanup of 'tr->progs_hlist' in 'bpf_shim_tramp_link_release' is deferred. During this window, another process can cause a use-after-free via 'bpf_trampoline_link_cgroup_shim'.
Based on Martin KaFai Lau's suggestions, I have created a simple patch.
To fix this:
Add an atomic non-zero check in 'bpf_trampoline_link_cgroup_shim'. Only increment the refcount if it is not already zero.
Testing:
I verified the fix by adding a delay in 'bpf_shim_tramp_link_release' to make the bug easier to trigger:
static void bpf_shim_tramp_link_release(struct bpf_link *link)
{
/* ... */
if (!shim_link->trampoline)
return;+ msleep(100); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline, NULL)); bpf_trampoline_put(shim_link->trampoline); }
Before the patch, running a PoC easily reproduced the crash(almost 100%) with a call trace similar to KaiyanM's report.
After the patch, the bug no longer occurs even after millions of iterations.
--- kernel/bpf/trampoline.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
kernel/bpf/trampoline.c +1 -3
@@ -749,10 +749,8 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,mutex_lock (&tr->mutex); shim_link =cgroup_shim_find (tr, bpf_func); -if (shim_link) { +if (shim_link && !IS_ERR (bpf_link_inc_not_zero (&shim_link->link.link))) {/* Reusing existing shim attached by the other program. */ -bpf_link_inc (&shim_link->link.link); -mutex_unlock (&tr->mutex);bpf_trampoline_put (tr);/* bpf_trampoline_get above */ return 0 ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 215/265 smb/client: fix buffer size for smb311_posix_qinfo in smb2_compound_op()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: ZhangGuoDong <[email protected]>
[ Upstream commit 12c43a062acb0ac137fc2a4a106d4d084b8c5416 ]
Use sizeof(struct smb311_posix_qinfo) instead of sizeof its pointer, so the allocated buffer matches the actual struct size.
--- fs/smb/client/smb2inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
fs/smb/client/smb2inode.c +2 -2
@@ -315,7 +315,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, cfile->fid.volatile_fid,SMB_FIND_FILE_POSIX_INFO ,SMB2_O_INFO_FILE ,0 , -sizeof (struct smb311_posix_qinfo *) + +sizeof (struct smb311_posix_qinfo ) + (PATH_MAX *2 ) + (sizeof(struct smb_sid) * 2), 0, NULL); }else {
@@ -325,7 +325,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,COMPOUND_FID ,SMB_FIND_FILE_POSIX_INFO ,SMB2_O_INFO_FILE ,0 , -sizeof (struct smb311_posix_qinfo *) + +sizeof (struct smb311_posix_qinfo ) + (PATH_MAX *2 ) + (sizeof(struct smb_sid) * 2), 0, NULL); }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 216/265 smb/client: fix buffer size for smb311_posix_qinfo in SMB311_posix_query_info()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: ZhangGuoDong <[email protected]>
[ Upstream commit 9621b996e4db1dbc2b3dc5d5910b7d6179397320 ]
SMB311_posix_query_info() is currently unused, but it may still be used in some stable versions, so these changes are submitted as a separate patch.
Use sizeof(struct smb311_posix_qinfo) instead of sizeof its pointer, so the allocated buffer matches the actual struct size.
--- fs/smb/client/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/smb/client/smb2pdu.c +1 -1
@@ -3933,7 +3933,7 @@ int SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct smb311_posix_qinfo *data, u32 *plen) { - size_t output_len = sizeof(struct smb311_posix_qinfo *) + + size_t output_len = sizeof(struct smb311_posix_qinfo) + (sizeof (struct smb_sid ) *2 ) + (PATH_MAX *2 ); *plen =0 ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 217/265 ipv6: fix NULL pointer deref in ip6_rt_get_dev_rcu()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit 2ffb4f5c2ccb2fa1c049dd11899aee7967deef5a ]
l3mdev_master_dev_rcu() can return NULL when the slave device is being un-slaved from a VRF. All other callers deal with this, but we lost the fallback to loopback in ip6_rt_pcpu_alloc() -> ip6_rt_get_dev_rcu() with commit 4832c30d5458 ("net: ipv6: put host and anycast routes on device with address").
KASAN: null-ptr-deref in range [0x0000000000000108-0x000000000000010f] RIP: 0010:ip6_rt_pcpu_alloc (net/ipv6/route.c:1418) Call Trace: ip6_pol_route (net/ipv6/route.c:2318) fib6_rule_lookup (net/ipv6/fib6_rules.c:115) ip6_route_output_flags (net/ipv6/route.c:2607) vrf_process_v6_outbound (drivers/net/vrf.c:437)
I was tempted to rework the un-slaving code to clear the flag first and insert synchronize_rcu() before we remove the upper. But looks like the explicit fallback to loopback_dev is an established pattern. And I guess avoiding the synchronize_rcu() is nice, too.
--- net/ipv6/route.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/ipv6/route.c +2 -1
@@ -1064,7 +1064,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)*/ if (netif_is_l3_slave (dev) && !rt6_need_strict (&res->f6i->fib6_dst.addr)) - dev =l3mdev_master_dev_rcu (dev); + dev =l3mdev_master_dev_rcu (dev) ? : +dev_net (dev)->loopback_dev;else if (!netif_is_l3_master (dev)) dev =dev_net (dev)->loopback_dev;/* last case is netif_is_l3_master(dev) is true in which
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 218/265 net: ipv4: fix ARM64 alignment fault in multipath hash seed
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yung Chih Su <[email protected]>
[ Upstream commit 4ee7fa6cf78ff26d783d39e2949d14c4c1cd5e7f ]
struct sysctl_fib_multipath_hash_seed contains two u32 fields (user_seed and mp_seed), making it an 8-byte structure with a 4-byte alignment requirement.
In fib_multipath_hash_from_keys(), the code evaluates the entire struct atomically via READ_ONCE():
mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed;
While this silently works on GCC by falling back to unaligned regular loads which the ARM64 kernel tolerates, it causes a fatal kernel panic when compiled with Clang and LTO enabled.
Commit e35123d83ee3 ("arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y") strengthens READ_ONCE() to use Load-Acquire instructions (ldar / ldapr) to prevent compiler reordering bugs under Clang LTO. Since the macro evaluates the full 8-byte struct, Clang emits a 64-bit ldar instruction. ARM64 architecture strictly requires ldar to be naturally aligned, thus executing it on a 4-byte aligned address triggers a strict Alignment Fault (FSC = 0x21).
Fix the read side by moving the READ_ONCE() directly to the u32 member, which emits a safe 32-bit ldar Wn.
Furthermore, Eric Dumazet pointed out that WRITE_ONCE() on the entire struct in proc_fib_multipath_hash_set_seed() is also flawed. Analysis shows that Clang splits this 8-byte write into two separate 32-bit str instructions. While this avoids an alignment fault, it destroys atomicity and exposes a tear-write vulnerability. Fix this by explicitly splitting the write into two 32-bit WRITE_ONCE() operations.
Finally, add the missing READ_ONCE() when reading user_seed in proc_fib_multipath_hash_seed() to ensure proper pairing and concurrency safety.
--- include/net/ip_fib.h | 2 +- net/ipv4/sysctl_net_ipv4.c | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-)
include/net/ip_fib.h +1 -1
@@ -544,7 +544,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net,siphash_aligned_key_t hash_key;u32 mp_seed; - mp_seed =READ_ONCE (net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + mp_seed =READ_ONCE (net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed);fib_multipath_hash_construct_key (&hash_key, mp_seed);return flow_hash_from_keys_seed (keys, &hash_key);
net/ipv4/sysctl_net_ipv4.c +3 -2
@@ -481,7 +481,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) proc_fib_multipath_hash_rand_seed), }; -WRITE_ONCE (net->ipv4.sysctl_fib_multipath_hash_seed, new); +WRITE_ONCE (net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed); +WRITE_ONCE (net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write,
@@ -495,7 +496,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int writeint ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; - user_seed = mphs->user_seed; + user_seed =READ_ONCE (mphs->user_seed); tmp = *table; tmp.data = &user_seed;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 219/265 amd-xgbe: fix sleep while atomic on suspend/resume
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Raju Rangoju <[email protected]>
[ Upstream commit e2f27363aa6d983504c6836dd0975535e2e9dba0 ]
The xgbe_powerdown() and xgbe_powerup() functions use spinlocks (spin_lock_irqsave) while calling functions that may sleep:
- napi_disable() can sleep waiting for NAPI polling to complete
- flush_workqueue() can sleep waiting for pending work items
This causes a "BUG: scheduling while atomic" error during suspend/resume cycles on systems using the AMD XGBE Ethernet controller.
The spinlock protection in these functions is unnecessary as these functions are called from suspend/resume paths which are already serialized by the PM core
Fix this by removing the spinlock. Since only code that takes this lock is xgbe_powerdown() and xgbe_powerup(), remove it completely.
--- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 10 ---------- drivers/net/ethernet/amd/xgbe/xgbe-main.c | 1 - drivers/net/ethernet/amd/xgbe/xgbe.h | 3 --- 3 files changed, 14 deletions(-)
drivers/net/ethernet/amd/xgbe/xgbe-drv.c +0 -10
@@ -1181,7 +1181,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) {struct xgbe_prv_data *pdata =netdev_priv (netdev);struct xgbe_hw_if *hw_if = &pdata->hw_if; -unsigned long flags;DBGPR ("-->xgbe_powerdown\n" );
@@ -1192,8 +1191,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller)return -EINVAL ; } -spin_lock_irqsave (&pdata->lock, flags); -if (caller ==XGMAC_DRIVER_CONTEXT )netif_device_detach (netdev);
@@ -1209,8 +1206,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) pdata->power_down =1 ; -spin_unlock_irqrestore (&pdata->lock, flags); -DBGPR ("<--xgbe_powerdown\n" );return 0 ;
@@ -1220,7 +1215,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) {struct xgbe_prv_data *pdata =netdev_priv (netdev);struct xgbe_hw_if *hw_if = &pdata->hw_if; -unsigned long flags;DBGPR ("-->xgbe_powerup\n" );
@@ -1231,8 +1225,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)return -EINVAL ; } -spin_lock_irqsave (&pdata->lock, flags); - pdata->power_down =0 ;xgbe_napi_enable (pdata,0 );
@@ -1247,8 +1239,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller)xgbe_start_timers (pdata); -spin_unlock_irqrestore (&pdata->lock, flags); -DBGPR ("<--xgbe_powerup\n" );return 0 ;
drivers/net/ethernet/amd/xgbe/xgbe-main.c +0 -1
@@ -185,7 +185,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev) pdata->netdev = netdev; pdata->dev = dev; -spin_lock_init (&pdata->lock);spin_lock_init (&pdata->xpcs_lock);mutex_init (&pdata->rss_mutex);spin_lock_init (&pdata->tstamp_lock);
drivers/net/ethernet/amd/xgbe/xgbe.h +0 -3
@@ -1083,9 +1083,6 @@ struct xgbe_prv_data {unsigned int pp3;unsigned int pp4; -/* Overall device lock */ -spinlock_t lock; -/* XPCS indirect addressing lock */ spinlock_t xpcs_lock;unsigned int xpcs_window_def_reg;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 220/265 drm/sched: Fix kernel-doc warning for drm_sched_job_done()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yujie Liu <[email protected]>
[ Upstream commit 61ded1083b264ff67ca8c2de822c66b6febaf9a8 ]
There is a kernel-doc warning for the scheduler:
Warning: drivers/gpu/drm/scheduler/sched_main.c:367 function parameter 'result' not described in 'drm_sched_job_done'
Fix the warning by describing the undocumented error code.
--- drivers/gpu/drm/scheduler/sched_main.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/scheduler/sched_main.c +1 -0
@@ -404,6 +404,7 @@ static void drm_sched_run_free_queue(struct drm_gpu_scheduler *sched)/** * drm_sched_job_done - complete a job * @s_job: pointer to the job which is done +* @result: 0 on success, -ERRNO on error * * Finish the job's fence and wake up the worker thread. */
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 221/265 i2c: i801: Revert "i2c: i801: replace acpi_lock with I2C bus lock"
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Charles Haithcock <[email protected]>
[ Upstream commit cfc69c2e6c699c96949f7b0455195b0bfb7dc715 ]
This reverts commit f707d6b9e7c18f669adfdb443906d46cfbaaa0c1.
Under rare circumstances, multiple udev threads can collect i801 device info on boot and walk i801_acpi_io_handler somewhat concurrently. The first will note the area is reserved by acpi to prevent further touches. This ultimately causes the area to be deregistered. The second will enter i801_acpi_io_handler after the area is unregistered but before a check can be made that the area is unregistered. i2c_lock_bus relies on the now unregistered area containing lock_ops to lock the bus. The end result is a kernel panic on boot with the following backtrace;
[ 14.971872] ioatdma 0000:09:00.2: enabling device (0100 -> 0102) [ 14.971873] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 14.971880] #PF: supervisor read access in kernel mode [ 14.971884] #PF: error_code(0x0000) - not-present page [ 14.971887] PGD 0 P4D 0 [ 14.971894] Oops: 0000 [#1] PREEMPT SMP PTI [ 14.971900] CPU: 5 PID: 956 Comm: systemd-udevd Not tainted 5.14.0-611.5.1.el9_7.x86_64 #1 [ 14.971905] Hardware name: XXXXXXXXXXXXXXXXXXXXXXX BIOS 1.20.10.SV91 01/30/2023 [ 14.971908] RIP: 0010:i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.971929] Code: 00 00 49 8b 40 20 41 57 41 56 4d 8b b8 30 04 00 00 49 89 ce 41 55 41 89 d5 41 54 49 89 f4 be 02 00 00 00 55 4c 89 c5 53 89 fb <48> 8b 00 4c 89 c7 e8 18 61 54 e9 80 bd 80 04 00 00 00 75 09 4c 3b [ 14.971933] RSP: 0018:ffffbaa841483838 EFLAGS: 00010282 [ 14.971938] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff9685e01ba568 [ 14.971941] RDX: 0000000000000008 RSI: 0000000000000002 RDI: 0000000000000000 [ 14.971944] RBP: ffff9685ca22f028 R08: ffff9685ca22f028 R09: ffff9685ca22f028 [ 14.971948] R10: 000000000000000b R11: 0000000000000580 R12: 0000000000000580 [ 14.971951] R13: 0000000000000008 R14: ffff9685e01ba568 R15: ffff9685c222f000 [ 14.971954] FS: 00007f8287c0ab40(0000) GS:ffff96a47f940000(0000) knlGS:0000000000000000 [ 14.971959] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 14.971963] CR2: 0000000000000000 CR3: 0000000168090001 CR4: 00000000003706f0 [ 14.971966] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 14.971968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 14.971972] Call Trace: [ 14.971977] <TASK> [ 14.971981] ? show_trace_log_lvl+0x1c4/0x2df [ 14.971994] ? show_trace_log_lvl+0x1c4/0x2df [ 14.972003] ? acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972014] ? __die_body.cold+0x8/0xd [ 14.972021] ? page_fault_oops+0x132/0x170 [ 14.972028] ? exc_page_fault+0x61/0x150 [ 14.972036] ? asm_exc_page_fault+0x22/0x30 [ 14.972045] ? i801_acpi_io_handler+0x2d/0xb0 [i2c_i801] [ 14.972061] acpi_ev_address_space_dispatch+0x16e/0x3c0 [ 14.972069] ? __pfx_i801_acpi_io_handler+0x10/0x10 [i2c_i801] [ 14.972085] acpi_ex_access_region+0x5b/0xd0 [ 14.972093] acpi_ex_field_datum_io+0x73/0x2e0 [ 14.972100] acpi_ex_read_data_from_field+0x8e/0x230 [ 14.972106] acpi_ex_resolve_node_to_value+0x23d/0x310 [ 14.972114] acpi_ds_evaluate_name_path+0xad/0x110 [ 14.972121] acpi_ds_exec_end_op+0x321/0x510 [ 14.972127] acpi_ps_parse_loop+0xf7/0x680 [ 14.972136] acpi_ps_parse_aml+0x17a/0x3d0 [ 14.972143] acpi_ps_execute_method+0x137/0x270 [ 14.972150] acpi_ns_evaluate+0x1f4/0x2e0 [ 14.972158] acpi_evaluate_object+0x134/0x2f0 [ 14.972164] acpi_evaluate_integer+0x50/0xe0 [ 14.972173] ? vsnprintf+0x24b/0x570 [ 14.972181] acpi_ac_get_state.part.0+0x23/0x70 [ 14.972189] get_ac_property+0x4e/0x60 [ 14.972195] power_supply_show_property+0x90/0x1f0 [ 14.972205] add_prop_uevent+0x29/0x90 [ 14.972213] power_supply_uevent+0x109/0x1d0 [ 14.972222] dev_uevent+0x10e/0x2f0 [ 14.972228] uevent_show+0x8e/0x100 [ 14.972236] dev_attr_show+0x19/0x40 [ 14.972246] sysfs_kf_seq_show+0x9b/0x100 [ 14.972253] seq_read_iter+0x120/0x4b0 [ 14.972262] ? selinux_file_permission+0x106/0x150 [ 14.972273] vfs_read+0x24f/0x3a0 [ 14.972284] ksys_read+0x5f/0xe0 [ 14.972291] do_syscall_64+0x5f/0xe0
...
