Skip to contentSkip to conversation

6.6.14-rc1 review

PATCH In review Greg Kroah-Hartman 9 participants 597 messages Jan 23, 2024 – Jan 24, 2024 Page 4 of 5

Subsystems (8)
lore
Share & tools
lore
author maintainer
#445 lore raw

PATCH 439/583 mfd: cs42l43: Correct SoundWire port list

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Charles Keepax <[email protected]>

[ Upstream commit 47b1b03dc56ebc302620ce43e967aa8f33516f6f ]

Two ports are missing from the port list, and the wrong port is set to 4 channels. Also the attempt to list them by function is rather misguided, there is nothing in the hardware that fixes a particular port to one function. Factor out the port properties to an actual struct, fixing the missing ports and correcting the port set to 4 channels.

Fixes ace6d1448138 ("mfd: cs42l43: Add support for cs42l43 core driver")
---
 drivers/mfd/cs42l43-sdw.c | 74 +++++++++++++++------------------------
 1 file changed, 28 insertions(+), 46 deletions(-)
drivers/mfd/cs42l43-sdw.c +28 -46
index 7392b3d2e6b9..4be4df9dd8cf 100644
@@ -17,13 +17,12 @@
 
 #include "cs42l43.h"
 
-enum cs42l43_sdw_ports {
-	CS42L43_DMIC_DEC_ASP_PORT = 1,
-	CS42L43_SPK_TX_PORT,
-	CS42L43_SPDIF_HP_PORT,
-	CS42L43_SPK_RX_PORT,
-	CS42L43_ASP_PORT,
-};
+#define CS42L43_SDW_PORT(port, chans) { \
+	.num = port, \
+	.max_ch = chans, \
+	.type = SDW_DPN_FULL, \
+	.max_word = 24, \
+}
 
 static const struct regmap_config cs42l43_sdw_regmap = {
 	.reg_bits		= 32,
@@ -42,65 +41,48 @@ static const struct regmap_config cs42l43_sdw_regmap = {
 	.num_reg_defaults	= ARRAY_SIZE(cs42l43_reg_default),
 };
 
+static const struct sdw_dpn_prop cs42l43_src_port_props[] = {
+	CS42L43_SDW_PORT(1, 4),
+	CS42L43_SDW_PORT(2, 2),
+	CS42L43_SDW_PORT(3, 2),
+	CS42L43_SDW_PORT(4, 2),
+};
+
+static const struct sdw_dpn_prop cs42l43_sink_port_props[] = {
+	CS42L43_SDW_PORT(5, 2),
+	CS42L43_SDW_PORT(6, 2),
+	CS42L43_SDW_PORT(7, 2),
+};
+
 static int cs42l43_read_prop(struct sdw_slave *sdw)
 {
 	struct sdw_slave_prop *prop = &sdw->prop;
 	struct device *dev = &sdw->dev;
-	struct sdw_dpn_prop *dpn;
-	unsigned long addr;
-	int nval;
 	int i;
-	u32 bit;
 
 	prop->use_domain_irq = true;
 	prop->paging_support = true;
 	prop->wake_capable = true;
-	prop->source_ports = BIT(CS42L43_DMIC_DEC_ASP_PORT) | BIT(CS42L43_SPK_TX_PORT);
-	prop->sink_ports = BIT(CS42L43_SPDIF_HP_PORT) |
-			   BIT(CS42L43_SPK_RX_PORT) | BIT(CS42L43_ASP_PORT);
 	prop->quirks = SDW_SLAVE_QUIRKS_INVALID_INITIAL_PARITY;
 	prop->scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY |
 			      SDW_SCP_INT1_IMPL_DEF;
 
-	nval = hweight32(prop->source_ports);
-	prop->src_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->src_dpn_prop),
-					  GFP_KERNEL);
+	for (i = 0; i < ARRAY_SIZE(cs42l43_src_port_props); i++)
+		prop->source_ports |= BIT(cs42l43_src_port_props[i].num);
+
+	prop->src_dpn_prop = devm_kmemdup(dev, cs42l43_src_port_props,
+					  sizeof(cs42l43_src_port_props), GFP_KERNEL);
 	if (!prop->src_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->src_dpn_prop;
-	addr = prop->source_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-	/*
-	 * All ports are 2 channels max, except the first one,
-	 * CS42L43_DMIC_DEC_ASP_PORT.
-	 */
-	dpn[CS42L43_DMIC_DEC_ASP_PORT].max_ch = 4;
+	for (i = 0; i < ARRAY_SIZE(cs42l43_sink_port_props); i++)
+		prop->sink_ports |= BIT(cs42l43_sink_port_props[i].num);
 
-	nval = hweight32(prop->sink_ports);
-	prop->sink_dpn_prop = devm_kcalloc(dev, nval, sizeof(*prop->sink_dpn_prop),
-					   GFP_KERNEL);
+	prop->sink_dpn_prop = devm_kmemdup(dev, cs42l43_sink_port_props,
+					   sizeof(cs42l43_sink_port_props), GFP_KERNEL);
 	if (!prop->sink_dpn_prop)
 		return -ENOMEM;
 
-	i = 0;
-	dpn = prop->sink_dpn_prop;
-	addr = prop->sink_ports;
-	for_each_set_bit(bit, &addr, 32) {
-		dpn[i].num = bit;
-		dpn[i].max_ch = 2;
-		dpn[i].type = SDW_DPN_FULL;
-		dpn[i].max_word = 24;
-		i++;
-	}
-
 	return 0;
 }
 
Signature · 1 line
2.43.0
author maintainer
#446 lore raw

PATCH 440/583 mfd: syscon: Fix null pointer dereference in of_syscon_register()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kunwu Chan <[email protected]>

[ Upstream commit 41673c66b3d0c09915698fec5c13b24336f18dd1 ]

kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure.

Fixes e15d7f2b81d2 ("mfd: syscon: Use a unique name with regmap_config")
---
 drivers/mfd/syscon.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/mfd/syscon.c +4 -0
index 57b29c325131..c9550368d9ea 100644
@@ -105,6 +105,10 @@ static struct syscon *of_syscon_register(struct device_node *np, bool check_res)
 	}
 
 	syscon_config.name = kasprintf(GFP_KERNEL, "%pOFn@%pa", np, &res.start);
+	if (!syscon_config.name) {
+		ret = -ENOMEM;
+		goto err_regmap;
+	}
 	syscon_config.reg_stride = reg_io_width;
 	syscon_config.val_bits = reg_io_width * 8;
 	syscon_config.max_register = resource_size(&res) - reg_io_width;
Signature · 1 line
2.43.0
author maintainer
#447 lore raw

PATCH 441/583 leds: aw2013: Select missing dependency REGMAP_I2C

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dang Huynh <[email protected]>

[ Upstream commit 75469bb0537ad2ab0fc1fb6e534a79cfc03f3b3f ]

The AW2013 driver uses devm_regmap_init_i2c, so REGMAP_I2C needs to be selected.

Otherwise build process may fail with:
ld: drivers/leds/leds-aw2013.o: in function `aw2013_probe':

    leds-aw2013.c:345: undefined reference to `__devm_regmap_init_i2c'
---
 drivers/leds/Kconfig | 1 +
 1 file changed, 1 insertion(+)
drivers/leds/Kconfig +1 -0
index b92208eccdea..3132439f99e0 100644
@@ -110,6 +110,7 @@ config LEDS_AW200XX
 config LEDS_AW2013
 	tristate "LED support for Awinic AW2013"
 	depends on LEDS_CLASS && I2C && OF
+	select REGMAP_I2C
 	help
 	  This option enables support for the AW2013 3-channel
 	  LED driver.
Signature · 1 line
2.43.0
author maintainer
#448 lore raw

PATCH 442/583 leds: aw200xx: Fix write to DIM parameter

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin Kurbanov <[email protected]>

[ Upstream commit adfd4621b78d0c02da91335da2b9ad847cb7b39e ]

If write only DIM value to the page 4, LED brightness will not be updated, as both DIM and FADE need to be written to the page 4. Therefore, write DIM to the page 1.

---
 drivers/leds/leds-aw200xx.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/leds/leds-aw200xx.c +6 -1
index 691a743cc9b0..5142efea2339 100644
@@ -74,6 +74,10 @@
 #define AW200XX_LED2REG(x, columns) \
 	((x) + (((x) / (columns)) * (AW200XX_DSIZE_COLUMNS_MAX - (columns))))
 
+/* DIM current configuration register on page 1 */
+#define AW200XX_REG_DIM_PAGE1(x, columns) \
+	AW200XX_REG(AW200XX_PAGE1, AW200XX_LED2REG(x, columns))
+
 /*
  * DIM current configuration register (page 4).
  * The even address for current DIM configuration.
@@ -153,7 +157,8 @@ static ssize_t dim_store(struct device *dev, struct device_attribute *devattr,
 
 	if (dim >= 0) {
 		ret = regmap_write(chip->regmap,
-				   AW200XX_REG_DIM(led->num, columns), dim);
+				   AW200XX_REG_DIM_PAGE1(led->num, columns),
+				   dim);
 		if (ret)
 			goto out_unlock;
 	}
Signature · 1 line
2.43.0
author maintainer
#449 lore raw

PATCH 443/583 mfd: tps6594: Add null pointer check to tps6594_device_init()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kunwu Chan <[email protected]>

[ Upstream commit 825906f2ebe83977d747d8bce61675dddd72485d ]

devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure.

Fixes 325bec7157b3 ("mfd: tps6594: Add driver for TI TPS6594 PMIC")
---
 drivers/mfd/tps6594-core.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/mfd/tps6594-core.c +3 -0
index 0fb9c5cf213a..783ee59901e8 100644
@@ -433,6 +433,9 @@ int tps6594_device_init(struct tps6594 *tps, bool enable_crc)
 	tps6594_irq_chip.name = devm_kasprintf(dev, GFP_KERNEL, "%s-%ld-0x%02x",
 					       dev->driver->name, tps->chip_id, tps->reg);
 
+	if (!tps6594_irq_chip.name)
+		return -ENOMEM;
+
 	ret = devm_regmap_add_irq_chip(dev, tps->regmap, tps->irq, IRQF_SHARED | IRQF_ONESHOT,
 				       0, &tps6594_irq_chip, &tps->irq_data);
 	if (ret)
Signature · 1 line
2.43.0
author maintainer
#450 lore raw

PATCH 444/583 mfd: intel-lpss: Fix the fractional clock divider flags

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Shevchenko <[email protected]>

[ Upstream commit 03d790f04fb2507173913cad9c213272ac983a60 ]

The conversion to CLK_FRAC_DIVIDER_POWER_OF_TWO_PS uses wrong flags in the parameters and hence miscalculates the values in the clock divider. Fix this by applying the flag to the proper parameter.

Fixes 82f53f9ee577 ("clk: fractional-divider: Introduce POWER_OF_TWO_PS flag")
---
 drivers/mfd/intel-lpss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mfd/intel-lpss.c +1 -1
index 9591b354072a..00e7b578bb3e 100644
@@ -301,8 +301,8 @@ static int intel_lpss_register_clock_divider(struct intel_lpss *lpss,
 
 	snprintf(name, sizeof(name), "%s-div", devname);
 	tmp = clk_register_fractional_divider(NULL, name, __clk_get_name(tmp),
+					      0, lpss->priv, 1, 15, 16, 15,
 					      CLK_FRAC_DIVIDER_POWER_OF_TWO_PS,
-					      lpss->priv, 1, 15, 16, 15, 0,
 					      NULL);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
Signature · 1 line
2.43.0
author maintainer
#451 lore raw

PATCH 445/583 srcu: Use try-lock lockdep annotation for NMI-safe access.

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <[email protected]>

[ Upstream commit 3c6b0c1c28184038d90dffe8eb542bedcb8ccf98 ]

It is claimed that srcu_read_lock_nmisafe() NMI-safe. However it triggers a lockdep if used from NMI because lockdep expects a deadlock since nothing disables NMIs while the lock is acquired.

This is because commit f0f44752f5f61 ("rcu: Annotate SRCU's update-side lockdep dependencies") annotates synchronize_srcu() as a write lock usage. This helps to detect a deadlocks such as

	srcu_read_lock();
	synchronize_srcu();
	srcu_read_unlock();

The side effect is that the lock srcu_struct now has a USED usage in normal contexts, so it conflicts with a USED_READ usage in NMI. But this shouldn't cause a real deadlock because the write lock usage from synchronize_srcu() is a fake one and only used for read/write deadlock detection.

Use a try-lock annotation for srcu_read_lock_nmisafe() to avoid lockdep complains if used from NMI.

---
 include/linux/rcupdate.h | 6 ++++++
 include/linux/srcu.h     | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)
include/linux/rcupdate.h +6 -0
index 5e5f920ade90..44aab5c0bd2c 100644
@@ -303,6 +303,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map)
 	lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
 }
 
+static inline void rcu_try_lock_acquire(struct lockdep_map *map)
+{
+	lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_);
+}
+
 static inline void rcu_lock_release(struct lockdep_map *map)
 {
 	lock_release(map, _THIS_IP_);
@@ -317,6 +322,7 @@ int rcu_read_lock_any_held(void);
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 # define rcu_lock_acquire(a)		do { } while (0)
+# define rcu_try_lock_acquire(a)	do { } while (0)
 # define rcu_lock_release(a)		do { } while (0)
 
 static inline int rcu_read_lock_held(void)
include/linux/srcu.h +1 -1
index 127ef3b2e607..236610e4a8fa 100644
@@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp
 
 	srcu_check_nmi_safety(ssp, true);
 	retval = __srcu_read_lock_nmisafe(ssp);
-	rcu_lock_acquire(&ssp->dep_map);
+	rcu_try_lock_acquire(&ssp->dep_map);
 	return retval;
 }
 
Signature · 1 line
2.43.0
author maintainer
#452 lore raw

PATCH 446/583 mips: dmi: Fix early remap on MIPS32

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Serge Semin <[email protected]>

[ Upstream commit 0d0a3748a2cb38f9da1f08d357688ebd982eb788 ]

dmi_early_remap() has been defined as ioremap_cache() which on MIPS32 gets to be converted to the VM-based mapping. DMI early remapping is performed at the setup_arch() stage with no VM available. So calling the dmi_early_remap() for MIPS32 causes the system to crash at the early boot time. Fix that by converting dmi_early_remap() to the uncached remapping which is always available on both 32 and 64-bits MIPS systems.

Note this change shall not cause any regressions on the current DMI support implementation because on the early boot-up stage neither MIPS32 nor MIPS64 has the cacheable ioremapping support anyway.