The kernel panic is mitigated by setting limiting the count of udev children to 1. Revert to using the acpi_lock to continue protecting marking the area as owned by firmware without relying on a lock in a potentially unmapped region of memory.
--- drivers/i2c/busses/i2c-i801.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
drivers/i2c/busses/i2c-i801.c +10 -4
@@ -303,9 +303,10 @@ struct i801_priv {/* * If set to true the host controller registers are reserved for -* ACPI AML use. +* ACPI AML use. Needs extra protection by acpi_lock. */ bool acpi_reserved; +struct mutex acpi_lock; };#define FEATURE_SMBUS_PEC BIT(0)
@@ -893,8 +894,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,int hwpec, ret;struct i801_priv *priv =i2c_get_adapdata (adap); -if (priv->acpi_reserved) +mutex_lock (&priv->acpi_lock); +if (priv->acpi_reserved) { +mutex_unlock (&priv->acpi_lock);return -EBUSY ; + }pm_runtime_get_sync (&priv->pci_dev->dev);
@@ -935,6 +939,7 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,pm_runtime_mark_last_busy (&priv->pci_dev->dev);pm_runtime_put_autosuspend (&priv->pci_dev->dev); +mutex_unlock (&priv->acpi_lock);return ret; }
@@ -1586,7 +1591,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,* further access from the driver itself. This device is now owned * by the system firmware. */ -i2c_lock_bus (&priv->adapter,I2C_LOCK_SEGMENT ); +mutex_lock (&priv->acpi_lock);if (!priv->acpi_reserved &&i801_acpi_is_smbus_ioport (priv, address)) { priv->acpi_reserved = true;
@@ -1606,7 +1611,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,else status =acpi_os_write_port (address, (u32)*value, bits); -i2c_unlock_bus (&priv->adapter,I2C_LOCK_SEGMENT ); +mutex_unlock (&priv->acpi_lock);return status; }
@@ -1666,6 +1671,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) priv->adapter.dev.parent = &dev->dev;acpi_use_parent_companion (&priv->adapter.dev); priv->adapter.retries =3 ; +mutex_init (&priv->acpi_lock); priv->pci_dev = dev; priv->features = id->driver_data;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 222/265 drm/xe/reg_sr: Fix leak on xa_store failure
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shuicheng Lin <[email protected]>
[ Upstream commit 3091723785def05ebfe6a50866f87a044ae314ba ]
Free the newly allocated entry when xa_store() fails to avoid a memory leak on the error path.
v2: use goto fail_free. (Bala)
--- drivers/gpu/drm/xe/xe_reg_sr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpu/drm/xe/xe_reg_sr.c +3 -1
@@ -102,10 +102,12 @@ int xe_reg_sr_add(struct xe_reg_sr *sr, *pentry = *e; ret =xa_err (xa_store (&sr->xa, idx, pentry,GFP_KERNEL ));if (ret) - goto fail; + goto fail_free;return 0 ; +fail_free: +kfree (pentry); fail: xe_gt_err(gt, "discarding save-restore reg %04lx (clear: %08x, set: %08x, masked: %s, mcr: %s): ret=%d\n",
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 223/265 nvme: reject invalid pr_read_keys() num_keys values
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Stefan Hajnoczi <[email protected]>
[ Upstream commit 38ec8469f39e0e96e7dd9b76f05e0f8eb78be681 ]
The pr_read_keys() interface has a u32 num_keys parameter. The NVMe Reservation Report command has a u32 maximum length. Reject num_keys values that are too large to fit.
This will become important when pr_read_keys() is exposed to untrusted userspace via an <linux/pr.h> ioctl.
Stable-dep-of: c3320153769f ("nvme: fix memory allocation in nvme_pr_read_keys()")
--- drivers/nvme/host/pr.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/nvme/host/pr.c +5 -1
@@ -200,7 +200,8 @@ static int nvme_pr_resv_report(struct block_device *bdev, void *data,static int nvme_pr_read_keys (struct block_device *bdev,struct pr_keys *keys_info) { -u32 rse_len, num_keys = keys_info->num_keys; +size_t rse_len; +u32 num_keys = keys_info->num_keys;struct nvme_reservation_status_ext *rse;int ret, i;bool eds;
@@ -210,6 +211,9 @@ static int nvme_pr_read_keys(struct block_device *bdev,* enough to get enough keys to fill the return keys buffer. */ rse_len =struct_size (rse, regctl_eds, num_keys); +if (rse_len >U32_MAX ) +return -EINVAL ; + rse =kzalloc (rse_len,GFP_KERNEL );if (!rse)return -ENOMEM ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 224/265 nvme: fix memory allocation in nvme_pr_read_keys()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sungwoo Kim <[email protected]>
[ Upstream commit c3320153769f05fd7fe9d840cb555dd3080ae424 ]
nvme_pr_read_keys() takes num_keys from userspace and uses it to calculate the allocation size for rse via struct_size(). The upper limit is PR_KEYS_MAX (64K).
A malicious or buggy userspace can pass a large num_keys value that results in a 4MB allocation attempt at most, causing a warning in the page allocator when the order exceeds MAX_PAGE_ORDER.
To fix this, use kvzalloc() instead of kzalloc().
This bug has the same reasoning and fix with the patch below:
https://lore.kernel.org/linux-block/[email protected]/
Warning log:
WARNING: mm/page_alloc.c:5216 at __alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216, CPU#1: syz-executor117/272 Modules linked in: CPU: 1 UID: 0 PID: 272 Comm: syz-executor117 Not tainted 6.19.0 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:__alloc_frozen_pages_noprof+0x5aa/0x2300 mm/page_alloc.c:5216 Code: ff 83 bd a8 fe ff ff 0a 0f 86 69 fb ff ff 0f b6 1d f9 f9 c4 04 80 fb 01 0f 87 3b 76 30 ff 83 e3 01 75 09 c6 05 e4 f9 c4 04 01 <0f> 0b 48 c7 85 70 fe ff ff 00 00 00 00 e9 8f fd ff ff 31 c0 e9 0d RSP: 0018:ffffc90000fcf450 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 1ffff920001f9ea0 RDX: 0000000000000000 RSI: 000000000000000b RDI: 0000000000040dc0 RBP: ffffc90000fcf648 R08: ffff88800b6c3380 R09: 0000000000000001 R10: ffffc90000fcf840 R11: ffff88807ffad280 R12: 0000000000000000 R13: 0000000000040dc0 R14: 0000000000000001 R15: ffffc90000fcf620 FS: 0000555565db33c0(0000) GS:ffff8880be26c000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000002000000c CR3: 0000000003b72000 CR4: 00000000000006f0 Call Trace: <TASK> alloc_pages_mpol+0x236/0x4d0 mm/mempolicy.c:2486 alloc_frozen_pages_noprof+0x149/0x180 mm/mempolicy.c:2557 ___kmalloc_large_node+0x10c/0x140 mm/slub.c:5598 __kmalloc_large_node_noprof+0x25/0xc0 mm/slub.c:5629 __do_kmalloc_node mm/slub.c:5645 [inline] __kmalloc_noprof+0x483/0x6f0 mm/slub.c:5669 kmalloc_noprof include/linux/slab.h:961 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] nvme_pr_read_keys+0x8f/0x4c0 drivers/nvme/host/pr.c:245 blkdev_pr_read_keys block/ioctl.c:456 [inline] blkdev_common_ioctl+0x1b71/0x29b0 block/ioctl.c:730 blkdev_ioctl+0x299/0x700 block/ioctl.c:786 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl fs/ioctl.c:583 [inline] __x64_sys_ioctl+0x1bf/0x220 fs/ioctl.c:583 x64_sys_call+0x1280/0x21b0 mnt/fuzznvme_1/fuzznvme/linux-build/v6.19/./arch/x86/include/generated/asm/syscalls_64.h:17 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x71/0x330 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7fb893d3108d Code: 28 c3 e8 46 1e 00 00 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffff61f2f38 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffff61f3138 RCX: 00007fb893d3108d RDX: 0000000020000040 RSI: 00000000c01070ce RDI: 0000000000000003 RBP: 0000000000000001 R08: 0000000000000000 R09: 00007ffff61f3138 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 R13: 00007ffff61f3128 R14: 00007fb893dae530 R15: 0000000000000001 </TASK>
--- drivers/nvme/host/pr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/nvme/host/pr.c +2 -2
@@ -214,7 +214,7 @@ static int nvme_pr_read_keys(struct block_device *bdev,if (rse_len >U32_MAX )return -EINVAL ; - rse =kzalloc (rse_len,GFP_KERNEL ); + rse =kvzalloc (rse_len,GFP_KERNEL );if (!rse)return -ENOMEM ;
@@ -239,7 +239,7 @@ static int nvme_pr_read_keys(struct block_device *bdev, } free_rse: -kfree (rse); +kvfree (rse);return ret; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 225/265 hwmon: (max6639) : Configure based on DT property
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Naresh Solanki <[email protected]>
[ Upstream commit 7506ebcd662b868780774d191a7c024c18c557a8 ]
Remove platform data & initialize with defaults
configuration & overwrite based on DT properties.
Message-ID: <[email protected]>
Stable-dep-of: 170a4b21f49b ("hwmon: (max6639) fix inverted polarity")
--- drivers/hwmon/max6639.c | 83 +++++++++++++++++++-------- include/linux/platform_data/max6639.h | 15 ----- 2 files changed, 60 insertions(+), 38 deletions(-) delete mode 100644 include/linux/platform_data/max6639.h
drivers/hwmon/max6639.c +60 -23
@@ -19,7 +19,6 @@#include <linux/hwmon-sysfs.h> #include <linux/err.h> #include <linux/mutex.h> -#include <linux/platform_data/max6639.h> #include <linux/regmap.h> #include <linux/util_macros.h>
@@ -531,14 +530,49 @@ static int rpm_range_to_reg(int range)return 1 ;/* default: 4000 RPM */ } +static int max6639_probe_child_from_dt (struct i2c_client *client, +struct device_node *child, +struct max6639_data *data) + +{ +struct device *dev = &client->dev; +u32 i; +int err, val; + + err =of_property_read_u32 (child,"reg" , &i); +if (err) { +dev_err (dev,"missing reg property of %pOFn\n" , child); +return err; + } + +if (i >1 ) { +dev_err (dev,"Invalid fan index reg %d\n" , i); +return -EINVAL ; + } + + err =of_property_read_u32 (child,"pulses-per-revolution" , &val); +if (!err) { +if (val <1 || val >5 ) { +dev_err (dev,"invalid pulses-per-revolution %d of %pOFn\n" , val, child); +return -EINVAL ; + } + data->ppr[i] = val; + } + + err =of_property_read_u32 (child,"max-rpm" , &val); +if (!err) + data->rpm_range[i] =rpm_range_to_reg (val); + +return 0 ; +} +static int max6639_init_client (struct i2c_client *client,struct max6639_data *data) { -struct max6639_platform_data *max6639_info = -dev_get_platdata (&client->dev); -int i; -int rpm_range =1 ;/* default: 4000 RPM */ -int err, ppr; +struct device *dev = &client->dev; +const struct device_node *np = dev->of_node; +struct device_node *child; +int i, err;/* Reset chip to default values, see below for GCONFIG setup */ err =regmap_write (data->regmap,MAX6639_REG_GCONFIG ,MAX6639_GCONFIG_POR );
@@ -546,21 +580,29 @@ static int max6639_init_client(struct i2c_client *client,return err;/* Fans pulse per revolution is 2 by default */ -if (max6639_info && max6639_info->ppr >0 && - max6639_info->ppr <5 ) - ppr = max6639_info->ppr; -else - ppr =2 ; + data->ppr[0 ] =2 ; + data->ppr[1 ] =2 ; + +/* default: 4000 RPM */ + data->rpm_range[0 ] =1 ; + data->rpm_range[1 ] =1 ; - data->ppr[0 ] = ppr; - data->ppr[1 ] = ppr; +for_each_child_of_node (np, child) { +if (strcmp (child->name,"fan" )) +continue ; -if (max6639_info) - rpm_range =rpm_range_to_reg (max6639_info->rpm_range); - data->rpm_range[0 ] = rpm_range; - data->rpm_range[1 ] = rpm_range; + err =max6639_probe_child_from_dt (client, child, data); +if (err) { +of_node_put (child); +return err; + } + }for (i =0 ; i <MAX6639_NUM_CHANNELS ; i++) { + err =regmap_set_bits (data->regmap,MAX6639_REG_OUTPUT_MASK ,BIT (1 - i)); +if (err) +return err; +/* Set Fan pulse per revolution */ err =max6639_set_ppr (data, i, data->ppr[i]);if (err)
@@ -573,12 +615,7 @@ static int max6639_init_client(struct i2c_client *client,return err;/* Fans PWM polarity high by default */ -if (max6639_info) { -if (max6639_info->pwm_polarity ==0 ) - err =regmap_write (data->regmap,MAX6639_REG_FAN_CONFIG2a (i),0x00 ); -else - err =regmap_write (data->regmap,MAX6639_REG_FAN_CONFIG2a (i),0x02 ); - } + err =regmap_write (data->regmap,MAX6639_REG_FAN_CONFIG2a (i),0x00 );if (err)return err;
include/linux/platform_data/max6639.h deleted +0 -15
@@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_MAX6639_H -#define _LINUX_MAX6639_H - -#include <linux/types.h> - -/* platform data for the MAX6639 temperature sensor and fan control */ - -struct max6639_platform_data { -bool pwm_polarity;/* Polarity low (0) or high (1, default) */ -int ppr;/* Pulses per rotation 1..4 (default == 2) */ -int rpm_range;/* 2000, 4000 (default), 8000 or 16000 */ -}; - -#endif /* _LINUX_MAX6639_H */
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 226/265 hwmon: (max6639) fix inverted polarity
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Olivier Sobrie <[email protected]>
[ Upstream commit 170a4b21f49b3dcff3115b4c90758f0a0d77375a ]
According to MAX6639 documentation:
D1: PWM Output Polarity. PWM output is low at 100% duty cycle when this bit is set to zero. PWM output is high at 100% duty cycle when this bit is set to 1.