Fixes be8fa1cb444c ("MIPS: Add support for Desktop Management Interface (DMI)")
---
 arch/mips/include/asm/dmi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/mips/include/asm/dmi.h +1 -1
index 27415a288adf..dc397f630c66 100644
@@ -5,7 +5,7 @@
 #include <linux/io.h>
 #include <linux/memblock.h>
 
-#define dmi_early_remap(x, l)		ioremap_cache(x, l)
+#define dmi_early_remap(x, l)		ioremap(x, l)
 #define dmi_early_unmap(x, l)		iounmap(x)
 #define dmi_remap(x, l)			ioremap_cache(x, l)
 #define dmi_unmap(x)			iounmap(x)
Signature · 1 line
2.43.0
author maintainer
#453 lore raw

PATCH 447/583 mips: Fix incorrect max_low_pfn adjustment

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Serge Semin <[email protected]>

[ Upstream commit 0f5cc249ff73552d3bd864e62f85841dafaa107d ]

max_low_pfn variable is incorrectly adjusted if the kernel is built with high memory support and the later is detected in a running system, so the memory which actually can be directly mapped is getting into the highmem zone. See the ZONE_NORMAL range on my MIPS32r5 system:

Quoted 4 lines

Zone ranges:

  DMA      [mem 0x0000000000000000-0x0000000000ffffff]
  Normal   [mem 0x0000000001000000-0x0000000007ffffff]
  HighMem  [mem 0x0000000008000000-0x000000020fffffff]

while the zones are supposed to look as follows:

Quoted 4 lines

Zone ranges:

  DMA      [mem 0x0000000000000000-0x0000000000ffffff]
  Normal   [mem 0x0000000001000000-0x000000001fffffff]
  HighMem  [mem 0x0000000020000000-0x000000020fffffff]

Even though the physical memory within the range [0x08000000;0x20000000] belongs to MMIO on our system, we don't really want it to be considered as high memory since on MIPS32 that range still can be directly mapped.

Note there might be other problems caused by the max_low_pfn variable misconfiguration. For instance high_memory variable is initialize with virtual address corresponding to the max_low_pfn PFN, and by design it must define the upper bound on direct map memory, then end of the normal zone. That in its turn potentially may cause problems in accessing the memory by means of the /dev/mem and /dev/kmem devices.

Let's fix the discovered misconfiguration then. It turns out the commit a94e4f24ec83 ("MIPS: init: Drop boot_mem_map") didn't introduce the max_low_pfn adjustment quite correct. If the kernel is built with high memory support and the system is equipped with high memory, the max_low_pfn variable will need to be initialized with PFN of the most upper directly reachable memory address so the zone normal would be correctly setup. On MIPS that PFN corresponds to PFN_DOWN(HIGHMEM_START). If the system is built with no high memory support and one is detected in the running system, we'll just need to adjust the max_pfn variable to discard the found high memory from the system and leave the max_low_pfn as is, since the later will be less than PFN_DOWN(HIGHMEM_START) anyway by design of the for_each_memblock() loop performed a bit early in the bootmem_init() method.

Fixes a94e4f24ec83 ("MIPS: init: Drop boot_mem_map")
---
 arch/mips/kernel/setup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/mips/kernel/setup.c +2 -2
index cb871eb784a7..f88a2f83c5ea 100644
@@ -326,11 +326,11 @@ static void __init bootmem_init(void)
 		panic("Incorrect memory mapping !!!");
 
 	if (max_pfn > PFN_DOWN(HIGHMEM_START)) {
+		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 #ifdef CONFIG_HIGHMEM
-		highstart_pfn = PFN_DOWN(HIGHMEM_START);
+		highstart_pfn = max_low_pfn;
 		highend_pfn = max_pfn;
 #else
-		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 		max_pfn = max_low_pfn;
 #endif
 	}
Signature · 1 line
2.43.0
author maintainer
#454 lore raw

PATCH 448/583 um: virt-pci: fix platform map offset

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vincent Whitchurch <[email protected]>

[ Upstream commit 32253f00ac8a8073bf6db4bfe9d6511cc93c4aef ]

The offset is currently always zero so the backend can't distinguish between accesses to different ioremapped areas.

Fixes 522c532c4fe7 ("virt-pci: add platform bus support")
---
 arch/um/drivers/virt-pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/um/drivers/virt-pci.c +1 -1
index ffe2ee8a0246..97a37c062997 100644
@@ -971,7 +971,7 @@ static long um_pci_map_platform(unsigned long offset, size_t size,
 	*ops = &um_pci_device_bar_ops;
 	*priv = &um_pci_platform_device->resptr[0];
 
-	return 0;
+	return offset;
 }
 
 static const struct logic_iomem_region_ops um_pci_platform_ops = {
Signature · 1 line
2.43.0
author maintainer
#455 lore raw

PATCH 449/583 riscv: Check if the code to patch lies in the exit section

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Ghiti <[email protected]>

[ Upstream commit 420370f3ae3d3b883813fd3051a38805160b2b9f ]

Otherwise we fall through to vmalloc_to_page() which panics since the address does not lie in the vmalloc region.

Fixes 043cb41a85de ("riscv: introduce interfaces to patch kernel code")
---
 arch/riscv/include/asm/sections.h   |  1 +
 arch/riscv/kernel/patch.c           | 11 ++++++++++-
 arch/riscv/kernel/vmlinux-xip.lds.S |  2 ++
 arch/riscv/kernel/vmlinux.lds.S     |  2 ++
 4 files changed, 15 insertions(+), 1 deletion(-)
arch/riscv/include/asm/sections.h +1 -0
index 32336e8a17cb..a393d5035c54 100644
@@ -13,6 +13,7 @@ extern char _start_kernel[];
 extern char __init_data_begin[], __init_data_end[];
 extern char __init_text_begin[], __init_text_end[];
 extern char __alt_start[], __alt_end[];
+extern char __exittext_begin[], __exittext_end[];
 
 static inline bool is_va_kernel_text(uintptr_t va)
 {
arch/riscv/kernel/patch.c +10 -1
index 13ee7bf589a1..37e87fdcf6a0 100644
@@ -14,6 +14,7 @@
 #include <asm/fixmap.h>
 #include <asm/ftrace.h>
 #include <asm/patch.h>
+#include <asm/sections.h>
 
 struct patch_insn {
 	void *addr;
@@ -25,6 +26,14 @@ struct patch_insn {
 int riscv_patch_in_stop_machine = false;
 
 #ifdef CONFIG_MMU
+
+static inline bool is_kernel_exittext(uintptr_t addr)
+{
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (uintptr_t)__exittext_begin &&
+		addr < (uintptr_t)__exittext_end;
+}
+
 /*
  * The fix_to_virt(, idx) needs a const value (not a dynamic variable of
  * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
@@ -35,7 +44,7 @@ static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
 	uintptr_t uintaddr = (uintptr_t) addr;
 	struct page *page;
 
-	if (core_kernel_text(uintaddr))
+	if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
 		page = phys_to_page(__pa_symbol(addr));
 	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 		page = vmalloc_to_page(addr);
arch/riscv/kernel/vmlinux-xip.lds.S +2 -0
index 50767647fbc6..8c3daa1b0531 100644
@@ -29,10 +29,12 @@ SECTIONS
 	HEAD_TEXT_SECTION
 	INIT_TEXT_SECTION(PAGE_SIZE)
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	.text : {
 		_text = .;
arch/riscv/kernel/vmlinux.lds.S +2 -0
index 492dd4b8f3d6..002ca58dd998 100644
@@ -69,10 +69,12 @@ SECTIONS
 		__soc_builtin_dtb_table_end = .;
 	}
 	/* we have to discard exit text and such at runtime, not link time */
+	__exittext_begin = .;
 	.exit.text :
 	{
 		EXIT_TEXT
 	}
+	__exittext_end = .;
 
 	__init_text_end = .;
 	. = ALIGN(SECTION_ALIGN);
Signature · 1 line
2.43.0
author maintainer
#456 lore raw

PATCH 450/583 riscv: Fix module_alloc() that did not reset the linear mapping permissions

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Ghiti <[email protected]>

[ Upstream commit 749b94b08005929bbc636df21a23322733166e35 ]

After unloading a module, we must reset the linear mapping permissions, see the example below:

Before unloading a module:

0xffffaf809d65d000-0xffffaf809d6dc000    0x000000011d65d000       508K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6dc000-0xffffaf809d6dd000    0x000000011d6dc000         4K PTE .   ..     ..   D A G . . . R V
0xffffaf809d6dd000-0xffffaf809d6e1000    0x000000011d6dd000        16K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6e1000-0xffffaf809d6e7000    0x000000011d6e1000        24K PTE .   ..     ..   D A G . X . R V

After unloading a module:

0xffffaf809d65d000-0xffffaf809d6e1000    0x000000011d65d000       528K PTE .   ..     ..   D A G . . W R V
0xffffaf809d6e1000-0xffffaf809d6e7000    0x000000011d6e1000        24K PTE .   ..     ..   D A G . X W R V

The last mapping is not reset and we end up with WX mappings in the linear mapping.

So add VM_FLUSH_RESET_PERMS to our module_alloc() definition.

Fixes 0cff8bff7af8 ("riscv: avoid the PIC offset of static percpu data in module beyond 2G limits")
---
 arch/riscv/kernel/module.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/riscv/kernel/module.c +2 -1
index 7c651d55fcbd..df4f6fec5d17 100644
@@ -440,7 +440,8 @@ void *module_alloc(unsigned long size)
 {
 	return __vmalloc_node_range(size, 1, MODULES_VADDR,
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE,
 				    __builtin_return_address(0));
 }
 #endif
Signature · 1 line
2.43.0
author maintainer
#457 lore raw

PATCH 451/583 riscv: Fix set_memory_XX() and set_direct_map_XX() by splitting huge linear mappings

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Ghiti <[email protected]>

[ Upstream commit 311cd2f6e25380cff0abc2884dc6a3d33bc9b5c3 ]

When STRICT_KERNEL_RWX is set, any change of permissions on any kernel mapping (vmalloc/modules/kernel text...etc) should be applied on its linear mapping alias. The problem is that the riscv kernel uses huge mappings for the linear mapping and walk_page_range_novma() does not split those huge mappings.

So this patchset implements such split in order to apply fine-grained permissions on the linear mapping.

Below is the difference before and after (the first PUD mapping is split into PTE/PMD mappings):

Before:

---[ Linear mapping ]---

0xffffaf8000080000-0xffffaf8000200000    0x0000000080080000      1536K PTE     D A G . . W R V
0xffffaf8000200000-0xffffaf8077c00000    0x0000000080200000      1914M PMD     D A G . . W R V
0xffffaf8077c00000-0xffffaf8078800000    0x00000000f7c00000        12M PMD     D A G . . . R V
0xffffaf8078800000-0xffffaf8078c00000    0x00000000f8800000         4M PMD     D A G . . W R V
0xffffaf8078c00000-0xffffaf8079200000    0x00000000f8c00000         6M PMD     D A G . . . R V
0xffffaf8079200000-0xffffaf807e600000    0x00000000f9200000        84M PMD     D A G . . W R V
0xffffaf807e600000-0xffffaf807e716000    0x00000000fe600000      1112K PTE     D A G . . W R V
0xffffaf807e717000-0xffffaf807e71a000    0x00000000fe717000        12K PTE     D A G . . W R V
0xffffaf807e71d000-0xffffaf807e71e000    0x00000000fe71d000         4K PTE     D A G . . W R V
0xffffaf807e722000-0xffffaf807e800000    0x00000000fe722000       888K PTE     D A G . . W R V
0xffffaf807e800000-0xffffaf807fe00000    0x00000000fe800000        22M PMD     D A G . . W R V
0xffffaf807fe00000-0xffffaf807ff54000    0x00000000ffe00000      1360K PTE     D A G . . W R V
0xffffaf807ff55000-0xffffaf8080000000    0x00000000fff55000       684K PTE     D A G . . W R V
0xffffaf8080000000-0xffffaf8400000000    0x0000000100000000        14G PUD     D A G . . W R V

After:

---[ Linear mapping ]---

0xffffaf8000080000-0xffffaf8000200000    0x0000000080080000      1536K PTE     D A G . . W R V
0xffffaf8000200000-0xffffaf8077c00000    0x0000000080200000      1914M PMD     D A G . . W R V
0xffffaf8077c00000-0xffffaf8078800000    0x00000000f7c00000        12M PMD     D A G . . . R V
0xffffaf8078800000-0xffffaf8078a00000    0x00000000f8800000         2M PMD     D A G . . W R V
0xffffaf8078a00000-0xffffaf8078c00000    0x00000000f8a00000         2M PTE     D A G . . W R V
0xffffaf8078c00000-0xffffaf8079200000    0x00000000f8c00000         6M PMD     D A G . . . R V
0xffffaf8079200000-0xffffaf807e600000    0x00000000f9200000        84M PMD     D A G . . W R V
0xffffaf807e600000-0xffffaf807e716000    0x00000000fe600000      1112K PTE     D A G . . W R V
0xffffaf807e717000-0xffffaf807e71a000    0x00000000fe717000        12K PTE     D A G . . W R V
0xffffaf807e71d000-0xffffaf807e71e000    0x00000000fe71d000         4K PTE     D A G . . W R V
0xffffaf807e722000-0xffffaf807e800000    0x00000000fe722000       888K PTE     D A G . . W R V
0xffffaf807e800000-0xffffaf807fe00000    0x00000000fe800000        22M PMD     D A G . . W R V
0xffffaf807fe00000-0xffffaf807ff54000    0x00000000ffe00000      1360K PTE     D A G . . W R V
0xffffaf807ff55000-0xffffaf8080000000    0x00000000fff55000       684K PTE     D A G . . W R V
0xffffaf8080000000-0xffffaf8080800000    0x0000000100000000         8M PMD     D A G . . W R V
0xffffaf8080800000-0xffffaf8080af6000    0x0000000100800000      3032K PTE     D A G . . W R V
0xffffaf8080af6000-0xffffaf8080af8000    0x0000000100af6000         8K PTE     D A G . X . R V
0xffffaf8080af8000-0xffffaf8080c00000    0x0000000100af8000      1056K PTE     D A G . . W R V
0xffffaf8080c00000-0xffffaf8081a00000    0x0000000100c00000        14M PMD     D A G . . W R V
0xffffaf8081a00000-0xffffaf8081a40000    0x0000000101a00000       256K PTE     D A G . . W R V
0xffffaf8081a40000-0xffffaf8081a44000    0x0000000101a40000        16K PTE     D A G . X . R V
0xffffaf8081a44000-0xffffaf8081a52000    0x0000000101a44000        56K PTE     D A G . . W R V
0xffffaf8081a52000-0xffffaf8081a54000    0x0000000101a52000         8K PTE     D A G . X . R V
...
0xffffaf809e800000-0xffffaf80c0000000    0x000000011e800000       536M PMD     D A G . . W R V
0xffffaf80c0000000-0xffffaf8400000000    0x0000000140000000        13G PUD     D A G . . W R V

Note that this also fixes memfd_secret() syscall which uses set_direct_map_invalid_noflush() and set_direct_map_default_noflush() to remove the pages from the linear mapping. Below is the kernel page table while a memfd_secret() syscall is running, you can see all the !valid page table entries in the linear mapping:

...

0xffffaf8082240000-0xffffaf8082241000    0x0000000102240000         4K PTE     D A G . . W R .
0xffffaf8082241000-0xffffaf8082250000    0x0000000102241000        60K PTE     D A G . . W R V
0xffffaf8082250000-0xffffaf8082252000    0x0000000102250000         8K PTE     D A G . . W R .
0xffffaf8082252000-0xffffaf8082256000    0x0000000102252000        16K PTE     D A G . . W R V
0xffffaf8082256000-0xffffaf8082257000    0x0000000102256000         4K PTE     D A G . . W R .
0xffffaf8082257000-0xffffaf8082258000    0x0000000102257000         4K PTE     D A G . . W R V
0xffffaf8082258000-0xffffaf8082259000    0x0000000102258000         4K PTE     D A G . . W R .
0xffffaf8082259000-0xffffaf808225a000    0x0000000102259000         4K PTE     D A G . . W R V
0xffffaf808225a000-0xffffaf808225c000    0x000000010225a000         8K PTE     D A G . . W R .
0xffffaf808225c000-0xffffaf8082266000    0x000000010225c000        40K PTE     D A G . . W R V
0xffffaf8082266000-0xffffaf8082268000    0x0000000102266000         8K PTE     D A G . . W R .
0xffffaf8082268000-0xffffaf8082284000    0x0000000102268000       112K PTE     D A G . . W R V
0xffffaf8082284000-0xffffaf8082288000    0x0000000102284000        16K PTE     D A G . . W R .
0xffffaf8082288000-0xffffaf808229c000    0x0000000102288000        80K PTE     D A G . . W R V
0xffffaf808229c000-0xffffaf80822a0000    0x000000010229c000        16K PTE     D A G . . W R .
0xffffaf80822a0000-0xffffaf80822a5000    0x00000001022a0000        20K PTE     D A G . . W R V
0xffffaf80822a5000-0xffffaf80822a6000    0x00000001022a5000         4K PTE     D A G . . . R V
0xffffaf80822a6000-0xffffaf80822ab000    0x00000001022a6000        20K PTE     D A G . . W R V

...

And when the memfd_secret() fd is released, the linear mapping is correctly reset:

...

0xffffaf8082240000-0xffffaf80822a5000    0x0000000102240000       404K PTE     D A G . . W R V
0xffffaf80822a5000-0xffffaf80822a6000    0x00000001022a5000         4K PTE     D A G . . . R V
0xffffaf80822a6000-0xffffaf80822af000    0x00000001022a6000        36K PTE     D A G . . W R V

...

Stable-dep-of: b8b2711336f0 ("riscv: Fix set_direct_map_default_noflush() to reset _PAGE_EXEC")

---
 arch/riscv/mm/pageattr.c | 270 +++++++++++++++++++++++++++++++++------
 1 file changed, 230 insertions(+), 40 deletions(-)
arch/riscv/mm/pageattr.c +230 -40
index 161d0b34c2cb..fc5fc4f785c4 100644
@@ -5,6 +5,7 @@
 
 #include <linux/pagewalk.h>
 #include <linux/pgtable.h>
+#include <linux/vmalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/bitops.h>
 #include <asm/set_memory.h>
@@ -25,19 +26,6 @@ static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
 	return new_val;
 }
 
-static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
-{
-	pgd_t val = READ_ONCE(*pgd);
-
-	if (pgd_leaf(val)) {
-		val = __pgd(set_pageattr_masks(pgd_val(val), walk));
-		set_pgd(pgd, val);
-	}
-
-	return 0;
-}
-
 static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
 			      unsigned long next, struct mm_walk *walk)
 {
@@ -96,7 +84,6 @@ static int pageattr_pte_hole(unsigned long addr, unsigned long next,
 }
 
 static const struct mm_walk_ops pageattr_ops = {
-	.pgd_entry = pageattr_pgd_entry,
 	.p4d_entry = pageattr_p4d_entry,
 	.pud_entry = pageattr_pud_entry,
 	.pmd_entry = pageattr_pmd_entry,
@@ -105,12 +92,181 @@ static const struct mm_walk_ops pageattr_ops = {
 	.walk_lock = PGWALK_RDLOCK,
 };
 
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(*pmdp)) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(*pmdp);
+			pgprot_t prot = __pgprot(pmd_val(*pmdp) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(*pudp)) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(*pudp);
+			pgprot_t prot = __pgprot(pud_val(*pudp) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(*p4dp)) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(*p4dp);
+			pgprot_t prot = __pgprot(p4d_val(*p4dp) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
 static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 			pgprot_t clear_mask)
 {
 	int ret;
 	unsigned long start = addr;
 	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
 	struct pageattr_masks masks = {
 		.set_mask = set_mask,
 		.clear_mask = clear_mask
@@ -120,11 +276,67 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 		return 0;
 
 	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		lm_start = (unsigned long)lm_alias(start);
+		lm_end = (unsigned long)lm_alias(end);
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
 	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
 				     &masks);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+				     &masks);
+
 	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
+#endif
 
 	return ret;
 }
@@ -159,36 +371,14 @@ int set_memory_nx(unsigned long addr, int numpages)
 
 int set_direct_map_invalid_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = __pgprot(0),
-		.clear_mask = __pgprot(_PAGE_PRESENT)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
 }
 
 int set_direct_map_default_noflush(struct page *page)
 {
-	int ret;
-	unsigned long start = (unsigned long)page_address(page);
-	unsigned long end = start + PAGE_SIZE;
-	struct pageattr_masks masks = {
-		.set_mask = PAGE_KERNEL,
-		.clear_mask = __pgprot(0)
-	};
-
-	mmap_read_lock(&init_mm);
-	ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks);
-	mmap_read_unlock(&init_mm);
-
-	return ret;
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(0));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
Signature · 1 line
2.43.0
author maintainer
#458 lore raw

PATCH 452/583 riscv: Fix set_direct_map_default_noflush() to reset _PAGE_EXEC

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandre Ghiti <[email protected]>

[ Upstream commit b8b2711336f03ece539de61479d6ffc44fb603d3 ]

When resetting the linear mapping permissions, we must make sure that we clear the X bit so that do not end up with WX mappings (since we set PAGE_KERNEL).

Fixes 395a21ff859c ("riscv: add ARCH_HAS_SET_DIRECT_MAP support")
---
 arch/riscv/mm/pageattr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/riscv/mm/pageattr.c +1 -1
index fc5fc4f785c4..e703a9b59fc3 100644
@@ -378,7 +378,7 @@ int set_direct_map_invalid_noflush(struct page *page)
 int set_direct_map_default_noflush(struct page *page)
 {
 	return __set_memory((unsigned long)page_address(page), 1,
-			    PAGE_KERNEL, __pgprot(0));
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
Signature · 1 line
2.43.0
author maintainer
#459 lore raw

PATCH 453/583 riscv: Fixed wrong register in XIP_FIXUP_FLASH_OFFSET macro

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Frederik Haxel <[email protected]>

[ Upstream commit 5daa3726410288075ba73c336bb2e80d6b06aa4d ]

During the refactoring, a bug was introduced in the rarly used XIP_FIXUP_FLASH_OFFSET macro.

Fixes bee7fbc38579 ("RISC-V CPU Idle Support")
Fixes e7681beba992 ("RISC-V: Split out the XIP fixups into their own file")
---
 arch/riscv/include/asm/xip_fixup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/riscv/include/asm/xip_fixup.h +1 -1
index d4ffc3c37649..b65bf6306f69 100644
@@ -13,7 +13,7 @@
         add \reg, \reg, t0
 .endm
 .macro XIP_FIXUP_FLASH_OFFSET reg
-	la t1, __data_loc
+	la t0, __data_loc
 	REG_L t1, _xip_phys_offset
 	sub \reg, \reg, t1
 	add \reg, \reg, t0
Signature · 1 line
2.43.0
author maintainer
#460 lore raw

PATCH 454/583 MIPS: Alchemy: Fix an out-of-bound access in db1200_dev_setup()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit 89c4b588d11e9acf01d604de4b0c715884f59213 ]

When calling spi_register_board_info(), we should pass the number of elements in 'db1200_spi_devs', not 'db1200_i2c_devs'.

Fixes 63323ec54a7e ("MIPS: Alchemy: Extended DB1200 board support.")
---
 arch/mips/alchemy/devboards/db1200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/mips/alchemy/devboards/db1200.c +1 -1
index f521874ebb07..67f067706af2 100644
@@ -847,7 +847,7 @@ int __init db1200_dev_setup(void)
 	i2c_register_board_info(0, db1200_i2c_devs,
 				ARRAY_SIZE(db1200_i2c_devs));
 	spi_register_board_info(db1200_spi_devs,
-				ARRAY_SIZE(db1200_i2c_devs));
+				ARRAY_SIZE(db1200_spi_devs));
 
 	/* SWITCHES:	S6.8 I2C/SPI selector  (OFF=I2C	 ON=SPI)
 	 *		S6.7 AC97/I2S selector (OFF=AC97 ON=I2S)
Signature · 1 line
2.43.0
author maintainer
#461 lore raw

PATCH 455/583 MIPS: Alchemy: Fix an out-of-bound access in db1550_dev_setup()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit 3c1e5abcda64bed0c7bffa65af2316995f269a61 ]

When calling spi_register_board_info(),

Fixes f869d42e580f ("MIPS: Alchemy: Improved DB1550 support, with audio and serial busses.")
---
 arch/mips/alchemy/devboards/db1550.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/mips/alchemy/devboards/db1550.c +1 -1
index fd91d9c9a252..6c6837181f55 100644
@@ -589,7 +589,7 @@ int __init db1550_dev_setup(void)
 	i2c_register_board_info(0, db1550_i2c_devs,
 				ARRAY_SIZE(db1550_i2c_devs));
 	spi_register_board_info(db1550_spi_devs,
-				ARRAY_SIZE(db1550_i2c_devs));
+				ARRAY_SIZE(db1550_spi_devs));
 
 	c = clk_get(NULL, "psc0_intclk");
 	if (!IS_ERR(c)) {
Signature · 1 line
2.43.0
author maintainer
#462 lore raw

PATCH 456/583 power: supply: cw2015: correct time_to_empty units in sysfs

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jan Palus <[email protected]>

[ Upstream commit f37669119423ca852ca855b24732f25c0737aa57 ]

RRT_ALRT register holds remaining battery time in minutes therefore it needs to be scaled accordingly when exposing TIME_TO_EMPTY via sysfs expressed in seconds

Fixes b4c7715c10c1 ("power: supply: add CellWise cw2015 fuel gauge driver")
---
 drivers/power/supply/cw2015_battery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/power/supply/cw2015_battery.c +1 -1
index bb29e9ebd24a..99f3ccdc30a6 100644
@@ -491,7 +491,7 @@ static int cw_battery_get_property(struct power_supply *psy,
 
 	case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW:
 		if (cw_battery_valid_time_to_empty(cw_bat))
-			val->intval = cw_bat->time_to_empty;
+			val->intval = cw_bat->time_to_empty * 60;
 		else
 			val->intval = 0;
 		break;
Signature · 1 line
2.43.0
author maintainer
#463 lore raw

PATCH 457/583 power: supply: bq256xx: fix some problem in bq256xx_hw_init

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Su Hui <[email protected]>

[ Upstream commit b55d073e6501dc6077edaa945a6dad8ac5c8bbab ]

smatch complains that there is a buffer overflow and clang complains 'ret' is never read.

Smatch error:
drivers/power/supply/bq256xx_charger.c:1578 bq256xx_hw_init() error:
buffer overflow 'bq256xx_watchdog_time' 4 <= 4

Clang static checker:
Value stored to 'ret' is never read.

Add check for buffer overflow and error code from regmap_update_bits().

Fixes 32e4978bb920 ("power: supply: bq256xx: Introduce the BQ256XX charger driver")
---
 drivers/power/supply/bq256xx_charger.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/power/supply/bq256xx_charger.c +4 -1
index 82d3cd5ee2f9..c8368dae69c7 100644
@@ -1574,13 +1574,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq)
 			wd_reg_val = i;
 			break;
 		}
-		if (bq->watchdog_timer > bq256xx_watchdog_time[i] &&
+		if (i + 1 < BQ256XX_NUM_WD_VAL &&
+		    bq->watchdog_timer > bq256xx_watchdog_time[i] &&
 		    bq->watchdog_timer < bq256xx_watchdog_time[i + 1])
 			wd_reg_val = i;
 	}
 	ret = regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_1,
 				 BQ256XX_WATCHDOG_MASK, wd_reg_val <<
 						BQ256XX_WDT_BIT_SHIFT);
+	if (ret)
+		return ret;
 
 	ret = power_supply_get_battery_info(bq->charger, &bat_info);
 	if (ret == -ENOMEM)
Signature · 1 line
2.43.0
author maintainer
#464 lore raw

PATCH 458/583 PCI: Avoid potential out-of-bounds read in pci_dev_for_each_resource()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andy Shevchenko <[email protected]>

[ Upstream commit 3171e46d677a668eed3086da78671f1e4f5b8405 ]

Coverity complains that pointer in the pci_dev_for_each_resource() may be wrong, i.e., might be used for the out-of-bounds read.

There is no actual issue right now because we have another check afterwards and the out-of-bounds read is not being performed. In any case it's better code with this fixed, hence the proposed change.

As Jonas pointed out "It probably makes the code slightly less performant as res will now be checked for being not NULL (which will always be true), but I doubt it will be significant (or in any hot paths)."

---
 include/linux/pci.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
include/linux/pci.h +6 -6
index 1596b1205b8d..3af5f2998551 100644
@@ -2101,14 +2101,14 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 	(pci_resource_end((dev), (bar)) ? 				\
 	 resource_size(pci_resource_n((dev), (bar))) : 0)
 
-#define __pci_dev_for_each_res0(dev, res, ...)				\
-	for (unsigned int __b = 0;					\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res0(dev, res, ...)				  \
+	for (unsigned int __b = 0;					  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
-#define __pci_dev_for_each_res1(dev, res, __b)				\
-	for (__b = 0;							\
-	     res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES;	\
+#define __pci_dev_for_each_res1(dev, res, __b)				  \
+	for (__b = 0;							  \
+	     __b < PCI_NUM_RESOURCES && (res = pci_resource_n(dev, __b)); \
 	     __b++)
 
 #define pci_dev_for_each_resource(dev, res, ...)			\
Signature · 1 line
2.43.0
author maintainer
#465 lore raw

PATCH 459/583 serial: 8250: omap: Dont skip resource freeing if pm_runtime_resume_and_get() failed

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Uwe Kleine-König <[email protected]>

[ Upstream commit ad90d0358bd3b4554f243a425168fc7cebe7d04e ]

Returning an error code from .remove() makes the driver core emit the little helpful error message:

remove callback returned a non-zero value. This will be ignored.

and then remove the device anyhow. So all resources that were not freed are leaked in this case. Skipping serial8250_unregister_port() has the potential to keep enough of the UART around to trigger a use-after-free.

So replace the error return (and with it the little helpful error message) by a more useful error message and continue to cleanup.