Up to commit 0f33272b60ed ("hwmon: (max6639) : Update hwmon init using info structure"), the polarity was set to high (0x2) when no platform data was set. After the patch, the polarity register wasn't set anymore if no platform data was specified. Nowadays, since commit 7506ebcd662b ("hwmon: (max6639) : Configure based on DT property"), it is always set to low which doesn't match with the comment above and change the behavior compared to versions prior 0f33272b60ed.
--- drivers/hwmon/max6639.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/hwmon/max6639.c +1 -1
@@ -615,7 +615,7 @@ static int max6639_init_client(struct i2c_client *client,return err;/* Fans PWM polarity high by default */ - err =regmap_write (data->regmap,MAX6639_REG_FAN_CONFIG2a (i),0x00 ); + err =regmap_write (data->regmap,MAX6639_REG_FAN_CONFIG2a (i),0x02 );if (err)return err;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 227/265 net: sched: avoid qdisc_reset_all_tx_gt() vs dequeue race for lockless qdiscs
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Koichiro Den <[email protected]>
[ Upstream commit 7f083faf59d14c04e01ec05a7507f036c965acf8 ]
When shrinking the number of real tx queues, netif_set_real_num_tx_queues() calls qdisc_reset_all_tx_gt() to flush qdiscs for queues which will no longer be used.
qdisc_reset_all_tx_gt() currently serializes qdisc_reset() with qdisc_lock(). However, for lockless qdiscs, the dequeue path is serialized by qdisc_run_begin/end() using qdisc->seqlock instead, so qdisc_reset() can run concurrently with __qdisc_run() and free skbs while they are still being dequeued, leading to UAF.
This can easily be reproduced on e.g. virtio-net by imposing heavy traffic while frequently changing the number of queue pairs:
iperf3 -ub0 -c $peer -t 0 &
while :; do
ethtool -L eth0 combined 1
ethtool -L eth0 combined 2
done
With KASAN enabled, this leads to reports like:
BUG: KASAN: slab-use-after-free in __qdisc_run+0x133f/0x1760 ... Call Trace: <TASK> ... __qdisc_run+0x133f/0x1760 __dev_queue_xmit+0x248f/0x3550 ip_finish_output2+0xa42/0x2110 ip_output+0x1a7/0x410 ip_send_skb+0x2e6/0x480 udp_send_skb+0xb0a/0x1590 udp_sendmsg+0x13c9/0x1fc0 ... </TASK> Allocated by task 1270 on cpu 5 at 44.558414s: ... alloc_skb_with_frags+0x84/0x7c0 sock_alloc_send_pskb+0x69a/0x830 __ip_append_data+0x1b86/0x48c0 ip_make_skb+0x1e8/0x2b0 udp_sendmsg+0x13a6/0x1fc0 ... Freed by task 1306 on cpu 3 at 44.558445s: ... kmem_cache_free+0x117/0x5e0 pfifo_fast_reset+0x14d/0x580 qdisc_reset+0x9e/0x5f0 netif_set_real_num_tx_queues+0x303/0x840 virtnet_set_channels+0x1bf/0x260 [virtio_net] ethnl_set_channels+0x684/0xae0 ethnl_default_set_doit+0x31a/0x890 ...
Serialize qdisc_reset_all_tx_gt() against the lockless dequeue path by taking qdisc->seqlock for TCQ_F_NOLOCK qdiscs, matching the serialization model already used by dev_reset_queue().
Additionally clear QDISC_STATE_NON_EMPTY after reset so the qdisc state reflects an empty queue, avoiding needless re-scheduling.
--- include/net/sch_generic.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
include/net/sch_generic.h +10 -0
@@ -758,13 +758,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb)static inline void qdisc_reset_all_tx_gt (struct net_device *dev,unsigned int i) {struct Qdisc *qdisc; +bool nolock;for (; i < dev->num_tx_queues; i++) { qdisc =rtnl_dereference (netdev_get_tx_queue (dev, i)->qdisc);if (qdisc) { + nolock = qdisc->flags &TCQ_F_NOLOCK ; + +if (nolock) +spin_lock_bh (&qdisc->seqlock);spin_lock_bh (qdisc_lock (qdisc));qdisc_reset (qdisc);spin_unlock_bh (qdisc_lock (qdisc)); +if (nolock) { +clear_bit (__QDISC_STATE_MISSED, &qdisc->state); +clear_bit (__QDISC_STATE_DRAINING, &qdisc->state); +spin_unlock_bh (&qdisc->seqlock); + } } } }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 228/265 net: nfc: nci: Fix zero-length proprietary notifications
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ian Ray <[email protected]>
[ Upstream commit f7d92f11bd33a6eb49c7c812255ef4ab13681f0f ]
NCI NFC controllers may have proprietary OIDs with zero-length payload. One example is: drivers/nfc/nxp-nci/core.c, NXP_NCI_RF_TXLDO_ERROR_NTF.
Allow a zero length payload in proprietary notifications *only*.
Before:
-- >8 --
kernel: nci: nci_recv_frame: len 3
-- >8 --
After:
-- >8 --
kernel: nci: nci_recv_frame: len 3
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x23, plen=0
kernel: nci: nci_ntf_packet: unknown ntf opcode 0x123
kernel: nfc nfc0: NFC: RF transmitter couldn't start. Bad power and/or configuration? -- >8 --
After fixing the hardware:
-- >8 --
kernel: nci: nci_recv_frame: len 27
kernel: nci: nci_ntf_packet: NCI RX: MT=ntf, PBF=0, GID=0x1, OID=0x5, plen=24
kernel: nci: nci_rf_intf_activated_ntf_packet: rf_discovery_id 1 -- >8 --
--- net/nfc/nci/core.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)
net/nfc/nci/core.c +11 -1
@@ -1471,10 +1471,20 @@ static bool nci_valid_size(struct sk_buff *skb)unsigned int hdr_size =NCI_CTRL_HDR_SIZE ;if (skb->len < hdr_size || - !nci_plen (skb->data) || skb->len < hdr_size +nci_plen (skb->data)) {return false; } + +if (!nci_plen (skb->data)) { +/* Allow zero length in proprietary notifications (0x20 - 0x3F). */ +if (nci_opcode_oid (nci_opcode (skb->data)) >=0x20 && +nci_mt (skb->data) ==NCI_MT_NTF_PKT ) +return true; + +/* Disallow zero length otherwise. */ +return false; + } +return true; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 229/265 net_sched: sch_fq: clear q->band_pkt_count[] in fq_reset()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit a4c2b8be2e5329e7fac6e8f64ddcb8958155cfcb ]
When/if a NIC resets, queues are deactivated by dev_deactivate_many(), then reactivated when the reset operation completes.
fq_reset() removes all the skbs from various queues.
If we do not clear q->band_pkt_count[], these counters keep growing and can eventually reach sch->limit, preventing new packets to be queued.
Many thanks to Praveen for discovering the root cause.
--- net/sched/sch_fq.c | 1 + 1 file changed, 1 insertion(+)
net/sched/sch_fq.c +1 -0
@@ -815,6 +815,7 @@ static void fq_reset(struct Qdisc *sch)for (idx =0 ; idx <FQ_BANDS ; idx++) { q->band_flows[idx].new_flows.first =NULL ; q->band_flows[idx].old_flows.first =NULL ; + q->band_pkt_count[idx] =0 ; } q->delayed =RB_ROOT ; q->flows =0 ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 230/265 nfc: nci: free skb on nci_transceive early error paths
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit 7bd4b0c4779f978a6528c9b7937d2ca18e936e2c ]
nci_transceive() takes ownership of the skb passed by the caller, but the -EPROTO, -EINVAL, and -EBUSY error paths return without freeing it.
Due to issues clearing NCI_DATA_EXCHANGE fixed by subsequent changes the nci/nci_dev selftest hits the error path occasionally in NIPA, and kmemleak detects leaks:
unreferenced object 0xff11000015ce6a40 (size 640):
comm "nci_dev", pid 3954, jiffies 4295441246
hex dump (first 32 bytes):
6b 6b 6b 6b 00 a4 00 0c 02 e1 03 6b 6b 6b 6b 6b kkkk.......kkkkk 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk
backtrace (crc 7c40cc2a):
kmem_cache_alloc_node_noprof+0x492/0x630
__alloc_skb+0x11e/0x5f0
alloc_skb_with_frags+0xc6/0x8f0
sock_alloc_send_pskb+0x326/0x3f0
nfc_alloc_send_skb+0x94/0x1d0
rawsock_sendmsg+0x162/0x4c0
do_syscall_64+0x117/0xfc0--- net/nfc/nci/core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
net/nfc/nci/core.c +7 -2
@@ -1024,18 +1024,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; -if (!conn_info) +if (!conn_info) { +kfree_skb (skb);return -EPROTO ; + }pr_debug ("target_idx %d, len %d\n" , target->idx, skb->len);if (!ndev->target_active_prot) {pr_err ("unable to exchange data, no active target\n" ); +kfree_skb (skb);return -EINVAL ; } -if (test_and_set_bit (NCI_DATA_EXCHANGE , &ndev->flags)) +if (test_and_set_bit (NCI_DATA_EXCHANGE , &ndev->flags)) { +kfree_skb (skb);return -EBUSY ; + }/* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 231/265 nfc: nci: clear NCI_DATA_EXCHANGE before calling completion callback
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit 0efdc02f4f6d52f8ca5d5889560f325a836ce0a8 ]
Move clear_bit(NCI_DATA_EXCHANGE) before invoking the data exchange callback in nci_data_exchange_complete().
The callback (e.g. rawsock_data_exchange_complete) may immediately schedule another data exchange via schedule_work(tx_work). On a multi-CPU system, tx_work can run and reach nci_transceive() before the current nci_data_exchange_complete() clears the flag, causing test_and_set_bit(NCI_DATA_EXCHANGE) to return -EBUSY and the new transfer to fail.
This causes intermittent flakes in nci/nci_dev in NIPA:
# # RUN NCI.NCI1_0.t4t_tag_read ...
# # t4t_tag_read: Test terminated by timeout
# # FAIL NCI.NCI1_0.t4t_tag_read
# not ok 3 NCI.NCI1_0.t4t_tag_read
--- net/nfc/nci/data.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)
net/nfc/nci/data.c +8 -4
@@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, conn_info =nci_get_conn_info_by_conn_id (ndev, conn_id);if (!conn_info) {kfree_skb (skb); - goto exit; +clear_bit (NCI_DATA_EXCHANGE , &ndev->flags); +return ; } cb = conn_info->data_exchange_cb;
@@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,del_timer_sync (&ndev->data_timer);clear_bit (NCI_DATA_EXCHANGE_TO , &ndev->flags); +/* Mark the exchange as done before calling the callback. +* The callback (e.g. rawsock_data_exchange_complete) may +* want to immediately queue another data exchange. +*/ +clear_bit (NCI_DATA_EXCHANGE , &ndev->flags); +if (cb) {/* forward skb to nfc core */ cb (cb_context, skb, err);
@@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,/* no waiting callback, free skb */ kfree_skb (skb); } - -exit: -clear_bit (NCI_DATA_EXCHANGE , &ndev->flags); }/* ----------------- NCI TX Data ----------------- */
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 232/265 nfc: rawsock: cancel tx_work before socket teardown
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit d793458c45df2aed498d7f74145eab7ee22d25aa ]
In rawsock_release(), cancel any pending tx_work and purge the write queue before orphaning the socket. rawsock_tx_work runs on the system workqueue and calls nfc_data_exchange which dereferences the NCI device. Without synchronization, tx_work can race with socket and device teardown when a process is killed (e.g. by SIGKILL), leading to use-after-free or leaked references.
Set SEND_SHUTDOWN first so that if tx_work is already running it will see the flag and skip transmitting, then use cancel_work_sync to wait for any in-progress execution to finish, and finally purge any remaining queued skbs.
--- net/nfc/rawsock.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
net/nfc/rawsock.c +11 -0
@@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock)if (sock->type ==SOCK_RAW )nfc_sock_unlink (&raw_sk_list, sk); +if (sk->sk_state ==TCP_ESTABLISHED ) { +/* Prevent rawsock_tx_work from starting new transmits and +* wait for any in-progress work to finish. This must happen +* before the socket is orphaned to avoid a race where +* rawsock_tx_work runs after the NCI device has been freed. +*/ + sk->sk_shutdown |=SEND_SHUTDOWN ; +cancel_work_sync (&nfc_rawsock (sk)->tx_work); +rawsock_write_queue_purge (sk); + } +sock_orphan (sk);sock_put (sk);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 233/265 net: stmmac: Fix error handling in VLAN add and delete paths
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ovidiu Panait <[email protected]>
[ Upstream commit 35dfedce442c4060cfe5b98368bc9643fb995716 ]
stmmac_vlan_rx_add_vid() updates active_vlans and the VLAN hash register before writing the HW filter entry. If the filter write fails, it leaves a stale VID in active_vlans and the hash register.
stmmac_vlan_rx_kill_vid() has the reverse problem: it clears active_vlans before removing the HW filter. On failure, the VID is gone from active_vlans but still present in the HW filter table.
To fix this, reorder the operations to update the hash table first, then attempt the HW filter operation. If the HW filter fails, roll back both the active_vlans bitmap and the hash table by calling stmmac_vlan_update() again.
--- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +14 -4
@@ -6679,9 +6679,13 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vidif (priv->hw->num_vlan) { ret =stmmac_add_hw_vlan_rx_fltr (priv, ndev, priv->hw, proto, vid); -if (ret) +if (ret) { +clear_bit (vid, priv->active_vlans); +stmmac_vlan_update (priv, is_double); goto err_pm_put; + } } + err_pm_put:pm_runtime_put (priv->device);
@@ -6702,15 +6706,21 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi is_double = true;clear_bit (vid, priv->active_vlans); + ret =stmmac_vlan_update (priv, is_double); +if (ret) { +set_bit (vid, priv->active_vlans); + goto del_vlan_error; + }if (priv->hw->num_vlan) { ret =stmmac_del_hw_vlan_rx_fltr (priv, ndev, priv->hw, proto, vid); -if (ret) +if (ret) { +set_bit (vid, priv->active_vlans); +stmmac_vlan_update (priv, is_double); goto del_vlan_error; + } } - ret =stmmac_vlan_update (priv, is_double); - del_vlan_error:pm_runtime_put (priv->device);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 234/265 netfilter: nft_set_pipapo: split gc into unlink and reclaim phase
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit 9df95785d3d8302f7c066050117b04cd3c2048c2 ]
Yiming Qian reports Use-after-free in the pipapo set type:
Under a large number of expired elements, commit-time GC can run for a very long time in a non-preemptible context, triggering soft lockup warnings and RCU stall reports (local denial of service).
We must split GC in an unlink and a reclaim phase.
We cannot queue elements for freeing until pointers have been swapped. Expired elements are still exposed to both the packet path and userspace dumpers via the live copy of the data structure.
call_rcu() does not protect us: dump operations or element lookups starting after call_rcu has fired can still observe the free'd element, unless the commit phase has made enough progress to swap the clone and live pointers before any new reader has picked up the old version.
This a similar approach as done recently for the rbtree backend in commit 35f83a75529a ("netfilter: nft_set_rbtree: don't gc elements on insert").
--- include/net/netfilter/nf_tables.h | 5 +++ net/netfilter/nf_tables_api.c | 5 --- net/netfilter/nft_set_pipapo.c | 51 ++++++++++++++++++++++++++----- net/netfilter/nft_set_pipapo.h | 2 ++ 4 files changed, 50 insertions(+), 13 deletions(-)
include/net/netfilter/nf_tables.h +5 -0
@@ -1851,6 +1851,11 @@ struct nft_trans_gc {struct rcu_head rcu; }; +static inline int nft_trans_gc_space (const struct nft_trans_gc *trans) +{ +return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} +static inline void nft_ctx_update (struct nft_ctx *ctx,const struct nft_trans *trans) {
net/netfilter/nf_tables_api.c +0 -5
@@ -10151,11 +10151,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans)schedule_work (&trans_gc_work); } -static int nft_trans_gc_space (struct nft_trans_gc *trans) -{ -return NFT_TRANS_GC_BATCHCOUNT - trans->count; -} -struct nft_trans_gc *nft_trans_gc_queue_async (struct nft_trans_gc *gc,unsigned int gc_seq,gfp_t gfp) {
net/netfilter/nft_set_pipapo.c +43 -8
110 lines not on this page · raw message
net/netfilter/nft_set_pipapo.h +2 -0
@@ -156,12 +156,14 @@ struct nft_pipapo_match {* @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies +* @gc_head: list of nft_trans_gc to queue up for mem reclaim */ struct nft_pipapo {struct nft_pipapo_match __rcu *match;struct nft_pipapo_match *clone;int width;unsigned long last_gc; +struct list_head gc_head; };struct nft_pipapo_elem ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 235/265 net: ethernet: mtk_eth_soc: Reset prog ptr to old_prog in case of error in mtk_xdp_setup()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lorenzo Bianconi <[email protected]>
[ Upstream commit 0abc73c8a40fd64ac1739c90bb4f42c418d27a5e ]
Reset eBPF program pointer to old_prog and do not decrease its ref-count if mtk_open routine in mtk_xdp_setup() fails.
--- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/net/ethernet/mediatek/mtk_eth_soc.c +12 -3
@@ -3566,12 +3566,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog,mtk_stop (dev); old_prog =rcu_replace_pointer (eth->prog, prog,lockdep_rtnl_is_held ()); + +if (netif_running (dev) && need_update) { +int err; + + err =mtk_open (dev); +if (err) { +rcu_assign_pointer (eth->prog, old_prog); + +return err; + } + } +if (old_prog)bpf_prog_put (old_prog); -if (netif_running (dev) && need_update) -return mtk_open (dev); -return 0 ; }
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 236/265 kselftest/harness: Use helper to avoid zero-size memset warning
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wake Liu <[email protected]>
[ Upstream commit 19b8a76cd99bde6d299e60490f3e62b8d3df3997 ]
When building kselftests with a toolchain that enables source fortification (e.g., Android's build environment, which uses -D_FORTIFY_SOURCE=3), a build failure occurs in tests that use an empty FIXTURE().
The root cause is that an empty fixture struct results in sizeof(self_private) evaluating to 0. The compiler's fortification checks then detect the memset() call with a compile-time constant size of 0, issuing a -Wuser-defined-warnings which is promoted to an error by -Werror.
An initial attempt to guard the call with if (sizeof(self_private) > 0) was insufficient. The compiler's static analysis is aggressive enough to flag the memset(..., 0) pattern before evaluating the conditional, thus still triggering the error.
To resolve this robustly, this change introduces a static inline helper function, __kselftest_memset_safe(). This function wraps the size check and the memset() call. By replacing the direct memset() in the __TEST_F_IMPL macro with a call to this helper, we create an abstraction boundary. This prevents the compiler's static analyzer from "seeing" the problematic pattern at the macro expansion site, resolving the build failure.
Build Context:
Compiler: Android (14488419, +pgo, +bolt, +lto, +mlgo, based on r584948) clang version 22.0.0 (https://android.googlesource.com/toolchain/llvm-project 2d65e4108033380e6fe8e08b1f1826cd2bfb0c99) Relevant Options: -O2 -Wall -Werror -D_FORTIFY_SOURCE=3 -target i686-linux-android10000
Test: m kselftest_futex_futex_requeue_pi
Removed Gerrit Change-Id
Shuah Khan <[email protected]>
Stable-dep-of: 6be268151426 ("selftests/harness: order TEST_F and XFAIL_ADD constructors")
--- tools/testing/selftests/kselftest_harness.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/testing/selftests/kselftest_harness.h +7 -1
@@ -69,6 +69,12 @@#include "kselftest.h" +static inline void __kselftest_memset_safe (void *s,int c,size_t n) +{ +if (n >0 ) +memset (s, c, n); +} +#define TEST_TIMEOUT_DEFAULT 30/* Utilities exposed to the test definitions */
@@ -418,7 +424,7 @@ self =mmap (NULL ,sizeof (*self),PROT_READ |PROT_WRITE , \MAP_SHARED |MAP_ANONYMOUS ,-1 ,0 ); \ }else { \ -memset (&self_private,0 ,sizeof (self_private)); \ +__kselftest_memset_safe (&self_private,0 ,sizeof (self_private)); \ self = &self_private; \ } \ } \
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 237/265 selftests/harness: order TEST_F and XFAIL_ADD constructors
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sun Jian <[email protected]>
[ Upstream commit 6be2681514261324c8ee8a1c6f76cefdf700220f ]
TEST_F() allocates and registers its struct __test_metadata via mmap() inside its constructor, and only then assigns the _##fixture_##test##_object pointer.
XFAIL_ADD() runs in a constructor too and reads _##fixture_##test##_object to initialize xfail->test. If XFAIL_ADD runs first, xfail->test can be NULL and the expected failure will be reported as FAIL.
Use constructor priorities to ensure TEST_F registration runs before XFAIL_ADD, without adding extra state or runtime lookups.
--- tools/testing/selftests/kselftest_harness.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
tools/testing/selftests/kselftest_harness.h +5 -2
@@ -75,6 +75,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)memset (s, c, n); } +#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_XFAIL 20001 +#define TEST_TIMEOUT_DEFAULT 30/* Utilities exposed to the test definitions */
@@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n)__test_check_assert (_metadata); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \
@@ -879,7 +882,7 @@ struct __test_xfail { .fixture = &_##fixture_name##_fixture_object, \ .variant = &_##fixture_name##_##variant_name##_object, \ }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \ _register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \ { \ _##fixture_name##_##variant_name##_##test_name##_xfail.test = \
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 238/265 net: bridge: fix nd_tbl NULL dereference when IPv6 is disabled
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit e5e890630533bdc15b26a34bb8e7ef539bdf1322 ]
When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. Then, if neigh_suppress is enabled and an ICMPv6 Neighbor Discovery packet reaches the bridge, br_do_suppress_nd() will dereference ipv6_stub->nd_tbl which is NULL, passing it to neigh_lookup(). This causes a kernel NULL pointer dereference.
BUG: kernel NULL pointer dereference, address: 0000000000000268 Oops: 0000 [#1] PREEMPT SMP NOPTI [...] RIP: 0010:neigh_lookup+0x16/0xe0 [...] Call Trace: <IRQ> ? neigh_lookup+0x16/0xe0 br_do_suppress_nd+0x160/0x290 [bridge] br_handle_frame_finish+0x500/0x620 [bridge] br_handle_frame+0x353/0x440 [bridge] __netif_receive_skb_core.constprop.0+0x298/0x1110 __netif_receive_skb_one_core+0x3d/0xa0 process_backlog+0xa0/0x140 __napi_poll+0x2c/0x170 net_rx_action+0x2c4/0x3a0 handle_softirqs+0xd0/0x270 do_softirq+0x3f/0x60
Fix this by replacing IS_ENABLED(IPV6) call with ipv6_mod_enabled() in the callers. This is in essence disabling NS/NA suppression when IPv6 is disabled.
--- net/bridge/br_device.c | 2 +- net/bridge/br_input.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
net/bridge/br_device.c +1 -1
@@ -72,7 +72,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) {br_do_proxy_suppress_arp (skb, br, vid,NULL ); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) +
net/bridge/br_input.c +1 -1
@@ -165,7 +165,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) {br_do_proxy_suppress_arp (skb, br, vid, p); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) +
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 239/265 net: vxlan: fix nd_tbl NULL dereference when IPv6 is disabled
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit 168ff39e4758897d2eee4756977d036d52884c7e ]
When booting with the 'ipv6.disable=1' parameter, the nd_tbl is never initialized because inet6_init() exits before ndisc_init() is called which initializes it. If an IPv6 packet is injected into the interface, route_shortcircuit() is called and a NULL pointer dereference happens on neigh_lookup().
BUG: kernel NULL pointer dereference, address: 0000000000000380 Oops: Oops: 0000 [#1] SMP NOPTI [...] RIP: 0010:neigh_lookup+0x20/0x270 [...] Call Trace: <TASK> vxlan_xmit+0x638/0x1ef0 [vxlan] dev_hard_start_xmit+0x9e/0x2e0 __dev_queue_xmit+0xbee/0x14e0 packet_sendmsg+0x116f/0x1930 __sys_sendto+0x1f5/0x200 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x12f/0x1590 entry_SYSCALL_64_after_hwframe+0x76/0x7e
Fix this by adding an early check on route_shortcircuit() when protocol is ETH_P_IPV6. Note that ipv6_mod_enabled() cannot be used here because VXLAN can be built-in even when IPv6 is built as a module.
--- drivers/net/vxlan/vxlan_core.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/net/vxlan/vxlan_core.c +5 -0
@@ -2153,6 +2153,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) {struct ipv6hdr *pip6; +/* check if nd_tbl is not initiliazed due to +* ipv6.disable=1 set during boot +*/ +if (!ipv6_stub->nd_tbl) +return false;if (!pskb_may_pull (skb,sizeof (struct ipv6hdr )))return false; pip6 =ipv6_hdr (skb);
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 240/265 net: ipv6: fix panic when IPv4 route references loopback IPv6 nexthop
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiayuan Chen <[email protected]>
[ Upstream commit 21ec92774d1536f71bdc90b0e3d052eff99cf093 ]
When a standalone IPv6 nexthop object is created with a loopback device (e.g., "ip -6 nexthop add id 100 dev lo"), fib6_nh_init() misclassifies it as a reject route. This is because nexthop objects have no destination prefix (fc_dst=::), causing fib6_is_reject() to match any loopback nexthop. The reject path skips fib_nh_common_init(), leaving nhc_pcpu_rth_output unallocated. If an IPv4 route later references this nexthop, __mkroute_output() dereferences NULL nhc_pcpu_rth_output and panics.
Simplify the check in fib6_nh_init() to only match explicit reject routes (RTF_REJECT) instead of using fib6_is_reject(). The loopback promotion heuristic in fib6_is_reject() is handled separately by ip6_route_info_create_nh(). After this change, the three cases behave as follows:
1. Explicit reject route ("ip -6 route add unreachable 2001:db8::/64"):
RTF_REJECT is set, enters reject path, skips fib_nh_common_init(). No behavior change.
2. Implicit loopback reject route ("ip -6 route add 2001:db8::/32 dev lo"):
RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. ip6_route_info_create_nh() still promotes it to reject afterward. nhc_pcpu_rth_output is allocated but unused, which is harmless.
3. Standalone nexthop object ("ip -6 nexthop add id 100 dev lo"):
RTF_REJECT is not set, takes normal path, fib_nh_common_init() is called. nhc_pcpu_rth_output is properly allocated, fixing the crash when IPv4 routes reference this nexthop.
--- net/ipv6/route.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
net/ipv6/route.c +3 -5
@@ -3577,7 +3577,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker;struct net_device *dev =NULL ;struct inet6_dev *idev =NULL ; -int addr_type;int err; fib6_nh->fib_nh_family =AF_INET6 ;
@@ -3619,11 +3618,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, fib6_nh->fib_nh_weight =1 ; -/* We cannot add true routes via loopback here, -* they would result in kernel looping; promote them to reject routes +/* Reset the nexthop device to the loopback device in case of reject +* routes. */ - addr_type =ipv6_addr_type (&cfg->fc_dst); -if (fib6_is_reject (cfg->fc_flags, dev, addr_type)) { +if (cfg->fc_flags &RTF_REJECT ) {/* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) {if (dev) {
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 241/265 net/sched: act_ife: Fix metalist update behavior
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jamal Hadi Salim <[email protected]>
[ Upstream commit e2cedd400c3ec0302ffca2490e8751772906ac23 ]
Whenever an ife action replace changes the metalist, instead of replacing the old data on the metalist, the current ife code is appending the new metadata. Aside from being innapropriate behavior, this may lead to an unbounded addition of metadata to the metalist which might cause an out of bounds error when running the encode op:
[ 138.423369][ C1] ================================================================== [ 138.424317][ C1] BUG: KASAN: slab-out-of-bounds in ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.424906][ C1] Write of size 4 at addr ffff8880077f4ffe by task ife_out_out_bou/255 [ 138.425778][ C1] CPU: 1 UID: 0 PID: 255 Comm: ife_out_out_bou Not tainted 7.0.0-rc1-00169-gfbdfa8da05b6 #624 PREEMPT(full) [ 138.425795][ C1] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 138.425800][ C1] Call Trace: [ 138.425804][ C1] <IRQ> [ 138.425808][ C1] dump_stack_lvl (lib/dump_stack.c:122) [ 138.425828][ C1] print_report (mm/kasan/report.c:379 mm/kasan/report.c:482) [ 138.425839][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425844][ C1] ? __virt_addr_valid (./arch/x86/include/asm/preempt.h:95 (discriminator 1) ./include/linux/rcupdate.h:975 (discriminator 1) ./include/linux/mmzone.h:2207 (discriminator 1) arch/x86/mm/physaddr.c:54 (discriminator 1)) [ 138.425853][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425859][ C1] kasan_report (mm/kasan/report.c:221 mm/kasan/report.c:597) [ 138.425868][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425878][ C1] kasan_check_range (mm/kasan/generic.c:186 (discriminator 1) mm/kasan/generic.c:200 (discriminator 1)) [ 138.425884][ C1] __asan_memset (mm/kasan/shadow.c:84 (discriminator 2)) [ 138.425889][ C1] ife_tlv_meta_encode (net/ife/ife.c:168) [ 138.425893][ C1] ? ife_tlv_meta_encode (net/ife/ife.c:171) [ 138.425898][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425903][ C1] ife_encode_meta_u16 (net/sched/act_ife.c:57) [ 138.425910][ C1] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114) [ 138.425916][ C1] ? __asan_memcpy (mm/kasan/shadow.c:105 (discriminator 3)) [ 138.425921][ C1] ? __pfx_ife_encode_meta_u16 (net/sched/act_ife.c:45) [ 138.425927][ C1] ? srso_alias_return_thunk (arch/x86/lib/retpoline.S:221) [ 138.425931][ C1] tcf_ife_act (net/sched/act_ife.c:847 net/sched/act_ife.c:879)
To solve this issue, fix the replace behavior by adding the metalist to the ife rcu data structure.