Fixes e3f0c638f428 ("serial: 8250: omap: Fix unpaired pm_runtime_put_sync() in omap8250_remove()")
---
 drivers/tty/serial/8250/8250_omap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/8250/8250_omap.c +1 -1
index 1122f37fe744..346167afe9e1 100644
@@ -1581,7 +1581,7 @@ static int omap8250_remove(struct platform_device *pdev)
 
 	err = pm_runtime_resume_and_get(&pdev->dev);
 	if (err)
-		return err;
+		dev_err(&pdev->dev, "Failed to resume hardware\n");
 
 	up = serial8250_get_port(priv->line);
 	omap_8250_shutdown(&up->port);
Signature · 1 line
2.43.0
author maintainer
#466 lore raw

PATCH 460/583 iommu: Map reserved memory as cacheable if device is coherent

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Laurentiu Tudor <[email protected]>

[ Upstream commit f1aad9df93f39267e890836a28d22511f23474e1 ]

Check if the device is marked as DMA coherent in the DT and if so, map its reserved memory as cacheable in the IOMMU.
This fixes the recently added IOMMU reserved memory support which uses IOMMU_RESV_DIRECT without properly building the PROT for the mapping.

---
 drivers/iommu/of_iommu.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/iommu/of_iommu.c +3 -0
index 35ba090f3b5e..47302b637cc0 100644
@@ -260,6 +260,9 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 				phys_addr_t iova;
 				size_t length;
 
+				if (of_dma_is_coherent(dev->of_node))
+					prot |= IOMMU_CACHE;
+
 				maps = of_translate_dma_region(np, maps, &iova, &length);
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
Signature · 1 line
2.43.0
author maintainer
#467 lore raw

PATCH 461/583 perf test: Remove atomics from test_loop to avoid test failures

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nick Forrington <[email protected]>

[ Upstream commit 72b4ca7e993e94f09bcf6d19fc385a2e8060c71f ]

The current use of atomics can lead to test failures, as tests (such as tests/shell/record.sh) search for samples with "test_loop" as the top-most stack frame, but find frames related to the atomic operation (e.g. __aarch64_ldadd4_relax).

This change simply removes the "count" variable, as it is not necessary.

Fixes 1962ab6f6e0b39e4 ("perf test workload thloop: Make count increments atomic")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
---
 tools/perf/tests/workloads/thloop.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
tools/perf/tests/workloads/thloop.c +1 -3
index af05269c2eb8..457b29f91c3e 100644
@@ -7,7 +7,6 @@
 #include "../tests.h"
 
 static volatile sig_atomic_t done;
-static volatile unsigned count;
 
 /* We want to check this symbol in perf report */
 noinline void test_loop(void);
@@ -19,8 +18,7 @@ static void sighandler(int sig __maybe_unused)
 
 noinline void test_loop(void)
 {
-	while (!done)
-		__atomic_fetch_add(&count, 1, __ATOMIC_RELAXED);
+	while (!done);
 }
 
 static void *thfunc(void *arg)
Signature · 1 line
2.43.0
author maintainer
#468 lore raw

PATCH 462/583 perf header: Fix segfault on build_mem_topology() error path

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adrian Hunter <[email protected]>

[ Upstream commit 70df07838fc1c0acfab3325ae79014e241a88bdf ]

Do not increase the node count unless a node has been successfully read, because it can lead to a segfault if an error occurs.

For example, if perf exceeds the open file limit in memory_node__read(), which, on a test system, could be made to happen by setting the file limit to exactly 32:

Before:

  $ ulimit -n 32
  $ perf mem record --all-user -- sleep 1
  [ perf record: Woken up 1 times to write data ]
  failed: can't open memory sysfs data
  perf: Segmentation fault
  Obtained 14 stack frames.
  perf(sighandler_dump_stack+0x48) [0x55f4b1f59558]
  /lib/x86_64-linux-gnu/libc.so.6(+0x42520) [0x7f4ba1c42520]
  /lib/x86_64-linux-gnu/libc.so.6(free+0x1e) [0x7f4ba1ca53fe]
  perf(+0x178ff4) [0x55f4b1f48ff4]
  perf(+0x179a70) [0x55f4b1f49a70]
  perf(+0x17ef5d) [0x55f4b1f4ef5d]
  perf(+0x85c0b) [0x55f4b1e55c0b]
  perf(cmd_record+0xe1d) [0x55f4b1e5920d]
  perf(cmd_mem+0xc96) [0x55f4b1e80e56]
  perf(+0x130460) [0x55f4b1f00460]
  perf(main+0x689) [0x55f4b1e427d9]
  /lib/x86_64-linux-gnu/libc.so.6(+0x29d90) [0x7f4ba1c29d90]
  /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80) [0x7f4ba1c29e40]
  perf(_start+0x25) [0x55f4b1e42a25]
  Segmentation fault (core dumped)
  $

After:

  $ ulimit -n 32
  $ perf mem record --all-user -- sleep 1
  [ perf record: Woken up 1 times to write data ]
  failed: can't open memory sysfs data
  [ perf record: Captured and wrote 0.005 MB perf.data (11 samples) ]
  $
Fixes f8e502b9d1b3b197 ("perf header: Ensure bitmaps are freed")
Cc German Gomez <[email protected]>
Cc Ian Rogers <[email protected]>
Cc James Clark <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Leo Yan <[email protected]>
Cc Namhyung Kim <[email protected]>
---
 tools/perf/util/header.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/header.c +3 -1
index d812e1e371a7..41032243774e 100644
@@ -1444,7 +1444,9 @@ static int build_mem_topology(struct memory_node **nodesp, u64 *cntp)
 			nodes = new_nodes;
 			size += 4;
 		}
-		ret = memory_node__read(&nodes[cnt++], idx);
+		ret = memory_node__read(&nodes[cnt], idx);
+		if (!ret)
+			cnt += 1;
 	}
 out:
 	closedir(dir);
Signature · 1 line
2.43.0
author maintainer
#469 lore raw

PATCH 463/583 libapi: Add missing linux/types.h header to get the __u64 type on io.h

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit af76b2dec0984a079d8497bfa37d29a9b55932e1 ]

There are functions using __u64, so we need to have the linux/types.h header otherwise we'll break when its not included before api/io.h.

Fixes e95770af4c4a280f ("tools api: Add a lightweight buffered reading api")
Cc Adrian Hunter <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
---
 tools/lib/api/io.h | 1 +
 1 file changed, 1 insertion(+)
tools/lib/api/io.h +1 -0
index 9fc429d2852d..f4a9328035bd 100644
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/types.h>
 
 struct io {
 	/* File descriptor being read/ */
Signature · 1 line
2.43.0
author maintainer
#470 lore raw

PATCH 464/583 usb: core: Allow subclassed USB drivers to override usb_choose_configuration()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Douglas Anderson <[email protected]>

[ Upstream commit a87b8e3be926af0fc3b9b1af42b1127bd1ff077c ]

For some USB devices we might want to do something different for usb_choose_configuration(). One example here is the r8152 driver where we want to end up using the vendor driver with the preferred interface.

The r8152 driver tried to make things work by implementing a USB generic_subclass driver and then overriding the normal config selection after it happened. This is less than ideal and also caused breakage if someone deauthorized and re-authorized the USB device because the USB core ended up going back to it's default logic for choosing the best config. I made an attempt to fix this [1] but it was a bit ugly.

Let's do this better and allow USB generic_subclass drivers to override usb_choose_configuration().

[1] https://lore.kernel.org/r/20231130154337.1.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid

Stable-dep-of: aa4f2b3e418e ("r8152: Choose our USB config with choose_configuration() rather than probe()")

---
 drivers/usb/core/generic.c | 7 +++++++
 include/linux/usb.h        | 6 ++++++
 2 files changed, 13 insertions(+)
drivers/usb/core/generic.c +7 -0
index 740342a2812a..dcb897158228 100644
@@ -59,10 +59,17 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
+	struct usb_device_driver *udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
 
+	if (udriver->choose_configuration) {
+		i = udriver->choose_configuration(udev);
+		if (i >= 0)
+			return i;
+	}
+
 	best = NULL;
 	c = udev->config;
 	num_configs = udev->descriptor.bNumConfigurations;
include/linux/usb.h +6 -0
index a21074861f91..bfd77ece0643 100644
@@ -1264,6 +1264,9 @@ struct usb_driver {
  *	module is being unloaded.
  * @suspend: Called when the device is going to be suspended by the system.
  * @resume: Called when the device is being resumed by the system.
+ * @choose_configuration: If non-NULL, called instead of the default
+ *	usb_choose_configuration(). If this returns an error then we'll go
+ *	on to call the normal usb_choose_configuration().
  * @dev_groups: Attributes attached to the device that will be created once it
  *	is bound to the driver.
  * @drvwrap: Driver-model core structure wrapper.
@@ -1287,6 +1290,9 @@ struct usb_device_driver {
 
 	int (*suspend) (struct usb_device *udev, pm_message_t message);
 	int (*resume) (struct usb_device *udev, pm_message_t message);
+
+	int (*choose_configuration) (struct usb_device *udev);
+
 	const struct attribute_group **dev_groups;
 	struct usbdrv_wrap drvwrap;
 	const struct usb_device_id *id_table;
Signature · 1 line
2.43.0
author maintainer
#471 lore raw

PATCH 465/583 r8152: Choose our USB config with choose_configuration() rather than probe()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Douglas Anderson <[email protected]>

[ Upstream commit aa4f2b3e418e8673e55145de8b8016a7a9920306 ]

If you deauthorize the r8152 device (by writing 0 to the "authorized" field in sysfs) and then reauthorize it (by writing a 1) then it no longer works. This is because when you do the above we lose the special configuration that we set in rtl8152_cfgselector_probe(). Deauthorizing causes the config to be set to -1 and then reauthorizing runs the default logic for choosing the best config.

I made an attempt to fix it so that the config is kept across deauthorizing / reauthorizing [1] but it was a bit ugly.

Let's instead use the new USB core feature to override choose_configuration().

This patch relies upon the patches ("usb: core: Don't force USB generic_subclass drivers to define probe()") and ("usb: core: Allow subclassed USB drivers to override usb_choose_configuration()")

[1] https://lore.kernel.org/r/20231130154337.1.Ie00e07f07f87149c9ce0b27ae4e26991d307e14b@changeid

---
 drivers/net/usb/r8152.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)
drivers/net/usb/r8152.c +5 -11
index 127b34dcc5b3..cca5b81c8b18 100644
@@ -10036,7 +10036,7 @@ static struct usb_driver rtl8152_driver = {
 	.disable_hub_initiated_lpm = 1,
 };
 
-static int rtl8152_cfgselector_probe(struct usb_device *udev)
+static int rtl8152_cfgselector_choose_configuration(struct usb_device *udev)
 {
 	struct usb_host_config *c;
 	int i, num_configs;
@@ -10063,19 +10063,13 @@ static int rtl8152_cfgselector_probe(struct usb_device *udev)
 	if (i == num_configs)
 		return -ENODEV;
 
-	if (usb_set_configuration(udev, c->desc.bConfigurationValue)) {
-		dev_err(&udev->dev, "Failed to set configuration %d\n",
-			c->desc.bConfigurationValue);
-		return -ENODEV;
-	}
-
-	return 0;
+	return c->desc.bConfigurationValue;
 }
 
 static struct usb_device_driver rtl8152_cfgselector_driver = {
-	.name =		MODULENAME "-cfgselector",
-	.probe =	rtl8152_cfgselector_probe,
-	.id_table =	rtl8152_table,
+	.name =	MODULENAME "-cfgselector",
+	.choose_configuration = rtl8152_cfgselector_choose_configuration,
+	.id_table = rtl8152_table,
 	.generic_subclass = 1,
 	.supports_autosuspend = 1,
 };
Signature · 1 line
2.43.0
author maintainer
#472 lore raw

PATCH 466/583 perf test record user-regs: Fix mask for vg register

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Veronika Molnarova <[email protected]>

[ Upstream commit 28b01743ca752cea5ab182297d8b912b22f2a2d1 ]

The 'vg' register for arm64 shows up in --user_regs as available when masking the variable AT_HWCAP with 1 << 22 returns '1' as done in perf_regs.c.

However, in subtests for support of SVE, the check for the 'vg' register is done by masking the variable AT_HWCAP with the value 0x200000 which is equals to 1 << 21 instead of 1 << 22.

This results in inconsistencies on certain systems where the test expects that the 'vg' register is not operational when it is, and vice-versa.

During the testing on a machine that the test expected not to have the 'vg' register available, 'perf record' with the option --user-regs showed records for the 'vg' register together with all of the others, which means that the mask for the subtest of perf_event_attr is off by one.

Change the value of the mask from 0x200000 to 0x400000 to correct it.

Fixes 9440ebdc333dd12e ("perf test arm64: Add attr tests for new VG register")
Cc James Clark <[email protected]>
Cc Michael Petlan <[email protected]>
---
 tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 | 2 +-
 tools/perf/tests/attr/test-record-user-regs-sve-aarch64    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
tools/perf/tests/attr/test-record-user-regs-no-sve-aarch64 +1 -1
index fbb065842880..bed765450ca9 100644
@@ -6,4 +6,4 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 129
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0
tools/perf/tests/attr/test-record-user-regs-sve-aarch64 +1 -1
index c598c803221d..a65113cd7311 100644
@@ -6,7 +6,7 @@ args    = --no-bpf-event --user-regs=vg kill >/dev/null 2>&1
 ret     = 1
 test_ret = true
 arch    = aarch64
-auxv    = auxv["AT_HWCAP"] & 0x200000 == 0x200000
+auxv    = auxv["AT_HWCAP"] & 0x400000 == 0x400000
 kernel_since = 6.1
 
 [event:base-record]
Signature · 1 line
2.43.0
author maintainer
#473 lore raw

PATCH 467/583 vfio/pds: Fix calculations in pds_vfio_dirty_sync

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Brett Creeley <[email protected]>

[ Upstream commit 4004497cec3093d7b0087bc70709b45969fa07b6 ]

The incorrect check is being done for comparing the iova/length being requested to sync. This can cause the dirty sync operation to fail. Fix this by making sure the iova offset added to the requested sync length doesn't exceed the region_size.

Also, the region_start is assumed to always be at 0. This can cause dirty tracking to fail because the device/driver bitmap offset always starts at 0, however, the region_start/iova may not. Fix this by determining the iova offset from region_start to determine the bitmap offset.

Fixes f232836a9152 ("vfio/pds: Add support for dirty page tracking")
---
 drivers/vfio/pci/pds/dirty.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/vfio/pci/pds/dirty.c +3 -3
index c937aa6f3954..27607d7b9030 100644
@@ -478,8 +478,7 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		pds_vfio->vf_id, iova, length, pds_vfio->dirty.region_page_size,
 		pages, bitmap_size);
 
-	if (!length || ((dirty->region_start + iova + length) >
-			(dirty->region_start + dirty->region_size))) {
+	if (!length || ((iova - dirty->region_start + length) > dirty->region_size)) {
 		dev_err(dev, "Invalid iova 0x%lx and/or length 0x%lx to sync\n",
 			iova, length);
 		return -EINVAL;
@@ -496,7 +495,8 @@ static int pds_vfio_dirty_sync(struct pds_vfio_pci_device *pds_vfio,
 		return -EINVAL;
 	}
 
-	bmp_offset = DIV_ROUND_UP(iova / dirty->region_page_size, sizeof(u64));
+	bmp_offset = DIV_ROUND_UP((iova - dirty->region_start) /
+				  dirty->region_page_size, sizeof(u64));
 
 	dev_dbg(dev,
 		"Syncing dirty bitmap, iova 0x%lx length 0x%lx, bmp_offset %llu bmp_bytes %llu\n",
Signature · 1 line
2.43.0
author maintainer
#474 lore raw

PATCH 468/583 perf vendor events arm64 AmpereOne: Rename BPU_FLUSH_MEM_FAULT to GPC_FLUSH_MEM_FAULT

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ilkka Koskinen <[email protected]>

[ Upstream commit 10a149e4b4a9187940adbfff0f216ccb5a15aa41 ]

The documentation wrongly called the event as BPU_FLUSH_MEM_FAULT and now has been fixed. Correct the name in the perf tool as well.