--- include/net/tc_act/tc_ife.h | 4 +- net/sched/act_ife.c | 93 ++++++++++++++++++------------------- 2 files changed, 45 insertions(+), 52 deletions(-)
include/net/tc_act/tc_ife.h +1 -3
@@ -13,15 +13,13 @@ struct tcf_ife_params {u8 eth_src[ETH_ALEN ];u16 eth_type;u16 flags; - +struct list_head metalist;struct rcu_head rcu; };struct tcf_ife_info {struct tc_action common;struct tcf_ife_params __rcu *params; -/* list of metaids allowed */ -struct list_head metalist; };#define to_ife (a) ((struct tcf_ife_info *)a)
net/sched/act_ife.c +44 -49
294 lines not on this page · raw message
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 242/265 xdp: use modulo operation to calculate XDP frag tailroom
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit 88b6b7f7b216108a09887b074395fa7b751880b1 ]
The current formula for calculating XDP tailroom in mbuf packets works only if each frag has its own page (if rxq->frag_size is PAGE_SIZE), this defeats the purpose of the parameter overall and without any indication leads to negative calculated tailroom on at least half of frags, if shared pages are used.
There are not many drivers that set rxq->frag_size. Among them:
* i40e and enetc always split page uniformly between frags, use shared pages
* ice uses page_pool frags via libeth, those are power-of-2 and uniformly distributed across page
* idpf has variable frag_size with XDP on, so current API is not applicable
* mlx5, mtk and mvneta use PAGE_SIZE or 0 as frag_size for page_pool
As for AF_XDP ZC, only ice, i40e and idpf declare frag_size for it. Modulo operation yields good results for aligned chunks, they are all power-of-2, between 2K and PAGE_SIZE. Formula without modulo fails when chunk_size is 2K. Buffers in unaligned mode are not distributed uniformly, so modulo operation would not work.
To accommodate unaligned buffers, we could define frag_size as data + tailroom, and hence do not subtract offset when calculating tailroom, but this would necessitate more changes in the drivers.
Define rxq->frag_size as an even portion of a page that fully belongs to a single frag. When calculating tailroom, locate the data start within such portion by performing a modulo operation on page offset.
--- net/core/filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/core/filter.c +2 -1
@@ -4159,7 +4159,8 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)return -EOPNOTSUPP ; - tailroom = rxq->frag_size -skb_frag_size (frag) -skb_frag_off (frag); + tailroom = rxq->frag_size -skb_frag_size (frag) - +skb_frag_off (frag) % rxq->frag_size;if (unlikely (offset > tailroom))return -EINVAL ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 243/265 xsk: introduce helper to determine rxq->frag_size
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit 16394d80539937d348dd3b9ea32415c54e67a81b ]
rxq->frag_size is basically a step between consecutive strictly aligned frames. In ZC mode, chunk size fits exactly, but if chunks are unaligned, there is no safe way to determine accessible space to grow tailroom.
Report frag_size to be zero, if chunks are unaligned, chunk_size otherwise.
--- include/net/xdp_sock_drv.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
include/net/xdp_sock_drv.h +10 -0
@@ -47,6 +47,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)return xsk_pool_get_chunk_size (pool) -xsk_pool_get_headroom (pool); } +static inline u32 xsk_pool_get_rx_frag_step (struct xsk_buff_pool *pool) +{ +return pool->unaligned ?0 :xsk_pool_get_chunk_size (pool); +} +static inline void xsk_pool_set_rxq_info (struct xsk_buff_pool *pool,struct xdp_rxq_info *rxq) {
@@ -296,6 +301,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool)return 0 ; } +static inline u32 xsk_pool_get_rx_frag_step (struct xsk_buff_pool *pool) +{ +return 0 ; +} +static inline void xsk_pool_set_rxq_info (struct xsk_buff_pool *pool,struct xdp_rxq_info *rxq) {
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 244/265 i40e: fix registering XDP RxQ info
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit 8f497dc8a61429cc004720aa8e713743355d80cf ]
Current way of handling XDP RxQ info in i40e has a problem, where frag_size is not updated when xsk_buff_pool is detached or when MTU is changed, this leads to growing tail always failing for multi-buffer packets.
Couple XDP RxQ info registering with buffer allocations and unregistering with cleaning the ring.
--- drivers/net/ethernet/intel/i40e/i40e_main.c | 34 ++++++++++++--------- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 5 +-- 2 files changed, 22 insertions(+), 17 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_main.c +19 -15
@@ -3633,18 +3633,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)if (ring->vsi->type !=I40E_VSI_MAIN ) goto skip; -if (!xdp_rxq_info_is_reg (&ring->xdp_rxq)) { - err =__xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, - ring->queue_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); -if (err) -return err; - } - ring->xsk_pool =i40e_xsk_pool (ring);if (ring->xsk_pool) { -xdp_rxq_info_unreg (&ring->xdp_rxq); ring->rx_buf_len =xsk_pool_get_rx_frame_size (ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->queue_index,
@@ -3656,17 +3646,23 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)MEM_TYPE_XSK_BUFF_POOL , NULL);if (err) -return err; + goto unreg_xdp;dev_info (&vsi->back->pdev->dev,"Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n" , ring->queue_index); }else { + err =__xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + ring->rx_buf_len); +if (err) +return err; err =xdp_rxq_info_reg_mem_model (&ring->xdp_rxq,MEM_TYPE_PAGE_SHARED ,NULL );if (err) -return err; + goto unreg_xdp; } skip:
@@ -3704,7 +3700,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)dev_info (&vsi->back->pdev->dev,"Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n" , ring->queue_index, pf_q, err); -return -ENOMEM ; + err = -ENOMEM ; + goto unreg_xdp; }/* set the context in the HMC */
@@ -3713,7 +3710,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)dev_info (&vsi->back->pdev->dev,"Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n" , ring->queue_index, pf_q, err); -return -ENOMEM ; + err = -ENOMEM ; + goto unreg_xdp; }/* configure Rx buffer alignment */
@@ -3721,7 +3719,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)if (I40E_2K_TOO_SMALL_WITH_PADDING ) {dev_info (&vsi->back->pdev->dev,"2k Rx buffer is too small to fit standard MTU and skb_shared_info\n" ); -return -EOPNOTSUPP ; + err = -EOPNOTSUPP ; + goto unreg_xdp; }clear_ring_build_skb_enabled (ring); }else {
@@ -3751,6 +3750,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) }return 0 ; +unreg_xdp: +if (ring->vsi->type ==I40E_VSI_MAIN ) +xdp_rxq_info_unreg (&ring->xdp_rxq); + +return err; }/**
drivers/net/ethernet/intel/i40e/i40e_txrx.c +3 -2
@@ -1469,6 +1469,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)if (!rx_ring->rx_bi)return ; +if (xdp_rxq_info_is_reg (&rx_ring->xdp_rxq)) +xdp_rxq_info_unreg (&rx_ring->xdp_rxq); +if (rx_ring->xsk_pool) {i40e_xsk_clean_rx_ring (rx_ring); goto skip_free;
@@ -1526,8 +1529,6 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)void i40e_free_rx_resources (struct i40e_ring *rx_ring) {i40e_clean_rx_ring (rx_ring); -if (rx_ring->vsi->type ==I40E_VSI_MAIN ) -xdp_rxq_info_unreg (&rx_ring->xdp_rxq); rx_ring->xdp_prog =NULL ;kfree (rx_ring->rx_bi); rx_ring->rx_bi =NULL ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 245/265 i40e: use xdp.frame_sz as XDP RxQ info frag_size
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit c69d22c6c46a1d792ba8af3d8d6356fdc0e6f538 ]
The only user of frag_size field in XDP RxQ info is bpf_xdp_frags_increase_tail(). It clearly expects whole buffer size instead of DMA write size. Different assumptions in i40e driver configuration lead to negative tailroom.
Set frag_size to the same value as frame_sz in shared pages mode, use new helper to set frag_size when AF_XDP ZC is active.
--- drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_main.c +6 -3
@@ -3619,6 +3619,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)u16 pf_q = vsi->base_queue + ring->queue_index;struct i40e_hw *hw = &vsi->back->hw;struct i40e_hmc_obj_rxq rx_ctx; +u32 xdp_frame_sz;int err =0 ;bool ok;
@@ -3628,6 +3629,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)memset (&rx_ctx,0 ,sizeof (rx_ctx)); ring->rx_buf_len = vsi->rx_buf_len; + xdp_frame_sz =i40e_rx_pg_size (ring) /2 ;/* XDP RX-queue info only needed for RX rings exposed to XDP */ if (ring->vsi->type !=I40E_VSI_MAIN )
@@ -3635,11 +3637,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->xsk_pool =i40e_xsk_pool (ring);if (ring->xsk_pool) { + xdp_frame_sz =xsk_pool_get_rx_frag_step (ring->xsk_pool); ring->rx_buf_len =xsk_pool_get_rx_frame_size (ring->xsk_pool); err =__xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, ring->queue_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + xdp_frame_sz);if (err)return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3655,7 +3658,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) err =__xdp_rxq_info_reg (&ring->xdp_rxq, ring->netdev, ring->queue_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + xdp_frame_sz);if (err)return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
@@ -3666,7 +3669,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) } skip: -xdp_init_buff (&ring->xdp,i40e_rx_pg_size (ring) /2 , &ring->xdp_rxq); +xdp_init_buff (&ring->xdp, xdp_frame_sz, &ring->xdp_rxq); rx_ctx.dbuff =DIV_ROUND_UP (ring->rx_buf_len,BIT_ULL (I40E_RXQ_CTX_DBUFF_SHIFT ));
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 246/265 xdp: produce a warning when calculated tailroom is negative
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Larysa Zaremba <[email protected]>
[ Upstream commit 8821e857759be9db3cde337ad328b71fe5c8a55f ]
Many ethernet drivers report xdp Rx queue frag size as being the same as DMA write size. However, the only user of this field, namely bpf_xdp_frags_increase_tail(), clearly expects a truesize.
Such difference leads to unspecific memory corruption issues under certain circumstances, e.g. in ixgbevf maximum DMA write size is 3 KB, so when running xskxceiver's XDP_ADJUST_TAIL_GROW_MULTI_BUFF, 6K packet fully uses all DMA-writable space in 2 buffers. This would be fine, if only rxq->frag_size was properly set to 4K, but value of 3K results in a negative tailroom, because there is a non-zero page offset.
We are supposed to return -EINVAL and be done with it in such case, but due to tailroom being stored as an unsigned int, it is reported to be somewhere near UINT_MAX, resulting in a tail being grown, even if the requested offset is too much (it is around 2K in the abovementioned test). This later leads to all kinds of unspecific calltraces.