Fixes a9650b7f6fc09d16 ("perf vendor events arm64: Add AmpereOne core PMU events")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ilkka Koskinen <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc James Clark <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc John Garry <[email protected]>
Cc Leo Yan <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mike Leach <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Will Deacon <[email protected]>
---
 .../pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/pmu-events/arch/arm64/ampere/ampereone/core-imp-def.json +1 -1
index 88b23b85e33c..879ff21e0b17 100644
@@ -110,7 +110,7 @@
     {
         "PublicDescription": "Flushes due to memory hazards",
         "EventCode": "0x121",
-        "EventName": "BPU_FLUSH_MEM_FAULT",
+        "EventName": "GPC_FLUSH_MEM_FAULT",
         "BriefDescription": "Flushes due to memory hazards"
     },
     {
Signature · 1 line
2.43.0
author maintainer
#475 lore raw

PATCH 469/583 perf mem: Fix error on hybrid related to availability of mem event in a PMU

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kan Liang <[email protected]>

[ Upstream commit a4320085a6c694326dd8db46f563d52d1a826f07 ]

The below error can be triggered on a hybrid machine.

 $ perf mem record -t load sleep 1
 event syntax error: 'breakpoint/mem-loads,ldlat=30/P'
                                \___ Bad event or PMU

Unable to find PMU or event on a PMU of 'breakpoint'

In the perf_mem_events__record_args(), the current perf never checks the availability of a mem event on a given PMU. All the PMUs will be added to the perf mem event list. Perf errors out for the unsupported PMU.

Extend perf_mem_event__supported() and take a PMU into account. Check the mem event for each PMU before adding it to the perf mem event list.

Optimize the perf_mem_events__init() a little bit. The function is to check whether the mem events are supported in the system. It doesn't need to scan all PMUs. Just return with the first supported PMU is good enough.

Fixes 5752c20f3787c9bc ("perf mem: Scan all PMUs instead of just core ones")
Cc Adrian Hunter <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ravi Bangoria <[email protected]>
---
 tools/perf/util/mem-events.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)
tools/perf/util/mem-events.c +14 -11
index 954b235e12e5..3a2e3687878c 100644
@@ -100,11 +100,14 @@ int perf_mem_events__parse(const char *str)
 	return -1;
 }
 
-static bool perf_mem_event__supported(const char *mnt, char *sysfs_name)
+static bool perf_mem_event__supported(const char *mnt, struct perf_pmu *pmu,
+				      struct perf_mem_event *e)
 {
+	char sysfs_name[100];
 	char path[PATH_MAX];
 	struct stat st;
 
+	scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
 	scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, sysfs_name);
 	return !stat(path, &st);
 }
@@ -120,7 +123,6 @@ int perf_mem_events__init(void)
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		struct perf_mem_event *e = perf_mem_events__ptr(j);
-		char sysfs_name[100];
 		struct perf_pmu *pmu = NULL;
 
 		/*
@@ -136,12 +138,12 @@ int perf_mem_events__init(void)
 		 * of core PMU.
 		 */
 		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name, pmu->name);
-			e->supported |= perf_mem_event__supported(mnt, sysfs_name);
+			e->supported |= perf_mem_event__supported(mnt, pmu, e);
+			if (e->supported) {
+				found = true;
+				break;
+			}
 		}
-
-		if (e->supported)
-			found = true;
 	}
 
 	return found ? 0 : -ENOENT;
@@ -167,13 +169,10 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 						    int idx)
 {
 	const char *mnt = sysfs__mount();
-	char sysfs_name[100];
 	struct perf_pmu *pmu = NULL;
 
 	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-		scnprintf(sysfs_name, sizeof(sysfs_name), e->sysfs_name,
-			  pmu->name);
-		if (!perf_mem_event__supported(mnt, sysfs_name)) {
+		if (!perf_mem_event__supported(mnt, pmu, e)) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(idx, pmu->name));
 		}
@@ -183,6 +182,7 @@ static void perf_mem_events__print_unsupport_hybrid(struct perf_mem_event *e,
 int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 				 char **rec_tmp, int *tmp_nr)
 {
+	const char *mnt = sysfs__mount();
 	int i = *argv_nr, k = 0;
 	struct perf_mem_event *e;
 
@@ -211,6 +211,9 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 			while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 				const char *s = perf_mem_events__name(j, pmu->name);
 
+				if (!perf_mem_event__supported(mnt, pmu, e))
+					continue;
+
 				rec_argv[i++] = "-e";
 				if (s) {
 					char *copy = strdup(s);
Signature · 1 line
2.43.0
author maintainer
#476 lore raw

PATCH 470/583 perf stat: Exit perf stat if parse groups fails

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 0713ab3bd169da82c35eefd012b07b715e4ebcf7 ]

Metrics were added by a callback but commit a4b8cfcabb1d90ec ("perf
stat: Delay metric parsing") postponed this to allow optimizations based on the CPU configuration.

In doing so it stopped errors in metric parsing from causing 'perf stat' termination.

This change adds the termination for bad metric names back in.

---
 tools/perf/builtin-stat.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)
tools/perf/builtin-stat.c +11 -7
index a3af805a1d57..78c104922181 100644
@@ -2695,15 +2695,19 @@ int cmd_stat(int argc, const char **argv)
 	 */
 	if (metrics) {
 		const char *pmu = parse_events_option_args.pmu_filter ?: "all";
+		int ret = metricgroup__parse_groups(evsel_list, pmu, metrics,
+						stat_config.metric_no_group,
+						stat_config.metric_no_merge,
+						stat_config.metric_no_threshold,
+						stat_config.user_requested_cpu_list,
+						stat_config.system_wide,
+						&stat_config.metric_events);
 
-		metricgroup__parse_groups(evsel_list, pmu, metrics,
-					stat_config.metric_no_group,
-					stat_config.metric_no_merge,
-					stat_config.metric_no_threshold,
-					stat_config.user_requested_cpu_list,
-					stat_config.system_wide,
-					&stat_config.metric_events);
 		zfree(&metrics);
+		if (ret) {
+			status = ret;
+			goto out;
+		}
 	}
 
 	if (add_default_attributes())
Signature · 1 line
2.43.0
author maintainer
#477 lore raw

PATCH 471/583 base/node.c: initialize the accessor list before registering

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gregory Price <[email protected]>

[ Upstream commit 48b5928e18dc27e05cab3dc4c78cd8a15baaf1e5 ]

The current code registers the node as available in the node array before initializing the accessor list. This makes it so that anything which might access the accessor list as a result of allocations will cause an undefined memory access.

In one example, an extension to access hmat data during interleave caused this undefined access as a result of a bulk allocation that occurs during node initialization but before the accessor list is initialized.

Initialize the accessor list before making the node generally available to the global system.

Fixes 08d9dbe72b1f ("node: Link memory nodes to their compute nodes")
---
 drivers/base/node.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/base/node.c +6 -3
index 493d533f8375..4d588f4658c8 100644
@@ -868,11 +868,15 @@ int __register_one_node(int nid)
 {
 	int error;
 	int cpu;
+	struct node *node;
 
-	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
-	if (!node_devices[nid])
+	node = kzalloc(sizeof(struct node), GFP_KERNEL);
+	if (!node)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&node->access_list);
+	node_devices[nid] = node;
+
 	error = register_node(node_devices[nid], nid);
 
 	/* link cpu under this node */
@@ -881,7 +885,6 @@ int __register_one_node(int nid)
 			register_cpu_under_node(cpu, nid);
 	}
 
-	INIT_LIST_HEAD(&node_devices[nid]->access_list);
 	node_init_caches(nid);
 
 	return error;
Signature · 1 line
2.43.0
author maintainer
#478 lore raw

PATCH 472/583 acpi: property: Let args be NULL in __acpi_node_get_property_reference

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sakari Ailus <[email protected]>

[ Upstream commit bef52aa0f3de1b7d8c258c13b16e577361dabf3a ]

fwnode_get_property_reference_args() may not be called with args argument NULL on ACPI, OF already supports this. Add the missing NULL checks and document this.

The purpose is to be able to count the references.

Fixes 977d5ad39f3e ("ACPI: Convert ACPI reference args to generic fwnode reference args")
---
 drivers/acpi/property.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/acpi/property.c +4 -0
index 99b4e3355435..4d958a165da0 100644
@@ -851,6 +851,7 @@ static int acpi_get_ref_args(struct fwnode_reference_args *args,
  * @index: Index of the reference to return
  * @num_args: Maximum number of arguments after each reference
  * @args: Location to store the returned reference with optional arguments
+ *	  (may be NULL)
  *
  * Find property with @name, verifify that it is a package containing at least
  * one object reference and if so, store the ACPI device object pointer to the
@@ -907,6 +908,9 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (!device)
 			return -EINVAL;
 
+		if (!args)
+			return 0;
+
 		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 		return 0;
Signature · 1 line
2.43.0
author maintainer
#479 lore raw

PATCH 473/583 software node: Let args be NULL in software_node_get_reference_args

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sakari Ailus <[email protected]>

[ Upstream commit 1eaea4b3604eb9ca7d9a1e73d88fc121bb4061f5 ]

fwnode_get_property_reference_args() may not be called with args argument NULL and while OF already supports this. Add the missing NULL check.

The purpose is to be able to count the references.

---
 drivers/base/swnode.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/base/swnode.c +3 -0
index 1886995a0b3a..079bd14bdedc 100644
@@ -541,6 +541,9 @@ software_node_get_reference_args(const struct fwnode_handle *fwnode,
 	if (nargs > NR_FWNODE_REFERENCE_ARGS)
 		return -EINVAL;
 
+	if (!args)
+		return 0;
+
 	args->fwnode = software_node_get(refnode);
 	args->nargs = nargs;
 
Signature · 1 line
2.43.0
author maintainer
#480 lore raw

PATCH 474/583 serial: imx: fix tx statemachine deadlock

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paul Geurts <[email protected]>

[ Upstream commit 78d60dae9a0c9f09aa3d6477c94047df2fe6f7b0 ]

When using the serial port as RS485 port, the tx statemachine is used to control the RTS pin to drive the RS485 transceiver TX_EN pin. When the TTY port is closed in the middle of a transmission (for instance during userland application crash), imx_uart_shutdown disables the interface and disables the Transmission Complete interrupt. afer that, imx_uart_stop_tx bails on an incomplete transmission, to be retriggered by the TC interrupt. This interrupt is disabled and therefore the tx statemachine never transitions out of SEND. The statemachine is in deadlock now, and the TX_EN remains low, making the interface useless.

imx_uart_stop_tx now checks for incomplete transmission AND whether TC interrupts are enabled before bailing to be retriggered. This makes sure the state machine handling is reached, and is properly set to WAIT_AFTER_SEND.

---
 drivers/tty/serial/imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/tty/serial/imx.c +2 -2
index 2e85c77e7c0d..c084ac3bb441 100644
@@ -421,13 +421,13 @@ static void imx_uart_stop_tx(struct uart_port *port)
 	ucr1 = imx_uart_readl(sport, UCR1);
 	imx_uart_writel(sport, ucr1 & ~UCR1_TRDYEN, UCR1);
 
+	ucr4 = imx_uart_readl(sport, UCR4);
 	usr2 = imx_uart_readl(sport, USR2);
-	if (!(usr2 & USR2_TXDC)) {
+	if ((!(usr2 & USR2_TXDC)) && (ucr4 & UCR4_TCEN)) {
 		/* The shifter is still busy, so retry once TC triggers */
 		return;
 	}
 
-	ucr4 = imx_uart_readl(sport, UCR4);
 	ucr4 &= ~UCR4_TCEN;
 	imx_uart_writel(sport, ucr4, UCR4);
 
Signature · 1 line
2.43.0
author maintainer
#481 lore raw

PATCH 475/583 selftests/sgx: Fix uninitialized pointer dereference in error path

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jo Van Bulck <[email protected]>

[ Upstream commit 79eba8c924f7decfa71ddf187d38cb9f5f2cd7b3 ]

Ensure ctx is zero-initialized, such that the encl_measure function will not call EVP_MD_CTX_destroy with an uninitialized ctx pointer in case of an early error during key generation.

---
 tools/testing/selftests/sgx/sigstruct.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
tools/testing/selftests/sgx/sigstruct.c +3 -2
index a07896a46364..d73b29becf5b 100644
@@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl)
 	struct sgx_sigstruct *sigstruct = &encl->sigstruct;
 	struct sgx_sigstruct_payload payload;
 	uint8_t digest[SHA256_DIGEST_LENGTH];
+	EVP_MD_CTX *ctx = NULL;
 	unsigned int siglen;
 	RSA *key = NULL;
-	EVP_MD_CTX *ctx;
 	int i;
 
 	memset(sigstruct, 0, sizeof(*sigstruct));
@@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl)
 	return true;
 
 err:
-	EVP_MD_CTX_destroy(ctx);
+	if (ctx)
+		EVP_MD_CTX_destroy(ctx);
 	RSA_free(key);
 	return false;
 }
Signature · 1 line
2.43.0
author maintainer
#482 lore raw

PATCH 476/583 selftests/sgx: Fix uninitialized pointer dereferences in encl_get_entry

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jo Van Bulck <[email protected]>

[ Upstream commit b84fc2e0139ba4b23b8039bd7cfd242894fe8f8b ]

Ensure sym_tab and sym_names are zero-initialized and add an early-out condition in the unlikely (erroneous) case that the enclave ELF file would not contain a symbol table.

This addresses -Werror=maybe-uninitialized compiler warnings for gcc -O2.

---
 tools/testing/selftests/sgx/load.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
tools/testing/selftests/sgx/load.c +6 -3
index 94bdeac1cf04..c9f658e44de6 100644
@@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
  */
 uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 {
+	Elf64_Sym *symtab = NULL;
+	char *sym_names = NULL;
 	Elf64_Shdr *sections;
-	Elf64_Sym *symtab;
 	Elf64_Ehdr *ehdr;
-	char *sym_names;
-	int num_sym;
+	int num_sym = 0;
 	int i;
 
 	ehdr = encl->bin;
@@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol)
 		}
 	}
 
+	if (!symtab || !sym_names)
+		return 0;
+
 	for (i = 0; i < num_sym; i++) {
 		Elf64_Sym *sym = &symtab[i];
 
Signature · 1 line
2.43.0
author maintainer
#483 lore raw

PATCH 477/583 selftests/sgx: Include memory clobber for inline asm in test enclave

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jo Van Bulck <[email protected]>

[ Upstream commit 853a57a43ebdb8c024160c1a0990bae85f4bcc2f ]

Add the "memory" clobber to the EMODPE and EACCEPT asm blocks to tell the compiler the assembly code accesses to the secinfo struct. This ensures the compiler treats the asm block as a memory barrier and the write to secinfo will be visible to ENCLU.