[ 7340.337579] xskxceiver[1440]: segfault at 1da718 ip 00007f4161aeac9d sp 00007f41615a6a00 error 6 [ 7340.338040] xskxceiver[1441]: segfault at 7f410000000b ip 00000000004042b5 sp 00007f415bffecf0 error 4 [ 7340.338179] in libc.so.6[61c9d,7f4161aaf000+160000] [ 7340.339230] in xskxceiver[42b5,400000+69000] [ 7340.340300] likely on CPU 6 (core 0, socket 6) [ 7340.340302] Code: ff ff 01 e9 f4 fe ff ff 0f 1f 44 00 00 4c 39 f0 74 73 31 c0 ba 01 00 00 00 f0 0f b1 17 0f 85 ba 00 00 00 49 8b 87 88 00 00 00 <4c> 89 70 08 eb cc 0f 1f 44 00 00 48 8d bd f0 fe ff ff 89 85 ec fe [ 7340.340888] likely on CPU 3 (core 0, socket 3) [ 7340.345088] Code: 00 00 00 ba 00 00 00 00 be 00 00 00 00 89 c7 e8 31 ca ff ff 89 45 ec 8b 45 ec 85 c0 78 07 b8 00 00 00 00 eb 46 e8 0b c8 ff ff <8b> 00 83 f8 69 74 24 e8 ff c7 ff ff 8b 00 83 f8 0b 74 18 e8 f3 c7 [ 7340.404334] Oops: general protection fault, probably for non-canonical address 0x6d255010bdffc: 0000 [#1] SMP NOPTI [ 7340.405972] CPU: 7 UID: 0 PID: 1439 Comm: xskxceiver Not tainted 6.19.0-rc1+ #21 PREEMPT(lazy) [ 7340.408006] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014 [ 7340.409716] RIP: 0010:lookup_swap_cgroup_id+0x44/0x80 [ 7340.410455] Code: 83 f8 1c 73 39 48 ba ff ff ff ff ff ff ff 03 48 8b 04 c5 20 55 fa bd 48 21 d1 48 89 ca 83 e1 01 48 d1 ea c1 e1 04 48 8d 04 90 <8b> 00 48 83 c4 10 d3 e8 c3 cc cc cc cc 31 c0 e9 98 b7 dd 00 48 89 [ 7340.412787] RSP: 0018:ffffcc5c04f7f6d0 EFLAGS: 00010202 [ 7340.413494] RAX: 0006d255010bdffc RBX: ffff891f477895a8 RCX: 0000000000000010 [ 7340.414431] RDX: 0001c17e3fffffff RSI: 00fa070000000000 RDI: 000382fc7fffffff [ 7340.415354] RBP: 00fa070000000000 R08: ffffcc5c04f7f8f8 R09: ffffcc5c04f7f7d0 [ 7340.416283] R10: ffff891f4c1a7000 R11: ffffcc5c04f7f9c8 R12: ffffcc5c04f7f7d0 [ 7340.417218] R13: 03ffffffffffffff R14: 00fa06fffffffe00 R15: ffff891f47789500 [ 7340.418229] FS: 0000000000000000(0000) GS:ffff891ffdfaa000(0000) knlGS:0000000000000000 [ 7340.419489] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7340.420286] CR2: 00007f415bfffd58 CR3: 0000000103f03002 CR4: 0000000000772ef0 [ 7340.421237] PKRU: 55555554 [ 7340.421623] Call Trace: [ 7340.421987] <TASK> [ 7340.422309] ? softleaf_from_pte+0x77/0xa0 [ 7340.422855] swap_pte_batch+0xa7/0x290 [ 7340.423363] zap_nonpresent_ptes.constprop.0.isra.0+0xd1/0x270 [ 7340.424102] zap_pte_range+0x281/0x580 [ 7340.424607] zap_pmd_range.isra.0+0xc9/0x240 [ 7340.425177] unmap_page_range+0x24d/0x420 [ 7340.425714] unmap_vmas+0xa1/0x180 [ 7340.426185] exit_mmap+0xe1/0x3b0 [ 7340.426644] __mmput+0x41/0x150 [ 7340.427098] exit_mm+0xb1/0x110 [ 7340.427539] do_exit+0x1b2/0x460 [ 7340.427992] do_group_exit+0x2d/0xc0 [ 7340.428477] get_signal+0x79d/0x7e0 [ 7340.428957] arch_do_signal_or_restart+0x34/0x100 [ 7340.429571] exit_to_user_mode_loop+0x8e/0x4c0 [ 7340.430159] do_syscall_64+0x188/0x6b0 [ 7340.430672] ? __do_sys_clone3+0xd9/0x120 [ 7340.431212] ? switch_fpu_return+0x4e/0xd0 [ 7340.431761] ? arch_exit_to_user_mode_prepare.isra.0+0xa1/0xc0 [ 7340.432498] ? do_syscall_64+0xbb/0x6b0 [ 7340.433015] ? __handle_mm_fault+0x445/0x690 [ 7340.433582] ? count_memcg_events+0xd6/0x210 [ 7340.434151] ? handle_mm_fault+0x212/0x340 [ 7340.434697] ? do_user_addr_fault+0x2b4/0x7b0 [ 7340.435271] ? clear_bhb_loop+0x30/0x80 [ 7340.435788] ? clear_bhb_loop+0x30/0x80 [ 7340.436299] ? clear_bhb_loop+0x30/0x80 [ 7340.436812] ? clear_bhb_loop+0x30/0x80 [ 7340.437323] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 7340.437973] RIP: 0033:0x7f4161b14169 [ 7340.438468] Code: Unable to access opcode bytes at 0x7f4161b1413f. [ 7340.439242] RSP: 002b:00007ffc6ebfa770 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca [ 7340.440173] RAX: fffffffffffffe00 RBX: 00000000000005a1 RCX: 00007f4161b14169 [ 7340.441061] RDX: 00000000000005a1 RSI: 0000000000000109 RDI: 00007f415bfff990 [ 7340.441943] RBP: 00007ffc6ebfa7a0 R08: 0000000000000000 R09: 00000000ffffffff [ 7340.442824] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 7340.443707] R13: 0000000000000000 R14: 00007f415bfff990 R15: 00007f415bfff6c0 [ 7340.444586] </TASK> [ 7340.444922] Modules linked in: rfkill intel_rapl_msr intel_rapl_common intel_uncore_frequency_common skx_edac_common nfit libnvdimm kvm_intel vfat fat kvm snd_pcm irqbypass rapl iTCO_wdt snd_timer intel_pmc_bxt iTCO_vendor_support snd ixgbevf virtio_net soundcore i2c_i801 pcspkr libeth_xdp net_failover i2c_smbus lpc_ich failover libeth virtio_balloon joydev 9p fuse loop zram lz4hc_compress lz4_compress 9pnet_virtio 9pnet netfs ghash_clmulni_intel serio_raw qemu_fw_cfg [ 7340.449650] ---[ end trace 0000000000000000 ]---
The issue can be fixed in all in-tree drivers, but we cannot just trust OOT drivers to not do this. Therefore, make tailroom a signed int and produce a warning when it is negative to prevent such mistakes in the future.
--- net/core/filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/core/filter.c +2 -1
@@ -4154,13 +4154,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)struct skb_shared_info *sinfo =xdp_get_shared_info_from_buff (xdp);skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags -1 ];struct xdp_rxq_info *rxq = xdp->rxq; -unsigned int tailroom; +int tailroom;if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)return -EOPNOTSUPP ; tailroom = rxq->frag_size -skb_frag_size (frag) -skb_frag_off (frag) % rxq->frag_size; +WARN_ON_ONCE (tailroom <0 );if (unlikely (offset > tailroom))return -EINVAL ;
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 247/265 selftest/arm64: Fix sve2p1_sigill() to hwcap test
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yifan Wu <[email protected]>
[ Upstream commit d87c828daa7ead9763416f75cc416496969cf1dc ]
The FEAT_SVE2p1 is indicated by ID_AA64ZFR0_EL1.SVEver. However, the BFADD requires the FEAT_SVE_B16B16, which is indicated by ID_AA64ZFR0_EL1.B16B16. This could cause the test to incorrectly fail on a CPU that supports FEAT_SVE2.1 but not FEAT_SVE_B16B16.
LD1Q Gather load quadwords which is decoded from SVE encodings and implied by FEAT_SVE2p1.
--- tools/testing/selftests/arm64/abi/hwcap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/arm64/abi/hwcap.c +2 -2
@@ -349,8 +349,8 @@ static void sve2_sigill(void)static void sve2p1_sigill (void ) { -/* BFADD Z0.H, Z0.H, Z0.H */ - asmvolatile (".inst 0x65000000" : : :"z0" ); +/* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */ + asmvolatile (".inst 0xC400A000" : : :"z0" ); }static void sveaes_sigill (void )
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 248/265 tracing: Add NULL pointer check to trigger_data_free()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Guenter Roeck <[email protected]>
[ Upstream commit 457965c13f0837a289c9164b842d0860133f6274 ]
If trigger_data_alloc() fails and returns NULL, event_hist_trigger_parse() jumps to the out_free error path. While kfree() safely handles a NULL pointer, trigger_data_free() does not. This causes a NULL pointer dereference in trigger_data_free() when evaluating data->cmd_ops->set_filter.
Fix the problem by adding a NULL pointer check to trigger_data_free().
The problem was found by an experimental code review agent based on gemini-3.1-pro while reviewing backports into v6.18.y.
--- kernel/trace/trace_events_trigger.c | 3 +++ 1 file changed, 3 insertions(+)
kernel/trace/trace_events_trigger.c +3 -0
@@ -19,6 +19,9 @@ static DEFINE_MUTEX(trigger_cmd_mutex);void trigger_data_free (struct event_trigger_data *data) { +if (!data) +return ; +if (data->cmd_ops->set_filter) data->cmd_ops->set_filter (NULL , data,NULL );
Signature · 1 line
2.51.0
Greg Kroah-Hartman
maintainerPATCH 249/265 net/sched: Only allow act_ct to bind to clsact/ingress qdiscs and shared blocks
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Victor Nogueira <[email protected]>
commit 11cb63b0d1a0685e0831ae3c77223e002ef18189 upstream.
As Paolo said earlier [1]:
"Since the blamed commit below, classify can return TC_ACT_CONSUMED while the current skb being held by the defragmentation engine. As reported by GangMin Kim, if such packet is that may cause a UaF when the defrag engine later on tries to tuch again such packet."
act_ct was never meant to be used in the egress path, however some users are attaching it to egress today [2]. Attempting to reach a middle ground, we noticed that, while most qdiscs are not handling TC_ACT_CONSUMED, clsact/ingress qdiscs are. With that in mind, we address the issue by only allowing act_ct to bind to clsact/ingress qdiscs and shared blocks. That way it's still possible to attach act_ct to egress (albeit only with clsact).
[1] https://lore.kernel.org/netdev/674b8cbfc385c6f37fb29a1de08d8fe5c2b0fbee.1771321118.git.pabeni@redhat.com/
[2] https://lore.kernel.org/netdev/[email protected]/
--- include/net/act_api.h | 1 + net/sched/act_ct.c | 6 ++++++ net/sched/cls_api.c | 7 +++++++ 3 files changed, 14 insertions(+)
include/net/act_api.h +1 -0
@@ -68,6 +68,7 @@ struct tc_action {#define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2))#define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3))#define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) +#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT (1U << (TCA_ACT_FLAGS_USER_BITS + 5))/* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice.
net/sched/act_ct.c +6 -0
@@ -1358,6 +1358,12 @@ static int tcf_ct_init(struct net *net,return -EINVAL ; } +if (bind && !(flags &TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT )) { +NL_SET_ERR_MSG_MOD (extack, +"Attaching ct to a non ingress/clsact qdisc is unsupported" ); +return -EOPNOTSUPP ; + } + err =nla_parse_nested (tb,TCA_CT_MAX , nla, ct_policy, extack);if (err <0 )return err;
net/sched/cls_api.c +7 -0
@@ -2222,6 +2222,11 @@ static bool is_qdisc_ingress(__u32 classreturn (TC_H_MIN (classid) ==TC_H_MIN (TC_H_MIN_INGRESS )); } +static bool is_ingress_or_clsact (struct tcf_block *block,struct Qdisc *q) +{ +return tcf_block_shared (block) || (q && !!(q->flags &TCQ_F_INGRESS )); +} +static int tc_new_tfilter (struct sk_buff *skb,struct nlmsghdr *n,struct netlink_ext_ack *extack) {
@@ -2415,6 +2420,8 @@ replay: flags |=TCA_ACT_FLAGS_NO_RTNL ;if (is_qdisc_ingress (parent)) flags |=TCA_ACT_FLAGS_AT_INGRESS ; +if (is_ingress_or_clsact (block, q)) + flags |=TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT ; err = tp->ops->change (net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack);if (err ==0 ) {
Greg Kroah-Hartman
maintainerPATCH 250/265 apparmor: validate DFA start states are in bounds in unpack_pdb
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Massimiliano Pellizzer <[email protected]>
commit 9063d7e2615f4a7ab321de6b520e23d370e58816 upstream.
Start states are read from untrusted data and used as indexes into the DFA state tables. The aa_dfa_next() function call in unpack_pdb() will access dfa->tables[YYTD_ID_BASE][start], and if the start state exceeds the number of states in the DFA, this results in an out-of-bound read.
==================================================================
BUG: KASAN: slab-out-of-bounds in aa_dfa_next+0x2a1/0x360 Read of size 4 at addr ffff88811956fb90 by task su/1097 ...
Reject policies with out-of-bounds start states during unpacking to prevent the issue.
--- security/apparmor/policy_unpack.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)
security/apparmor/policy_unpack.c +11 -1
@@ -762,7 +762,17 @@ static int unpack_pdb(struct aa_ext *e,if (!aa_unpack_u32 (e, &pdb->start[AA_CLASS_FILE ],"dfa_start" )) {/* default start state for xmatch and file dfa */ pdb->start[AA_CLASS_FILE ] =DFA_START ; - }/* setup class index */ + } + +size_t state_count = pdb->dfa->tables[YYTD_ID_BASE ]->td_lolen; + +if (pdb->start[0 ] >= state_count || + pdb->start[AA_CLASS_FILE ] >= state_count) { + *info ="invalid dfa start state" ; + goto fail; + } + +/* setup class index */ for (i =AA_CLASS_FILE +1 ; i <=AA_CLASS_LAST ; i++) { pdb->start[i] =aa_dfa_next (pdb->dfa, pdb->start[0 ], i);
Greg Kroah-Hartman
maintainerPATCH 251/265 apparmor: fix memory leak in verify_header
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Massimiliano Pellizzer <[email protected]>
commit e38c55d9f834e5b848bfed0f5c586aaf45acb825 upstream.
The function sets *ns = NULL on every call, leaking the namespace string allocated in previous iterations when multiple profiles are unpacked. This also breaks namespace consistency checking since *ns is always NULL when the comparison is made.
Remove the incorrect assignment.
The caller (aa_unpack) initializes *ns to NULL once before the loop, which is sufficient.
--- security/apparmor/policy_unpack.c | 1 - 1 file changed, 1 deletion(-)
security/apparmor/policy_unpack.c +0 -1
@@ -1142,7 +1142,6 @@ static int verify_header(struct aa_ext * {int error = -EPROTONOSUPPORT ;const char *name =NULL ; - *ns =NULL ;/* get the interface version */ if (!aa_unpack_u32 (e, &e->version,"version" )) {
Greg Kroah-Hartman
maintainerPATCH 252/265 apparmor: replace recursive profile removal with iterative approach
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Massimiliano Pellizzer <[email protected]>
commit ab09264660f9de5d05d1ef4e225aa447c63a8747 upstream.
The profile removal code uses recursion when removing nested profiles, which can lead to kernel stack exhaustion and system crashes.
Reproducer:
$ pf='a'; for ((i=0; i<1024; i++)); do
echo -e "profile $pf { \n }" | apparmor_parser -K -a;
pf="$pf//x";
done
$ echo -n a > /sys/kernel/security/apparmor/.removeReplace the recursive __aa_profile_list_release() approach with an iterative approach in __remove_profile(). The function repeatedly finds and removes leaf profiles until the entire subtree is removed, maintaining the same removal semantic without recursion.
--- security/apparmor/policy.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-)
security/apparmor/policy.c +27 -3
@@ -184,19 +184,43 @@ static void __list_remove_profile(struct }/** -* __remove_profile - remove old profile, and children -* @profile: profile to be replaced (NOT NULL) +* __remove_profile - remove profile, and children +* @profile: profile to be removed (NOT NULL) * * Requires: namespace list lock be held, or list not be shared */ static void __remove_profile (struct aa_profile *profile) { +struct aa_profile *curr, *to_remove; +AA_BUG (!profile);AA_BUG (!profile->ns);AA_BUG (!mutex_is_locked (&profile->ns->lock));/* release any children lists first */ -__aa_profile_list_release (&profile->base.profiles); +if (!list_empty (&profile->base.profiles)) { + curr = list_first_entry(&profile->base.profiles, struct aa_profile, base.list); + +while (curr != profile) { + +while (!list_empty (&curr->base.profiles)) + curr =list_first_entry (&curr->base.profiles, + struct aa_profile, base.list); + + to_remove = curr; +if (!list_is_last (&to_remove->base.list, + &aa_deref_parent (curr)->base.profiles)) + curr =list_next_entry (to_remove, base.list); +else + curr =aa_deref_parent (curr); + +/* released by free_profile */ +aa_label_remove (&to_remove->label); +__aafs_profile_rmdir (to_remove); +__list_remove_profile (to_remove); + } + } +/* released by free_profile */ aa_label_remove (&profile->label);__aafs_profile_rmdir (profile);
Greg Kroah-Hartman
maintainerPATCH 253/265 apparmor: fix: limit the number of levels of policy namespaces
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Johansen <[email protected]>
commit 306039414932c80f8420695a24d4fe10c84ccfb2 upstream.
Currently the number of policy namespaces is not bounded relying on the user namespace limit. However policy namespaces aren't strictly tied to user namespaces and it is possible to create them and nest them arbitrarily deep which can be used to exhaust system resource.
Hard cap policy namespaces to the same depth as user namespaces.
--- security/apparmor/include/policy_ns.h | 2 ++ security/apparmor/policy_ns.c | 2 ++ 2 files changed, 4 insertions(+)
security/apparmor/include/policy_ns.h +2 -0
@@ -18,6 +18,8 @@#include "label.h" #include "policy.h" +/* Match max depth of user namespaces */ +#define MAX_NS_DEPTH 32/* struct aa_ns_acct - accounting of profiles in namespace * @max_size: maximum space allowed for all profiles in namespace
security/apparmor/policy_ns.c +2 -0
@@ -223,6 +223,8 @@ static struct aa_ns *__aa_create_ns(struAA_BUG (!name);AA_BUG (!mutex_is_locked (&parent->lock)); +if (parent->level >MAX_NS_DEPTH ) +return ERR_PTR (-ENOSPC ); ns =alloc_ns (parent->base.hname, name);if (!ns)return ERR_PTR (-ENOMEM );
Greg Kroah-Hartman
maintainerPATCH 254/265 apparmor: fix side-effect bug in match_char() macro usage
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Massimiliano Pellizzer <[email protected]>
commit 8756b68edae37ff546c02091989a4ceab3f20abd upstream.
The match_char() macro evaluates its character parameter multiple times when traversing differential encoding chains. When invoked with *str++, the string pointer advances on each iteration of the inner do-while loop, causing the DFA to check different characters at each iteration and therefore skip input characters. This results in out-of-bounds reads when the pointer advances past the input buffer boundary.
[ 94.984676] ================================================================== [ 94.985301] BUG: KASAN: slab-out-of-bounds in aa_dfa_match+0x5ae/0x760 [ 94.985655] Read of size 1 at addr ffff888100342000 by task file/976
[ 94.986319] CPU: 7 UID: 1000 PID: 976 Comm: file Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 94.986322] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 94.986329] Call Trace: [ 94.986341] <TASK> [ 94.986347] dump_stack_lvl+0x5e/0x80 [ 94.986374] print_report+0xc8/0x270 [ 94.986384] ? aa_dfa_match+0x5ae/0x760 [ 94.986388] kasan_report+0x118/0x150 [ 94.986401] ? aa_dfa_match+0x5ae/0x760 [ 94.986405] aa_dfa_match+0x5ae/0x760 [ 94.986408] __aa_path_perm+0x131/0x400 [ 94.986418] aa_path_perm+0x219/0x2f0 [ 94.986424] apparmor_file_open+0x345/0x570 [ 94.986431] security_file_open+0x5c/0x140 [ 94.986442] do_dentry_open+0x2f6/0x1120 [ 94.986450] vfs_open+0x38/0x2b0 [ 94.986453] ? may_open+0x1e2/0x2b0 [ 94.986466] path_openat+0x231b/0x2b30 [ 94.986469] ? __x64_sys_openat+0xf8/0x130 [ 94.986477] do_file_open+0x19d/0x360 [ 94.986487] do_sys_openat2+0x98/0x100 [ 94.986491] __x64_sys_openat+0xf8/0x130 [ 94.986499] do_syscall_64+0x8e/0x660 [ 94.986515] ? count_memcg_events+0x15f/0x3c0 [ 94.986526] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986540] ? handle_mm_fault+0x1639/0x1ef0 [ 94.986551] ? vma_start_read+0xf0/0x320 [ 94.986558] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986561] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986563] ? fpregs_assert_state_consistent+0x50/0xe0 [ 94.986572] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986574] ? arch_exit_to_user_mode_prepare+0x9/0xb0 [ 94.986587] ? srso_alias_return_thunk+0x5/0xfbef5 [ 94.986588] ? irqentry_exit+0x3c/0x590 [ 94.986595] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 94.986597] RIP: 0033:0x7fda4a79c3ea
Fix by extracting the character value before invoking match_char, ensuring single evaluation per outer loop.
--- security/apparmor/match.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)
security/apparmor/match.c +20 -10
@@ -408,13 +408,18 @@ aa_state_t aa_dfa_match_len(struct aa_dfif (dfa->tables[YYTD_ID_EC ]) {/* Equivalence class table defined */ u8 *equiv =EQUIV_TABLE (dfa); -for (; len; len--) -match_char (state, def, base, next, check, - equiv[(u8) *str++]); +for (; len; len--) { +u8 c = equiv[(u8) *str]; + +match_char (state, def, base, next, check, c); + str++; + } }else {/* default is direct to next state */ -for (; len; len--) -match_char (state, def, base, next, check, (u8) *str++); +for (; len; len--) { +match_char (state, def, base, next, check, (u8) *str); + str++; + } }return state;
@@ -448,13 +453,18 @@ aa_state_t aa_dfa_match(struct aa_dfa *d/* Equivalence class table defined */ u8 *equiv =EQUIV_TABLE (dfa);/* default is direct to next state */ -while (*str) -match_char (state, def, base, next, check, - equiv[(u8) *str++]); +while (*str) { +u8 c = equiv[(u8) *str]; + +match_char (state, def, base, next, check, c); + str++; + } }else {/* default is direct to next state */ -while (*str) -match_char (state, def, base, next, check, (u8) *str++); +while (*str) { +match_char (state, def, base, next, check, (u8) *str); + str++; + } }return state;
Greg Kroah-Hartman
maintainerPATCH 255/265 apparmor: fix missing bounds check on DEFAULT table in verify_dfa()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: Massimiliano Pellizzer <[email protected]>
commit d352873bbefa7eb39995239d0b44ccdf8aaa79a4 upstream.
The verify_dfa() function only checks DEFAULT_TABLE bounds when the state is not differentially encoded.
When the verification loop traverses the differential encoding chain, it reads k = DEFAULT_TABLE[j] and uses k as an array index without validation. A malformed DFA with DEFAULT_TABLE[j] >= state_count, therefore, causes both out-of-bounds reads and writes.
[ 57.179855] ================================================================== [ 57.180549] BUG: KASAN: slab-out-of-bounds in verify_dfa+0x59a/0x660 [ 57.180904] Read of size 4 at addr ffff888100eadec4 by task su/993
[ 57.181554] CPU: 1 UID: 0 PID: 993 Comm: su Not tainted 6.19.0-rc7-next-20260127 #1 PREEMPT(lazy) [ 57.181558] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 [ 57.181563] Call Trace: [ 57.181572] <TASK> [ 57.181577] dump_stack_lvl+0x5e/0x80 [ 57.181596] print_report+0xc8/0x270 [ 57.181605] ? verify_dfa+0x59a/0x660 [ 57.181608] kasan_report+0x118/0x150 [ 57.181620] ? verify_dfa+0x59a/0x660 [ 57.181623] verify_dfa+0x59a/0x660 [ 57.181627] aa_dfa_unpack+0x1610/0x1740 [ 57.181629] ? __kmalloc_cache_noprof+0x1d0/0x470 [ 57.181640] unpack_pdb+0x86d/0x46b0 [ 57.181647] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181653] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181656] ? aa_unpack_nameX+0x1a8/0x300 [ 57.181659] aa_unpack+0x20b0/0x4c30 [ 57.181662] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181664] ? stack_depot_save_flags+0x33/0x700 [ 57.181681] ? kasan_save_track+0x4f/0x80 [ 57.181683] ? kasan_save_track+0x3e/0x80 [ 57.181686] ? __kasan_kmalloc+0x93/0xb0 [ 57.181688] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181693] ? aa_simple_write_to_buffer+0x54/0x130 [ 57.181697] ? policy_update+0x154/0x330 [ 57.181704] aa_replace_profiles+0x15a/0x1dd0 [ 57.181707] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181710] ? __kvmalloc_node_noprof+0x44a/0x780 [ 57.181712] ? aa_loaddata_alloc+0x77/0x140 [ 57.181715] ? srso_alias_return_thunk+0x5/0xfbef5 [ 57.181717] ? _copy_from_user+0x2a/0x70 [ 57.181730] policy_update+0x17a/0x330 [ 57.181733] profile_replace+0x153/0x1a0 [ 57.181735] ? rw_verify_area+0x93/0x2d0 [ 57.181740] vfs_write+0x235/0xab0 [ 57.181745] ksys_write+0xb0/0x170 [ 57.181748] do_syscall_64+0x8e/0x660 [ 57.181762] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 57.181765] RIP: 0033:0x7f6192792eb2
Remove the MATCH_FLAG_DIFF_ENCODE condition to validate all DEFAULT_TABLE entries unconditionally.
--- security/apparmor/match.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
security/apparmor/match.c +3 -2
@@ -160,9 +160,10 @@ static int verify_dfa(struct aa_dfa *dfaif (state_count ==0 ) goto out;for (i =0 ; i < state_count; i++) { -if (!(BASE_TABLE (dfa)[i] &MATCH_FLAG_DIFF_ENCODE ) && - (DEFAULT_TABLE (dfa)[i] >= state_count)) +if (DEFAULT_TABLE (dfa)[i] >= state_count) { +pr_err ("AppArmor DFA default state out of bounds" ); goto out; + }if (BASE_TABLE (dfa)[i] &MATCH_FLAGS_INVALID ) {pr_err ("AppArmor DFA state with invalid match flags" ); goto out;
Greg Kroah-Hartman
maintainerPATCH 256/265 apparmor: Fix double free of ns_name in aa_replace_profiles()
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Johansen <[email protected]>
commit 5df0c44e8f5f619d3beb871207aded7c78414502 upstream.
if ns_name is NULL after
1071 error = aa_unpack(udata, &lh, &ns_name);
and if ent->ns_name contains an ns_name in
1089 } else if (ent->ns_name) {
then ns_name is assigned the ent->ns_name
1095 ns_name = ent->ns_name;
however ent->ns_name is freed at
1262 aa_load_ent_free(ent);
and then again when freeing ns_name at
1270 kfree(ns_name);
Fix this by NULLing out ent->ns_name after it is transferred to ns_name
--- security/apparmor/policy.c | 1 + 1 file changed, 1 insertion(+)
security/apparmor/policy.c +1 -0
@@ -1118,6 +1118,7 @@ ssize_t aa_replace_profiles(struct aa_ns goto fail; } ns_name = ent->ns_name; + ent->ns_name =NULL ; }else count++; }
Greg Kroah-Hartman
maintainerPATCH 257/265 apparmor: fix unprivileged local user can do privileged policy management
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Johansen <[email protected]>
commit 6601e13e82841879406bf9f369032656f441a425 upstream.
An unprivileged local user can load, replace, and remove profiles by opening the apparmorfs interfaces, via a confused deputy attack, by passing the opened fd to a privileged process, and getting the privileged process to write to the interface.
This does require a privileged target that can be manipulated to do the write for the unprivileged process, but once such access is achieved full policy management is possible and all the possible implications that implies: removing confinement, DoS of system or target applications by denying all execution, by-passing the unprivileged user namespace restriction, to exploiting kernel bugs for a local privilege escalation.
The policy management interface can not have its permissions simply changed from 0666 to 0600 because non-root processes need to be able to load policy to different policy namespaces.
Instead ensure the task writing the interface has privileges that are a subset of the task that opened the interface. This is already done via policy for confined processes, but unconfined can delegate access to the opened fd, by-passing the usual policy check.
--- security/apparmor/apparmorfs.c | 16 +++++++++------- security/apparmor/include/policy.h | 2 +- security/apparmor/policy.c | 34 +++++++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 9 deletions(-)
security/apparmor/apparmorfs.c +9 -7
@@ -412,7 +412,8 @@ static struct aa_loaddata *aa_simple_wri }static ssize_t policy_update (u32 mask,const char __user *buf,size_t size, -loff_t *pos,struct aa_ns *ns) +loff_t *pos,struct aa_ns *ns, +const struct cred *ocred) {struct aa_loaddata *data;struct aa_label *label;
@@ -423,7 +424,7 @@ static ssize_t policy_update(u32 mask, c/* high level check about policy management - fine grained in * below after unpack */ - error =aa_may_manage_policy (current_cred (), label, ns, mask); + error =aa_may_manage_policy (current_cred (), label, ns, ocred, mask);if (error) goto end_section;
@@ -444,7 +445,8 @@ static ssize_t profile_load(struct file loff_t *pos) {struct aa_ns *ns =aa_get_ns (f->f_inode->i_private); -int error =policy_update (AA_MAY_LOAD_POLICY , buf, size, pos, ns); +int error =policy_update (AA_MAY_LOAD_POLICY , buf, size, pos, ns, + f->f_cred);aa_put_ns (ns);
@@ -462,7 +464,7 @@ static ssize_t profile_replace(struct fi {struct aa_ns *ns =aa_get_ns (f->f_inode->i_private);int error =policy_update (AA_MAY_LOAD_POLICY |AA_MAY_REPLACE_POLICY , - buf, size, pos, ns); + buf, size, pos, ns, f->f_cred);aa_put_ns (ns);return error;
@@ -487,7 +489,7 @@ static ssize_t profile_remove(struct fil* below after unpack */ error =aa_may_manage_policy (current_cred (), label, ns, -AA_MAY_REMOVE_POLICY ); + f->f_cred,AA_MAY_REMOVE_POLICY );if (error) goto out;
@@ -1813,7 +1815,7 @@ static int ns_mkdir_op(struct mnt_idmapint error; label =begin_current_label_crit_section (); - error =aa_may_manage_policy (current_cred (), label,NULL , + error =aa_may_manage_policy (current_cred (), label,NULL ,NULL ,AA_MAY_LOAD_POLICY );end_current_label_crit_section (label);if (error)
@@ -1863,7 +1865,7 @@ static int ns_rmdir_op(struct inode *dirint error; label =begin_current_label_crit_section (); - error =aa_may_manage_policy (current_cred (), label,NULL , + error =aa_may_manage_policy (current_cred (), label,NULL ,NULL ,AA_MAY_LOAD_POLICY );end_current_label_crit_section (label);if (error)
security/apparmor/include/policy.h +1 -1
@@ -393,7 +393,7 @@ bool aa_policy_admin_capable(const struc struct aa_label *label, struct aa_ns *ns);int aa_may_manage_policy (const struct cred *subj_cred,struct aa_label *label,struct aa_ns *ns, -u32 mask); +const struct cred *ocred,u32 mask);bool aa_current_policy_view_capable (struct aa_ns *ns);bool aa_current_policy_admin_capable (struct aa_ns *ns);
security/apparmor/policy.c +33 -1
@@ -894,17 +894,44 @@ bool aa_current_policy_admin_capable(strreturn res; } +static bool is_subset_of_obj_privilege (const struct cred *cred, +struct aa_label *label, +const struct cred *ocred) +{ +if (cred == ocred) +return true; + +if (!aa_label_is_subset (label,cred_label (ocred))) +return false; +/* don't allow crossing userns for now */ +if (cred->user_ns != ocred->user_ns) +return false; +if (!cap_issubset (cred->cap_inheritable, ocred->cap_inheritable)) +return false; +if (!cap_issubset (cred->cap_permitted, ocred->cap_permitted)) +return false; +if (!cap_issubset (cred->cap_effective, ocred->cap_effective)) +return false; +if (!cap_issubset (cred->cap_bset, ocred->cap_bset)) +return false; +if (!cap_issubset (cred->cap_ambient, ocred->cap_ambient)) +return false; +return true; +} + +/** * aa_may_manage_policy - can the current task manage policy * @subj_cred: subjects cred * @label: label to check if it can manage policy * @ns: namespace being managed by @label (may be NULL if @label's ns) +* @ocred: object cred if request is coming from an open object * @mask: contains the policy manipulation operation being done * * Returns: 0 if the task is allowed to manipulate policy else error */ int aa_may_manage_policy (const struct cred *subj_cred,struct aa_label *label, -struct aa_ns *ns,u32 mask) +struct aa_ns *ns,const struct cred *ocred,u32 mask) {const char *op;
@@ -920,6 +947,11 @@ int aa_may_manage_policy(const struct crreturn audit_policy (label, op,NULL ,NULL ,"policy_locked" , -EACCES ); +if (ocred && !is_subset_of_obj_privilege (subj_cred, label, ocred)) +return audit_policy (label, op,NULL ,NULL , +"not privileged for target profile" , + -EACCES ); +if (!aa_policy_admin_capable (subj_cred, label, ns))return audit_policy (label, op,NULL ,NULL ,"not policy admin" , -EACCES );
Greg Kroah-Hartman
maintainerPATCH 258/265 apparmor: fix differential encoding verification
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Johansen <[email protected]>
commit 39440b137546a3aa383cfdabc605fb73811b6093 upstream.