---
 tools/testing/selftests/sgx/test_encl.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
tools/testing/selftests/sgx/test_encl.c +5 -3
index c0d6397295e3..ae791df3e5a5 100644
@@ -24,10 +24,11 @@ static void do_encl_emodpe(void *_op)
 	secinfo.flags = op->flags;
 
 	asm volatile(".byte 0x0f, 0x01, 0xd7"
-				:
+				: /* no outputs */
 				: "a" (EMODPE),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 }
 
 static void do_encl_eaccept(void *_op)
@@ -42,7 +43,8 @@ static void do_encl_eaccept(void *_op)
 				: "=a" (rax)
 				: "a" (EACCEPT),
 				  "b" (&secinfo),
-				  "c" (op->epc_addr));
+				  "c" (op->epc_addr)
+				: "memory" /* read from secinfo pointer */);
 
 	op->ret = rax;
 }
Signature · 1 line
2.43.0
author maintainer
#484 lore raw

PATCH 478/583 selftests/sgx: Skip non X86_64 platform

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zhao Mengmeng <[email protected]>

[ Upstream commit 981cf568a8644161c2f15c02278ebc2834b51ba6 ]

When building whole selftests on arm64, rsync gives an erorr about sgx:

rsync: [sender] link_stat "/root/linux-next/tools/testing/selftests/sgx/test_encl.elf" failed: No such file or directory (2) rsync error: some files/attrs were not transferred (see previous errors) (code 23) at main.c(1327) [sender=3.2.5]

The root casue is sgx only used on X86_64, and shall be skipped on other platforms.

Fix this by moving TEST_CUSTOM_PROGS and TEST_FILES inside the if check, then the build result will be "Skipping non-existent dir: sgx".

---
 tools/testing/selftests/sgx/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/sgx/Makefile +1 -1
index 50aab6b57da3..01abe4969b0f 100644
@@ -16,10 +16,10 @@ HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack
 ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
 	       -fno-stack-protector -mrdrnd $(INCLUDES)
 
+ifeq ($(CAN_BUILD_X86_64), 1)
 TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx
 TEST_FILES := $(OUTPUT)/test_encl.elf
 
-ifeq ($(CAN_BUILD_X86_64), 1)
 all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf
 endif
 
Signature · 1 line
2.43.0
author maintainer
#485 lore raw

PATCH 479/583 iio: adc: ad9467: fix reset gpio handling

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nuno Sa <[email protected]>

[ Upstream commit 76f028539cf360f750efd8cde560edda298e4c6b ]

The reset gpio was being handled with inverted polarity. This means that as far as gpiolib is concerned we were actually leaving the pin asserted (in theory, this would mean reset). However, inverting the polarity in devicetree made things work. Fix it by doing it the proper way and how gpiolib expects it to be done.

While at it, moved the handling to it's own function and dropped 'reset_gpio' from the 'struct ad9467_state' as we only need it during probe. On top of that, refactored things so that we now request the gpio asserted (i.e in reset) and then de-assert it. Also note that we now use gpiod_set_value_cansleep() instead of gpiod_direction_output() as we already request the pin as output.

Fixes ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
---
 drivers/iio/adc/ad9467.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)
drivers/iio/adc/ad9467.c +18 -13
index 39eccc28debe..4fb9e48dc782 100644
@@ -121,7 +121,6 @@ struct ad9467_state {
 	unsigned int			output_mode;
 
 	struct gpio_desc		*pwrdown_gpio;
-	struct gpio_desc		*reset_gpio;
 };
 
 static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
@@ -378,6 +377,21 @@ static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 	return ad9467_outputmode_set(st->spi, st->output_mode);
 }
 
+static int ad9467_reset(struct device *dev)
+{
+	struct gpio_desc *gpio;
+
+	gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR_OR_NULL(gpio))
+		return PTR_ERR_OR_ZERO(gpio);
+
+	fsleep(1);
+	gpiod_set_value_cansleep(gpio, 0);
+	fsleep(10 * USEC_PER_MSEC);
+
+	return 0;
+}
+
 static int ad9467_probe(struct spi_device *spi)
 {
 	const struct ad9467_chip_info *info;
@@ -408,18 +422,9 @@ static int ad9467_probe(struct spi_device *spi)
 	if (IS_ERR(st->pwrdown_gpio))
 		return PTR_ERR(st->pwrdown_gpio);
 
-	st->reset_gpio = devm_gpiod_get_optional(&spi->dev, "reset",
-						 GPIOD_OUT_LOW);
-	if (IS_ERR(st->reset_gpio))
-		return PTR_ERR(st->reset_gpio);
-
-	if (st->reset_gpio) {
-		udelay(1);
-		ret = gpiod_direction_output(st->reset_gpio, 1);
-		if (ret)
-			return ret;
-		mdelay(10);
-	}
+	ret = ad9467_reset(&spi->dev);
+	if (ret)
+		return ret;
 
 	conv->chip_info = &info->axi_adc_info;
 
Signature · 1 line
2.43.0
author maintainer
#486 lore raw

PATCH 480/583 iio: adc: ad9467: dont ignore error codes

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nuno Sa <[email protected]>

[ Upstream commit e072e149cfb827e0ab4cafb0547e9658e35393cd ]

Make sure functions that return errors are not ignored.

Fixes ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
---
 drivers/iio/adc/ad9467.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)
drivers/iio/adc/ad9467.c +17 -10
index 4fb9e48dc782..d3c98c4eccd3 100644
@@ -162,9 +162,10 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 
 	if (readval == NULL) {
 		ret = ad9467_spi_write(spi, reg, writeval);
-		ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return ret;
+		if (ret)
+			return ret;
+		return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	ret = ad9467_spi_read(spi, reg);
@@ -272,10 +273,13 @@ static int ad9467_get_scale(struct adi_axi_adc_conv *conv, int *val, int *val2)
 	const struct ad9467_chip_info *info1 = to_ad9467_chip_info(info);
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int i, vref_val;
+	int ret;
 
-	vref_val = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	ret = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
+	if (ret < 0)
+		return ret;
 
-	vref_val &= info1->vref_mask;
+	vref_val = ret & info1->vref_mask;
 
 	for (i = 0; i < info->num_scales; i++) {
 		if (vref_val == info->scale_table[i][1])
@@ -296,6 +300,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
 	unsigned int scale_val[2];
 	unsigned int i;
+	int ret;
 
 	if (val != 0)
 		return -EINVAL;
@@ -305,11 +310,13 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 		if (scale_val[0] != val || scale_val[1] != val2)
 			continue;
 
-		ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
-				 info->scale_table[i][1]);
-		ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
-				 AN877_ADC_TRANSFER_SYNC);
-		return 0;
+		ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
+				       info->scale_table[i][1]);
+		if (ret < 0)
+			return ret;
+
+		return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
+					AN877_ADC_TRANSFER_SYNC);
 	}
 
 	return -EINVAL;
Signature · 1 line
2.43.0
author maintainer
#487 lore raw

PATCH 481/583 iio: adc: ad9467: add mutex to struct ad9467_state

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nuno Sa <[email protected]>

[ Upstream commit 737720197be445bb9eec2986101e4a386e019337 ]

When calling ad9467_set_scale(), multiple calls to ad9467_spi_write() are done which means we need to properly protect the whole operation so we are sure we will be in a sane state if two concurrent calls occur.

Fixes ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
---
 drivers/iio/adc/ad9467.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/iio/adc/ad9467.c +6 -1
index d3c98c4eccd3..104c6d394a3e 100644
@@ -4,8 +4,9 @@
  *
  * Copyright 2012-2020 Analog Devices Inc.
  */
-
+#include <linux/cleanup.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -121,6 +122,8 @@ struct ad9467_state {
 	unsigned int			output_mode;
 
 	struct gpio_desc		*pwrdown_gpio;
+	/* ensure consistent state obtained on multiple related accesses */
+	struct mutex			lock;
 };
 
 static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
@@ -161,6 +164,7 @@ static int ad9467_reg_access(struct adi_axi_adc_conv *conv, unsigned int reg,
 	int ret;
 
 	if (readval == NULL) {
+		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(spi, reg, writeval);
 		if (ret)
 			return ret;
@@ -310,6 +314,7 @@ static int ad9467_set_scale(struct adi_axi_adc_conv *conv, int val, int val2)
 		if (scale_val[0] != val || scale_val[1] != val2)
 			continue;
 
+		guard(mutex)(&st->lock);
 		ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
 				       info->scale_table[i][1]);
 		if (ret < 0)
Signature · 1 line
2.43.0
author maintainer
#488 lore raw

PATCH 482/583 iio: adc: ad9467: fix scale setting

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nuno Sa <[email protected]>

[ Upstream commit b73f08bb7fe5a0901646ca5ceaa1e7a2d5ee6293 ]

When reading in_voltage_scale we can get something like:

root@analog:/sys/bus/iio/devices/iio:device2# cat in_voltage_scale
0.038146

However, when reading the available options:

root@analog:/sys/bus/iio/devices/iio:device2# cat
in_voltage_scale_available
2000.000000 2100.000006 2200.000007 2300.000008 2400.000009 2500.000010

which does not make sense. Moreover, when trying to set a new scale we get an error because there's no call to __ad9467_get_scale() to give us values as given when reading in_voltage_scale. Fix it by computing the available scales during probe and properly pass the list when .read_available() is called.

While at it, change to use .read_available() from iio_info. Also note that to properly fix this, adi-axi-adc.c has to be changed accordingly.

Fixes ad6797120238 ("iio: adc: ad9467: add support AD9467 ADC")
---
 drivers/iio/adc/ad9467.c            | 47 ++++++++++++++++++
 drivers/iio/adc/adi-axi-adc.c       | 74 ++++++-----------------------
 include/linux/iio/adc/adi-axi-adc.h |  4 ++
 3 files changed, 66 insertions(+), 59 deletions(-)
drivers/iio/adc/ad9467.c +47 -0
index 104c6d394a3e..f668313730cb 100644
@@ -120,6 +120,7 @@ struct ad9467_state {
 	struct spi_device		*spi;
 	struct clk			*clk;
 	unsigned int			output_mode;
+	unsigned int                    (*scales)[2];
 
 	struct gpio_desc		*pwrdown_gpio;
 	/* ensure consistent state obtained on multiple related accesses */
@@ -216,6 +217,7 @@ static void __ad9467_get_scale(struct adi_axi_adc_conv *conv, int index,
 	.channel = _chan,						\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) |		\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ),				\
+	.info_mask_shared_by_type_available = BIT(IIO_CHAN_INFO_SCALE), \
 	.scan_index = _si,						\
 	.scan_type = {							\
 		.sign = _sign,						\
@@ -370,6 +372,26 @@ static int ad9467_write_raw(struct adi_axi_adc_conv *conv,
 	}
 }
 
+static int ad9467_read_avail(struct adi_axi_adc_conv *conv,
+			     struct iio_chan_spec const *chan,
+			     const int **vals, int *type, int *length,
+			     long mask)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		*vals = (const int *)st->scales;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		/* Values are stored in a 2D matrix */
+		*length = info->num_scales * 2;
+		return IIO_AVAIL_LIST;
+	default:
+		return -EINVAL;
+	}
+}
+
 static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 {
 	int ret;
@@ -382,6 +404,26 @@ static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
 				AN877_ADC_TRANSFER_SYNC);
 }
 
+static int ad9467_scale_fill(struct adi_axi_adc_conv *conv)
+{
+	const struct adi_axi_adc_chip_info *info = conv->chip_info;
+	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
+	unsigned int i, val1, val2;
+
+	st->scales = devm_kmalloc_array(&st->spi->dev, info->num_scales,
+					sizeof(*st->scales), GFP_KERNEL);
+	if (!st->scales)
+		return -ENOMEM;
+
+	for (i = 0; i < info->num_scales; i++) {
+		__ad9467_get_scale(conv, i, &val1, &val2);
+		st->scales[i][0] = val1;
+		st->scales[i][1] = val2;
+	}
+
+	return 0;
+}
+
 static int ad9467_preenable_setup(struct adi_axi_adc_conv *conv)
 {
 	struct ad9467_state *st = adi_axi_adc_conv_priv(conv);
@@ -440,6 +482,10 @@ static int ad9467_probe(struct spi_device *spi)
 
 	conv->chip_info = &info->axi_adc_info;
 
+	ret = ad9467_scale_fill(conv);
+	if (ret)
+		return ret;
+
 	id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID);
 	if (id != conv->chip_info->id) {
 		dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n",
@@ -450,6 +496,7 @@ static int ad9467_probe(struct spi_device *spi)
 	conv->reg_access = ad9467_reg_access;
 	conv->write_raw = ad9467_write_raw;
 	conv->read_raw = ad9467_read_raw;
+	conv->read_avail = ad9467_read_avail;
 	conv->preenable_setup = ad9467_preenable_setup;
 
 	st->output_mode = info->default_output_mode |
drivers/iio/adc/adi-axi-adc.c +15 -59

90 lines not on this page · raw message

include/linux/iio/adc/adi-axi-adc.h +4 -0
index 52620e5b8052..b7904992d561 100644
@@ -41,6 +41,7 @@ struct adi_axi_adc_chip_info {
  * @reg_access		IIO debugfs_reg_access hook for the client ADC
  * @read_raw		IIO read_raw hook for the client ADC
  * @write_raw		IIO write_raw hook for the client ADC
+ * @read_avail		IIO read_avail hook for the client ADC
  */
 struct adi_axi_adc_conv {
 	const struct adi_axi_adc_chip_info		*chip_info;
@@ -54,6 +55,9 @@ struct adi_axi_adc_conv {
 	int (*write_raw)(struct adi_axi_adc_conv *conv,
 			 struct iio_chan_spec const *chan,
 			 int val, int val2, long mask);
+	int (*read_avail)(struct adi_axi_adc_conv *conv,
+			  struct iio_chan_spec const *chan,
+			  const int **val, int *type, int *length, long mask);
 };
 
 struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
Signature · 1 line
2.43.0
author maintainer
#489 lore raw

PATCH 483/583 perf header: Fix one memory leakage in perf_event__fprintf_event_update()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yicong Yang <[email protected]>

[ Upstream commit 813900d19b923fc1b241c1ce292472f68066092b ]

When dump the raw trace by perf report -D ASan reports a memory leakage in perf_event__fprintf_event_update().

It shows that we allocated a temporary cpumap for dumping the CPUs but doesn't release it and it's not used elsewhere. Fix this by free the cpumap after the dumping.