Differential encoding allows loops to be created if it is abused. To prevent this the unpack should verify that a diff-encode chain terminates.
Unfortunately the differential encode verification had two bugs.
1. it conflated states that had gone through check and already been marked, with states that were currently being checked and marked. This means that loops in the current chain being verified are treated as a chain that has already been verified.
2. the order bailout on already checked states compared current chain check iterators j,k instead of using the outer loop iterator i. Meaning a step backwards in states in the current chain verification was being mistaken for moving to an already verified state.
Move to a double mark scheme where already verified states get a different mark, than the current chain being kept. This enables us to also drop the backwards verification check that was the cause of the second error as any already verified state is already marked.
--- security/apparmor/include/match.h | 1 + security/apparmor/match.c | 23 +++++++++++++++++++---- 2 files changed, 20 insertions(+), 4 deletions(-)
security/apparmor/include/match.h +1 -0
@@ -183,6 +183,7 @@ static inline void aa_put_dfa(struct aa_#define MATCH_FLAG_DIFF_ENCODE 0x80000000#define MARK_DIFF_ENCODE 0x40000000#define MATCH_FLAG_OOB_TRANSITION 0x20000000 +#define MARK_DIFF_ENCODE_VERIFIED 0x10000000#define MATCH_FLAGS_MASK 0xff000000#define MATCH_FLAGS_VALID (MATCH_FLAG_DIFF_ENCODE | MATCH_FLAG_OOB_TRANSITION)#define MATCH_FLAGS_INVALID (MATCH_FLAGS_MASK & ~MATCH_FLAGS_VALID)
security/apparmor/match.c +19 -4
@@ -202,16 +202,31 @@ static int verify_dfa(struct aa_dfa *dfasize_t j, k;for (j = i; - (BASE_TABLE (dfa)[j] &MATCH_FLAG_DIFF_ENCODE ) && - !(BASE_TABLE (dfa)[j] &MARK_DIFF_ENCODE ); + ((BASE_TABLE (dfa)[j] &MATCH_FLAG_DIFF_ENCODE ) && + !(BASE_TABLE (dfa)[j] &MARK_DIFF_ENCODE_VERIFIED )); j = k) { +if (BASE_TABLE (dfa)[j] &MARK_DIFF_ENCODE ) +/* loop in current chain */ + goto out; k =DEFAULT_TABLE (dfa)[j];if (j == k) +/* self loop */ goto out; -if (k < j) -break ;/* already verified */ BASE_TABLE (dfa)[j] |=MARK_DIFF_ENCODE ; } +/* move mark to verified */ +for (j = i; + (BASE_TABLE (dfa)[j] &MATCH_FLAG_DIFF_ENCODE ); + j = k) { + k =DEFAULT_TABLE (dfa)[j]; +if (j < i) +/* jumps to state/chain that has been +* verified +*/ +break ; +BASE_TABLE (dfa)[j] &= ~MARK_DIFF_ENCODE ; +BASE_TABLE (dfa)[j] |=MARK_DIFF_ENCODE_VERIFIED ; + } } error =0 ;
Greg Kroah-Hartman
maintainerPATCH 259/265 apparmor: fix race on rawdata dereference
In reply to Greg Kroah-Hartman6.12-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Johansen <[email protected]>
commit a0b7091c4de45a7325c8780e6934a894f92ac86b upstream.
There is a race condition that leads to a use-after-free situation:
because the rawdata inodes are not refcounted, an attacker can start open()ing one of the rawdata files, and at the same time remove the last reference to this rawdata (by removing the corresponding profile, for example), which frees its struct aa_loaddata; as a result, when seq_rawdata_open() is reached, i_private is a dangling pointer and freed memory is accessed.
The rawdata inodes weren't refcounted to avoid a circular refcount and were supposed to be held by the profile rawdata reference. However during profile removal there is a window where the vfs and profile destruction race, resulting in the use after free.
Fix this by moving to a double refcount scheme. Where the profile refcount on rawdata is used to break the circular dependency. Allowing for freeing of the rawdata once all inode references to the rawdata are put.
--- security/apparmor/apparmorfs.c | 35 ++++++++------ security/apparmor/include/policy_unpack.h | 71 ++++++++++++++++++------------ security/apparmor/policy.c | 12 ++--- security/apparmor/policy_unpack.c | 32 +++++++++---- 4 files changed, 93 insertions(+), 57 deletions(-)
security/apparmor/apparmorfs.c +21 -14
@@ -79,7 +79,7 @@ static void rawdata_f_data_free(struct rif (!private)return ; -aa_put_loaddata (private->loaddata); +aa_put_i_loaddata (private->loaddata);kvfree (private); }
@@ -404,7 +404,8 @@ static struct aa_loaddata *aa_simple_wri data->size = copy_size;if (copy_from_user (data->data, userbuf, copy_size)) { -aa_put_loaddata (data); +/* trigger free - don't need to put pcount */ +aa_put_i_loaddata (data);return ERR_PTR (-EFAULT ); }
@@ -432,7 +433,10 @@ static ssize_t policy_update(u32 mask, c error =PTR_ERR (data);if (!IS_ERR (data)) { error =aa_replace_profiles (ns, label, mask, data); -aa_put_loaddata (data); +/* put pcount, which will put count and free if no +* profiles referencing it. +*/ +aa_put_profile_loaddata (data); } end_section:end_current_label_crit_section (label);
@@ -503,7 +507,7 @@ static ssize_t profile_remove(struct filif (!IS_ERR (data)) { data->data[size] =0 ; error =aa_remove_profiles (ns, label, data->data, size); -aa_put_loaddata (data); +aa_put_profile_loaddata (data); } out:end_current_label_crit_section (label);
@@ -1242,18 +1246,17 @@ static const struct file_operations seq_static int seq_rawdata_open (struct inode *inode,struct file *file,int (*show)(struct seq_file *,void *)) { -struct aa_loaddata *data =__aa_get_loaddata (inode->i_private); +struct aa_loaddata *data =aa_get_i_loaddata (inode->i_private);int error;if (!data) -/* lost race this ent is being reaped */ return -ENOENT ; error =single_open (file, show, data);if (error) {AA_BUG (file->private_data && ((struct seq_file *)file->private_data)->private); -aa_put_loaddata (data); +aa_put_i_loaddata (data); }return error;
@@ -1264,7 +1267,7 @@ static int seq_rawdata_release(struct instruct seq_file *seq = (struct seq_file *) file->private_data;if (seq) -aa_put_loaddata (seq->private); +aa_put_i_loaddata (seq->private);return single_release (inode, file); }
@@ -1376,9 +1379,8 @@ static int rawdata_open(struct inode *inif (!aa_current_policy_view_capable (NULL ))return -EACCES ; - loaddata =__aa_get_loaddata (inode->i_private); + loaddata =aa_get_i_loaddata (inode->i_private);if (!loaddata) -/* lost race: this entry is being reaped */ return -ENOENT ; private =rawdata_f_data_alloc (loaddata->size);
@@ -1403,7 +1405,7 @@ fail_decompress:return error; fail_private_alloc: -aa_put_loaddata (loaddata); +aa_put_i_loaddata (loaddata);return error; }
@@ -1420,9 +1422,9 @@ static void remove_rawdata_dents(structfor (i =0 ; i <AAFS_LOADDATA_NDENTS ; i++) {if (!IS_ERR_OR_NULL (rawdata->dents[i])) { -/* no refcounts on i_private */ aafs_remove (rawdata->dents[i]); rawdata->dents[i] =NULL ; +aa_put_i_loaddata (rawdata); } } }
@@ -1461,18 +1463,21 @@ int __aa_fs_create_rawdata(struct aa_nsif (IS_ERR (dir))/* ->name freed when rawdata freed */ return PTR_ERR (dir); +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_DIR ] = dir; dent =aafs_create_file ("abi" ,S_IFREG |0444 , dir, rawdata, &seq_rawdata_abi_fops);if (IS_ERR (dent)) goto fail; +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_ABI ] = dent; dent =aafs_create_file ("revision" ,S_IFREG |0444 , dir, rawdata, &seq_rawdata_revision_fops);if (IS_ERR (dent)) goto fail; +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_REVISION ] = dent;if (aa_g_hash_policy) {
@@ -1480,6 +1485,7 @@ int __aa_fs_create_rawdata(struct aa_ns rawdata, &seq_rawdata_hash_fops);if (IS_ERR (dent)) goto fail; +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_HASH ] = dent; }
@@ -1488,24 +1494,25 @@ int __aa_fs_create_rawdata(struct aa_ns &seq_rawdata_compressed_size_fops);if (IS_ERR (dent)) goto fail; +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE ] = dent; dent =aafs_create_file ("raw_data" ,S_IFREG |0444 , dir, rawdata, &rawdata_fops);if (IS_ERR (dent)) goto fail; +aa_get_i_loaddata (rawdata); rawdata->dents[AAFS_LOADDATA_DATA ] = dent;d_inode (dent)->i_size = rawdata->size; rawdata->ns =aa_get_ns (ns);list_add (&rawdata->list, &ns->rawdata_list); -/* no refcount on inode rawdata */ return 0 ; fail:remove_rawdata_dents (rawdata); - +aa_put_i_loaddata (rawdata); return PTR_ERR(dent); }#endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
security/apparmor/include/policy_unpack.h +43 -28
112 lines not on this page · raw message
security/apparmor/policy.c +6 -6
@@ -338,7 +338,7 @@ void aa_free_profile(struct aa_profile * }kfree_sensitive (profile->hash); -aa_put_loaddata (profile->rawdata); +aa_put_profile_loaddata (profile->rawdata);aa_label_destroy (&profile->label);kfree_sensitive (profile);
@@ -1123,7 +1123,7 @@ ssize_t aa_replace_profiles(struct aa_nsLIST_HEAD (lh); op = mask &AA_MAY_REPLACE_POLICY ?OP_PROF_REPL :OP_PROF_LOAD ; -aa_get_loaddata (udata); +aa_get_profile_loaddata (udata);/* released below */ error =aa_unpack (udata, &lh, &ns_name);if (error)
@@ -1175,10 +1175,10 @@ ssize_t aa_replace_profiles(struct aa_nsif (aa_rawdata_eq (rawdata_ent, udata)) {struct aa_loaddata *tmp; - tmp =__aa_get_loaddata (rawdata_ent); + tmp =aa_get_profile_loaddata (rawdata_ent);/* check we didn't fail the race */ if (tmp) { -aa_put_loaddata (udata); +aa_put_profile_loaddata (udata); udata = tmp;break ; }
@@ -1191,7 +1191,7 @@ ssize_t aa_replace_profiles(struct aa_nsstruct aa_profile *p;if (aa_g_export_binary) - ent->new->rawdata =aa_get_loaddata (udata); + ent->new->rawdata =aa_get_profile_loaddata (udata); error =__lookup_replace (ns, ent->new->base.hname, !(mask &AA_MAY_REPLACE_POLICY ), &ent->old, &info);
@@ -1324,7 +1324,7 @@ ssize_t aa_replace_profiles(struct aa_ns out:aa_put_ns (ns); -aa_put_loaddata (udata); +aa_put_profile_loaddata (udata);kfree (ns_name);if (error)
security/apparmor/policy_unpack.c +23 -9
@@ -108,34 +108,47 @@ bool aa_rawdata_eq(struct aa_loaddata *lreturn memcmp (l->data, r->data, r->compressed_size ?: r->size) ==0 ; } +static void do_loaddata_free (struct aa_loaddata *d) +{ +kfree_sensitive (d->hash); +kfree_sensitive (d->name); +kvfree (d->data); +kfree_sensitive (d); +} + +void aa_loaddata_kref (struct kref *kref) +{ + struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count); + +do_loaddata_free (d); +} +/* * need to take the ns mutex lock which is NOT safe most places that * put_loaddata is called, so we have to delay freeing it */ -static void do_loaddata_free (struct work_struct *work) +static void do_ploaddata_rmfs (struct work_struct *work) { struct aa_loaddata *d = container_of(work, struct aa_loaddata, work);struct aa_ns *ns =aa_get_ns (d->ns);if (ns) {mutex_lock_nested (&ns->lock, ns->level); +/* remove fs ref to loaddata */ __aa_fs_remove_rawdata (d);mutex_unlock (&ns->lock);aa_put_ns (ns); } - -kfree_sensitive (d->hash); -kfree_sensitive (d->name); -kvfree (d->data); -kfree_sensitive (d); +/* called by dropping last pcount, so drop its associated icount */ +aa_put_i_loaddata (d); } -void aa_loaddata_kref (struct kref *kref) +void aa_ploaddata_kref (struct kref *kref) { - struct aa_loaddata *d = container_of(kref, struct aa_loaddata, count); + struct aa_loaddata *d = container_of(kref, struct aa_loaddata, pcount);if (d) { -INIT_WORK (&d->work, do_loaddata_free); +INIT_WORK (&d->work, do_ploaddata_rmfs);schedule_work (&d->work); } }
@@ -153,6 +166,7 @@ struct aa_loaddata *aa_loaddata_alloc(sireturn ERR_PTR (-ENOMEM ); }kref_init (&d->count); +kref_init (&d->pcount);INIT_LIST_HEAD (&d->list);return d;