Fixes c853f9394b7bc189 ("perf tools: Add perf_event__fprintf_event_update function")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Jonathan Cameron <[email protected]>
Cc Junhao He <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/header.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
tools/perf/util/header.c +3 -2
index 41032243774e..f6035c219b41 100644
@@ -4363,9 +4363,10 @@ size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
 		ret += fprintf(fp, "... ");
 
 		map = cpu_map__new_data(&ev->cpus.cpus);
-		if (map)
+		if (map) {
 			ret += cpu_map__fprintf(map, fp);
-		else
+			perf_cpu_map__put(map);
+		} else
 			ret += fprintf(fp, "failed to get cpus\n");
 		break;
 	default:
Signature · 1 line
2.43.0
author maintainer
#490 lore raw

PATCH 484/583 perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yicong Yang <[email protected]>

[ Upstream commit 1bc479d665bc25a9a4e8168d5b400a47491511f9 ]

ASan complains a memory leakage in hisi_ptt_process_auxtrace_event() that the data buffer is not freed. Since currently we only support the raw dump trace mode, the data buffer is used only within this function. So fix this by freeing the data buffer before going out.

Fixes 5e91e57e68090c0e ("perf auxtrace arm64: Add support for parsing HiSilicon PCIe Trace packet")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Jonathan Cameron <[email protected]>
Cc Junhao He <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Qi Liu <[email protected]>
---
 tools/perf/util/hisi-ptt.c | 1 +
 1 file changed, 1 insertion(+)
tools/perf/util/hisi-ptt.c +1 -0
index 45b614bb73bf..764d660d30e2 100644
@@ -121,6 +121,7 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session,
 	if (dump_trace)
 		hisi_ptt_dump_event(ptt, data, size);
 
+	free(data);
 	return 0;
 }
 
Signature · 1 line
2.43.0
author maintainer
#491 lore raw

PATCH 485/583 perf genelf: Set ELF program header addresses properly

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit 1af478903fc48c1409a8dd6b698383b62387adf1 ]

The text section starts after the ELF headers so PHDR.p_vaddr and others should have the correct addresses.

Fixes babd04386b1df8c3 ("perf jit: Include program header in ELF files")
Cc Adrian Hunter <[email protected]>
Cc Fangrui Song <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Lieven Hey <[email protected]>
Cc Milian Wolff <[email protected]>
Cc Pablo Galindo <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/genelf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
tools/perf/util/genelf.c +3 -3
index fefc72066c4e..ac17a3cb59dc 100644
@@ -293,9 +293,9 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
 	 */
 	phdr = elf_newphdr(e, 1);
 	phdr[0].p_type = PT_LOAD;
-	phdr[0].p_offset = 0;
-	phdr[0].p_vaddr = 0;
-	phdr[0].p_paddr = 0;
+	phdr[0].p_offset = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_vaddr = GEN_ELF_TEXT_OFFSET;
+	phdr[0].p_paddr = GEN_ELF_TEXT_OFFSET;
 	phdr[0].p_filesz = csize;
 	phdr[0].p_memsz = csize;
 	phdr[0].p_flags = PF_X | PF_R;
Signature · 1 line
2.43.0
author maintainer
#492 lore raw

PATCH 486/583 perf unwind-libdw: Handle JIT-generated DSOs properly

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit c966d23a351a33f8a977fd7efbb6f467132f7383 ]

Usually DSOs are mapped from the beginning of the file, so the base address of the DSO can be calculated by map->start - map->pgoff.

However, JIT DSOs which are generated by perf inject -j, are mapped only the code segment. This makes unwind-libdw code confusing and rejects processing unwinds in the JIT DSOs. It should use the map start address as base for them to fix the confusion.

Fixes 1fe627da30331024 ("perf unwind: Take pgoff into account when reporting elf to libdwfl")
Cc Adrian Hunter <[email protected]>
Cc Fangrui Song <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Milian Wolff <[email protected]>
Cc Pablo Galindo <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/unwind-libdw.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)
tools/perf/util/unwind-libdw.c +17 -4
index 8554db3fc0d7..6013335a8dae 100644
@@ -46,6 +46,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
+	Dwarf_Addr base;
 	/*
 	 * Some callers will use al->sym, so we can't just use the
 	 * cheaper thread__find_map() here.
@@ -58,13 +59,25 @@ static int __report_module(struct addr_location *al, u64 ip,
 	if (!dso)
 		return 0;
 
+	/*
+	 * The generated JIT DSO files only map the code segment without
+	 * ELF headers.  Since JIT codes used to be packed in a memory
+	 * segment, calculating the base address using pgoff falls into
+	 * a different code in another DSO.  So just use the map->start
+	 * directly to pick the correct one.
+	 */
+	if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
+		base = map__start(al->map);
+	else
+		base = map__start(al->map) - map__pgoff(al->map);
+
 	mod = dwfl_addrmodule(ui->dwfl, ip);
 	if (mod) {
 		Dwarf_Addr s;
 
 		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-		if (s != map__start(al->map) - map__pgoff(al->map))
-			mod = 0;
+		if (s != base)
+			mod = NULL;
 	}
 
 	if (!mod) {
@@ -72,14 +85,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 
 		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-				      map__start(al->map) - map__pgoff(al->map), false);
+				      base, false);
 	}
 	if (!mod) {
 		char filename[PATH_MAX];
 
 		if (dso__build_id_filename(dso, filename, sizeof(filename), false))
 			mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
-					      map__start(al->map) - map__pgoff(al->map), false);
+					      base, false);
 	}
 
 	if (mod) {
Signature · 1 line
2.43.0
author maintainer
#493 lore raw

PATCH 487/583 perf unwind-libunwind: Fix base address for .eh_frame

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Namhyung Kim <[email protected]>

[ Upstream commit 4fb54994b2360ab5029ee3a959161f6fe6bbb349 ]

The base address of a DSO mapping should start at the start of the file. Usually DSOs are mapped from the pgoff 0 so it doesn't matter when it uses the start of the map address.

But generated DSOs for JIT codes doesn't start from the 0 so it should subtract the offset to calculate the .eh_frame table offsets correctly.

Fixes dc2cf4ca866f5715 ("perf unwind: Fix segbase for ld.lld linked objects")
Cc Adrian Hunter <[email protected]>
Cc Fangrui Song <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Milian Wolff <[email protected]>
Cc Pablo Galindo <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/unwind-libunwind-local.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/unwind-libunwind-local.c +1 -1
index c0641882fd2f..5e5c3395a499 100644
@@ -327,7 +327,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui,
 
 	maps__for_each_entry(thread__maps(ui->thread), map_node) {
 		struct map *map = map_node->map;
-		u64 start = map__start(map);
+		u64 start = map__start(map) - map__pgoff(map);
 
 		if (map__dso(map) == dso && start < base_addr)
 			base_addr = start;
Signature · 1 line
2.43.0
author maintainer
#494 lore raw

PATCH 488/583 bus: mhi: ep: Do not allocate event ring element on stack

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit 987fdb5a43a66764808371b54e6047834170d565 ]

It is possible that the host controller driver would use DMA framework to write the event ring element. So avoid allocating event ring element on the stack as DMA cannot work on vmalloc memory.

Fixes 961aeb689224 ("bus: mhi: ep: Add support for sending events to the host")

Stable-dep-of: 327ec5f70609 ("PCI: epf-mhi: Fix the DMA data direction of dma_unmap_single()")

---
 drivers/bus/mhi/ep/main.c | 68 ++++++++++++++++++++++++++++-----------
 1 file changed, 50 insertions(+), 18 deletions(-)
drivers/bus/mhi/ep/main.c +50 -18
index 600881808982..e2513f5f47a6 100644
@@ -71,45 +71,77 @@ static int mhi_ep_send_event(struct mhi_ep_cntrl *mhi_cntrl, u32 ring_idx,
 static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_ring *ring,
 					struct mhi_ring_element *tre, u32 len, enum mhi_ev_ccs code)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
-	event.dword[0] = MHI_TRE_EV_DWORD0(code, len);
-	event.dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(*tre));
+	event->dword[0] = MHI_TRE_EV_DWORD0(code, len);
+	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, ring->er_index, &event, MHI_TRE_DATA_GET_BEI(tre));
+	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
+	kfree(event);
+
+	return ret;
 }
 
 int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_state state)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.dword[0] = MHI_SC_EV_DWORD0(state);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
+	event->dword[0] = MHI_SC_EV_DWORD0(state);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_env)
 {
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.dword[0] = MHI_EE_EV_DWORD0(exec_env);
-	event.dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
+	event->dword[0] = MHI_EE_EV_DWORD0(exec_env);
+	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ev_ccs code)
 {
 	struct mhi_ep_ring *ring = &mhi_cntrl->mhi_cmd->ring;
-	struct mhi_ring_element event = {};
+	struct mhi_ring_element *event;
+	int ret;
+
+	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
 
-	event.ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
-	event.dword[0] = MHI_CC_EV_DWORD0(code);
-	event.dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
+	event->ptr = cpu_to_le64(ring->rbase + ring->rd_offset * sizeof(struct mhi_ring_element));
+	event->dword[0] = MHI_CC_EV_DWORD0(code);
+	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
-	return mhi_ep_send_event(mhi_cntrl, 0, &event, 0);
+	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
+	kfree(event);
+
+	return ret;
 }
 
 static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_element *el)
Signature · 1 line
2.43.0
author maintainer
#495 lore raw

PATCH 489/583 bus: mhi: ep: Use slab allocator where applicable

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit 62210a26cd4f8ad52683a71c0226dfe85de1144d ]

Use slab allocator for allocating the memory for objects used frequently and are of fixed size. This reduces the overheard associated with kmalloc().

Stable-dep-of: 327ec5f70609 ("PCI: epf-mhi: Fix the DMA data direction of dma_unmap_single()")

---
 drivers/bus/mhi/ep/main.c | 66 +++++++++++++++++++++++++++++----------
 include/linux/mhi_ep.h    |  3 ++
 2 files changed, 52 insertions(+), 17 deletions(-)
drivers/bus/mhi/ep/main.c +49 -17
index e2513f5f47a6..517279600645 100644
@@ -74,7 +74,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -83,7 +83,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
 	event->dword[1] = MHI_TRE_EV_DWORD1(ring->ch_id, MHI_PKT_TYPE_TX_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, ring->er_index, event, MHI_TRE_DATA_GET_BEI(tre));
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -93,7 +93,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -101,7 +101,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_STATE_CHANGE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -111,7 +111,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -119,7 +119,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
 	event->dword[1] = MHI_SC_EV_DWORD1(MHI_PKT_TYPE_EE_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -130,7 +130,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	struct mhi_ring_element *event;
 	int ret;
 
-	event = kzalloc(sizeof(struct mhi_ring_element), GFP_KERNEL);
+	event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
 	if (!event)
 		return -ENOMEM;
 
@@ -139,7 +139,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
 	event->dword[1] = MHI_CC_EV_DWORD1(MHI_PKT_TYPE_CMD_COMPLETION_EVENT);
 
 	ret = mhi_ep_send_event(mhi_cntrl, 0, event, 0);
-	kfree(event);
+	kmem_cache_free(mhi_cntrl->ev_ring_el_cache, event);
 
 	return ret;
 }
@@ -451,7 +451,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 		mhi_chan->xfer_cb(mhi_chan->mhi_dev, &result);
 	} else {
 		/* UL channel */
-		result.buf_addr = kzalloc(len, GFP_KERNEL);
+		result.buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
 		if (!result.buf_addr)
 			return -ENOMEM;
 
@@ -459,7 +459,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			ret = mhi_ep_read_channel(mhi_cntrl, ring, &result, len);
 			if (ret < 0) {
 				dev_err(&mhi_chan->mhi_dev->dev, "Failed to read channel\n");
-				kfree(result.buf_addr);
+				kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 				return ret;
 			}
 
@@ -471,7 +471,7 @@ static int mhi_ep_process_ch_ring(struct mhi_ep_ring *ring, struct mhi_ring_elem
 			/* Read until the ring becomes empty */
 		} while (!mhi_ep_queue_is_empty(mhi_chan->mhi_dev, DMA_TO_DEVICE));
 
-		kfree(result.buf_addr);
+		kmem_cache_free(mhi_cntrl->tre_buf_cache, result.buf_addr);
 	}
 
 	return 0;
@@ -780,14 +780,14 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 		if (ret) {
 			dev_err(dev, "Error updating write offset for ring\n");
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		/* Sanity check to make sure there are elements in the ring */
 		if (ring->rd_offset == ring->wr_offset) {
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
@@ -799,12 +799,12 @@ static void mhi_ep_ch_ring_worker(struct work_struct *work)
 			dev_err(dev, "Error processing ring for channel (%u): %d\n",
 				ring->ch_id, ret);
 			mutex_unlock(&chan->lock);
-			kfree(itr);
+			kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 			continue;
 		}
 
 		mutex_unlock(&chan->lock);
-		kfree(itr);
+		kmem_cache_free(mhi_cntrl->ring_item_cache, itr);
 	}
 }
 
@@ -860,7 +860,7 @@ static void mhi_ep_queue_channel_db(struct mhi_ep_cntrl *mhi_cntrl, unsigned lon
 		u32 ch_id = ch_idx + i;
 
 		ring = &mhi_cntrl->mhi_chan[ch_id].ring;
-		item = kzalloc(sizeof(*item), GFP_ATOMIC);
+		item = kmem_cache_zalloc(mhi_cntrl->ring_item_cache, GFP_ATOMIC);
 		if (!item)
 			return;
 
@@ -1407,6 +1407,29 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		goto err_free_ch;
 	}
 
+	mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el",
+							sizeof(struct mhi_ring_element), 0,
+							SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0,
+						      SLAB_CACHE_DMA, NULL);
+	if (!mhi_cntrl->tre_buf_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_ev_ring_el_cache;
+	}
+
+	mhi_cntrl->ring_item_cache = kmem_cache_create("mhi_ep_ring_item",
+							sizeof(struct mhi_ep_ring_item), 0,
+							0, NULL);
+	if (!mhi_cntrl->ev_ring_el_cache) {
+		ret = -ENOMEM;
+		goto err_destroy_tre_buf_cache;
+	}
+
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
@@ -1415,7 +1438,7 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	mhi_cntrl->wq = alloc_workqueue("mhi_ep_wq", 0, 0);
 	if (!mhi_cntrl->wq) {
 		ret = -ENOMEM;
-		goto err_free_cmd;
+		goto err_destroy_ring_item_cache;
 	}
 
 	INIT_LIST_HEAD(&mhi_cntrl->st_transition_list);
@@ -1474,6 +1497,12 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 	ida_free(&mhi_ep_cntrl_ida, mhi_cntrl->index);
 err_destroy_wq:
 	destroy_workqueue(mhi_cntrl->wq);
+err_destroy_ring_item_cache:
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
+err_destroy_ev_ring_el_cache:
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+err_destroy_tre_buf_cache:
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
 err_free_cmd:
 	kfree(mhi_cntrl->mhi_cmd);
 err_free_ch:
@@ -1495,6 +1524,9 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl)
 
 	free_irq(mhi_cntrl->irq, mhi_cntrl);
 
+	kmem_cache_destroy(mhi_cntrl->tre_buf_cache);
+	kmem_cache_destroy(mhi_cntrl->ev_ring_el_cache);
+	kmem_cache_destroy(mhi_cntrl->ring_item_cache);
 	kfree(mhi_cntrl->mhi_cmd);
 	kfree(mhi_cntrl->mhi_chan);
 
include/linux/mhi_ep.h +3 -0
index f198a8ac7ee7..ce85d42b685d 100644
@@ -128,6 +128,9 @@ struct mhi_ep_cntrl {
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
 	struct work_struct ch_ring_work;
+	struct kmem_cache *ring_item_cache;
+	struct kmem_cache *ev_ring_el_cache;
+	struct kmem_cache *tre_buf_cache;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
Signature · 1 line
2.43.0
author maintainer
#496 lore raw

PATCH 490/583 bus: mhi: ep: Pass mhi_ep_buf_info struct to read/write APIs

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit b08ded2ef2e98768d5ee5f71da8fe768b1f7774b ]

In the preparation of DMA async support, let's pass the parameters to read_from_host() and write_to_host() APIs using mhi_ep_buf_info structure.

No functional change.

Stable-dep-of: 327ec5f70609 ("PCI: epf-mhi: Fix the DMA data direction of dma_unmap_single()")

---
 drivers/bus/mhi/ep/main.c                    | 23 +++----
 drivers/bus/mhi/ep/ring.c                    | 41 ++++++------
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 66 +++++++++++---------
 include/linux/mhi_ep.h                       | 16 ++++-
 4 files changed, 84 insertions(+), 62 deletions(-)
drivers/bus/mhi/ep/main.c +12 -11
index 517279600645..582d5c166a75 100644
@@ -324,10 +324,9 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 	struct mhi_ep_chan *mhi_chan = &mhi_cntrl->mhi_chan[ring->ch_id];
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	size_t tr_len, read_offset, write_offset;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	bool tr_done = false;
-	void *write_addr;
-	u64 read_addr;
 	u32 buf_left;
 	int ret;
 
@@ -356,11 +355,13 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
 
 		read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
 		write_offset = len - buf_left;
-		read_addr = mhi_chan->tre_loc + read_offset;
-		write_addr = result->buf_addr + write_offset;
+
+		buf_info.host_addr = mhi_chan->tre_loc + read_offset;
+		buf_info.dev_addr = result->buf_addr + write_offset;
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Reading %zd bytes from channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->read_from_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->read_from_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(&mhi_chan->mhi_dev->dev, "Error reading from channel\n");
 			return ret;
@@ -483,12 +484,11 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 	struct mhi_ep_cntrl *mhi_cntrl = mhi_dev->mhi_cntrl;
 	struct mhi_ep_chan *mhi_chan = mhi_dev->dl_chan;
 	struct device *dev = &mhi_chan->mhi_dev->dev;
+	struct mhi_ep_buf_info buf_info = {};
 	struct mhi_ring_element *el;
 	u32 buf_left, read_offset;
 	struct mhi_ep_ring *ring;
 	enum mhi_ev_ccs code;
-	void *read_addr;
-	u64 write_addr;
 	size_t tr_len;
 	u32 tre_len;
 	int ret;
@@ -517,11 +517,13 @@ int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb)
 
 		tr_len = min(buf_left, tre_len);
 		read_offset = skb->len - buf_left;
-		read_addr = skb->data + read_offset;
-		write_addr = MHI_TRE_DATA_GET_PTR(el);
+
+		buf_info.dev_addr = skb->data + read_offset;
+		buf_info.host_addr = MHI_TRE_DATA_GET_PTR(el);
+		buf_info.size = tr_len;
 
 		dev_dbg(dev, "Writing %zd bytes to channel (%u)\n", tr_len, ring->ch_id);
-		ret = mhi_cntrl->write_to_host(mhi_cntrl, read_addr, write_addr, tr_len);
+		ret = mhi_cntrl->write_to_host(mhi_cntrl, &buf_info);
 		if (ret < 0) {
 			dev_err(dev, "Error writing to the channel\n");
 			goto err_exit;
@@ -1429,7 +1431,6 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
 		ret = -ENOMEM;
 		goto err_destroy_tre_buf_cache;
 	}
-
 	INIT_WORK(&mhi_cntrl->state_work, mhi_ep_state_worker);
 	INIT_WORK(&mhi_cntrl->reset_work, mhi_ep_reset_worker);
 	INIT_WORK(&mhi_cntrl->cmd_ring_work, mhi_ep_cmd_ring_worker);
drivers/bus/mhi/ep/ring.c +23 -18

78 lines not on this page · raw message

drivers/pci/endpoint/functions/pci-epf-mhi.c +35 -31

174 lines not on this page · raw message

include/linux/mhi_ep.h +14 -2
index ce85d42b685d..96f3a133540d 100644
@@ -49,6 +49,18 @@ struct mhi_ep_db_info {
 	u32 status;
 };
 
+/**
+ * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @dev_addr: Address of the buffer in endpoint
+ * @host_addr: Address of the bufffer in host
+ * @size: Size of the buffer
+ */
+struct mhi_ep_buf_info {
+	void *dev_addr;
+	u64 host_addr;
+	size_t size;
+};
+
 /**
  * struct mhi_ep_cntrl - MHI Endpoint controller structure
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
@@ -137,8 +149,8 @@ struct mhi_ep_cntrl {
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
Signature · 1 line
2.43.0
author maintainer
#497 lore raw

PATCH 491/583 PCI: epf-mhi: Fix the DMA data direction of dma_unmap_single()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit 327ec5f70609cf00c6f961073c01857555c6a8eb ]

In the error path of pci_epf_mhi_edma_write() function, the DMA data direction passed (DMA_FROM_DEVICE) doesn't match the actual direction used for the data transfer. Fix it by passing the correct one (DMA_TO_DEVICE).

---
 drivers/pci/endpoint/functions/pci-epf-mhi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/pci/endpoint/functions/pci-epf-mhi.c +1 -1
index ec5f4a38178b..6dc918a8a023 100644
@@ -405,7 +405,7 @@ static int pci_epf_mhi_edma_write(struct mhi_ep_cntrl *mhi_cntrl,
 	}
 
 err_unmap:
-	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_FROM_DEVICE);
+	dma_unmap_single(dma_dev, src_addr, buf_info->size, DMA_TO_DEVICE);
 err_unlock:
 	mutex_unlock(&epf_mhi->lock);
 
Signature · 1 line
2.43.0
author maintainer
#498 lore raw

PATCH 492/583 tty: early return from send_break() on TTY_DRIVER_HARDWARE_BREAK

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Slaby (SUSE) <[email protected]>

[ Upstream commit 66619686d187b4a6395316b7f39881e945dce4bc ]

If the driver sets TTY_DRIVER_HARDWARE_BREAK, we leave ops->break_ctl() to the driver and return from send_break(). But we do it using a local variable and keep the code flowing through the end of the function. Instead, do 'return' immediately with the ops->break_ctl()'s return value.

This way, we don't have to stuff the 'else' branch of the 'if' with the software break handling. And we can re-indent the function too.

Stable-dep-of: 66aad7d8d3ec ("usb: cdc-acm: return correct error code on unsupported break")

---
 drivers/tty/tty_io.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)
drivers/tty/tty_io.c +17 -15
index 8a94e5a43c6d..b6ddc1bf307b 100644
@@ -2475,22 +2475,24 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 		return 0;
 
 	if (tty->driver->flags & TTY_DRIVER_HARDWARE_BREAK)
-		retval = tty->ops->break_ctl(tty, duration);
-	else {
-		/* Do the work ourselves */
-		if (tty_write_lock(tty, false) < 0)
-			return -EINTR;
-		retval = tty->ops->break_ctl(tty, -1);
-		if (retval)
-			goto out;
-		if (!signal_pending(current))
-			msleep_interruptible(duration);
-		retval = tty->ops->break_ctl(tty, 0);
+		return tty->ops->break_ctl(tty, duration);
+
+	/* Do the work ourselves */
+	if (tty_write_lock(tty, false) < 0)
+		return -EINTR;
+
+	retval = tty->ops->break_ctl(tty, -1);
+	if (retval)
+		goto out;
+	if (!signal_pending(current))
+		msleep_interruptible(duration);
+	retval = tty->ops->break_ctl(tty, 0);
 out:
-		tty_write_unlock(tty);
-		if (signal_pending(current))
-			retval = -EINTR;
-	}
+	tty_write_unlock(tty);
+
+	if (signal_pending(current))
+		retval = -EINTR;
+
 	return retval;
 }
 
Signature · 1 line
2.43.0
author maintainer
#499 lore raw

PATCH 493/583 tty: dont check for signal_pending() in send_break()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Slaby (SUSE) <[email protected]>

[ Upstream commit fd99392b643b824813df2edbaebe26a2136d31e6 ]

msleep_interruptible() will check on its own. So no need to do the check in send_break() before calling the above.

Stable-dep-of: 66aad7d8d3ec ("usb: cdc-acm: return correct error code on unsupported break")

---
 drivers/tty/tty_io.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/tty/tty_io.c +1 -2
index b6ddc1bf307b..ddcaf967f64b 100644
@@ -2484,8 +2484,7 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	retval = tty->ops->break_ctl(tty, -1);
 	if (retval)
 		goto out;
-	if (!signal_pending(current))
-		msleep_interruptible(duration);
+	msleep_interruptible(duration);
 	retval = tty->ops->break_ctl(tty, 0);
 out:
 	tty_write_unlock(tty);
Signature · 1 line
2.43.0
author maintainer
#500 lore raw

PATCH 494/583 tty: use if in send_break() instead of goto

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiri Slaby (SUSE) <[email protected]>

[ Upstream commit 24f2cd019946fc2e88e632d2e24a34c2cc3f2be4 ]

Now, the "jumped-over" code is simple enough to be put inside an 'if'. Do so to make it 'goto'-less.

Stable-dep-of: 66aad7d8d3ec ("usb: cdc-acm: return correct error code on unsupported break")

---
 drivers/tty/tty_io.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)
drivers/tty/tty_io.c +4 -5
index ddcaf967f64b..724ebf82f2cd 100644
@@ -2482,11 +2482,10 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 		return -EINTR;
 
 	retval = tty->ops->break_ctl(tty, -1);
-	if (retval)
-		goto out;
-	msleep_interruptible(duration);
-	retval = tty->ops->break_ctl(tty, 0);
-out:
+	if (!retval) {
+		msleep_interruptible(duration);
+		retval = tty->ops->break_ctl(tty, 0);
+	}
 	tty_write_unlock(tty);
 
 	if (signal_pending(current))
Signature · 1 line
2.43.0
author maintainer
#501 lore raw

PATCH 495/583 usb: cdc-acm: return correct error code on unsupported break

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oliver Neukum <[email protected]>

[ Upstream commit 66aad7d8d3ec5a3a8ec2023841bcec2ded5f65c9 ]

In ACM support for sending breaks to devices is optional. If a device says that it doenot support sending breaks, the host must respect that.
Given the number of optional features providing tty operations for each combination is not practical and errors need to be returned dynamically if unsupported features are requested.

In case a device does not support break, we want the tty layer to treat that like it treats drivers that statically cannot support sending a break. It ignores the inability and does nothing. This patch uses EOPNOTSUPP to indicate that.

---
 drivers/tty/tty_io.c        | 3 +++
 drivers/usb/class/cdc-acm.c | 3 +++
 2 files changed, 6 insertions(+)
drivers/tty/tty_io.c +3 -0
index 724ebf82f2cd..493fc4742895 100644
@@ -2485,6 +2485,9 @@ static int send_break(struct tty_struct *tty, unsigned int duration)
 	if (!retval) {
 		msleep_interruptible(duration);
 		retval = tty->ops->break_ctl(tty, 0);
+	} else if (retval == -EOPNOTSUPP) {
+		/* some drivers can tell only dynamically */
+		retval = 0;
 	}
 	tty_write_unlock(tty);
 
drivers/usb/class/cdc-acm.c +3 -0
index a1f4e1ead97f..0e7439dba8fe 100644
@@ -916,6 +916,9 @@ static int acm_tty_break_ctl(struct tty_struct *tty, int state)
 	struct acm *acm = tty->driver_data;
 	int retval;
 
+	if (!(acm->ctrl_caps & USB_CDC_CAP_BRK))
+		return -EOPNOTSUPP;
+
 	retval = acm_send_break(acm, state ? 0xffff : 0);
 	if (retval < 0)
 		dev_dbg(&acm->control->dev,
Signature · 1 line
2.43.0
author maintainer
#502 lore raw

PATCH 496/583 usb: core: Fix crash w/ usb_choose_configuration() if no driver

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Douglas Anderson <[email protected]>

[ Upstream commit 44995e6f07028f798efd0c3c11a1efc78330f600 ]

It's possible that usb_choose_configuration() can get called when a USB device has no driver. In this case the recent commit a87b8e3be926 ("usb: core: Allow subclassed USB drivers to override usb_choose_configuration()") can cause a crash since it dereferenced the driver structure without checking for NULL. Let's add a check.

A USB device with no driver is an anomaly, so make usb_choose_configuration() return immediately if there is no driver.

This was seen in the real world when usbguard got ahold of a r8152 device at the wrong time. It can also be simulated via this on a computer with one r8152-based USB Ethernet adapter:
cd /sys/bus/usb/drivers/r8152-cfgselector to_unbind="$(ls -d *-*)"
real_dir="$(readlink -f "${to_unbind}")"
echo "${to_unbind}" > unbind
cd "${real_dir}"
echo 0 > authorized
echo 1 > authorized

---
 drivers/usb/core/generic.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
drivers/usb/core/generic.c +10 -1
index dcb897158228..b134bff5c3fe 100644
@@ -59,7 +59,16 @@ int usb_choose_configuration(struct usb_device *udev)
 	int num_configs;
 	int insufficient_power = 0;
 	struct usb_host_config *c, *best;
-	struct usb_device_driver *udriver = to_usb_device_driver(udev->dev.driver);
+	struct usb_device_driver *udriver;
+
+	/*
+	 * If a USB device (not an interface) doesn't have a driver then the
+	 * kernel has no business trying to select or install a configuration
+	 * for it.
+	 */
+	if (!udev->dev.driver)
+		return -1;
+	udriver = to_usb_device_driver(udev->dev.driver);
 
 	if (usb_device_is_owned(udev))
 		return 0;
Signature · 1 line
2.43.0
author maintainer
#503 lore raw

PATCH 497/583 spmi: mtk-pmif: Serialize PMIF status check and command submission

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nícolas F. R. A. Prado <[email protected]>

[ Upstream commit f200fff8d019f2754f91f5d715652e3e3fdf3604 ]

Before writing the read or write command to the SPMI arbiter through the PMIF interface, the current status of the channel is checked to ensure it is idle. However, since the status only changes from idle when the command is written, it is possible for two concurrent calls to determine that the channel is idle and simultaneously send their commands. At this point the PMIF interface hangs, with the status register no longer being updated, and thus causing all subsequent operations to time out.

This was observed on the mt8195-cherry-tomato-r2 machine, particularly after commit 46600ab142f8 ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for drivers between 5.10 and 5.15") was applied, since then the two MT6315 devices present on the SPMI bus would probe assynchronously and sometimes (during probe or at a later point) read the bus simultaneously, breaking the PMIF interface and consequently slowing down the whole system.

To fix the issue at its root cause, introduce locking around the channel status check and the command write, so that both become an atomic operation, preventing race conditions between two (or more) SPMI bus read/write operations. A spinlock is used since this is a fast bus, as indicated by the usage of the atomic variant of readl_poll, and '.fast_io = true' being used in the mt6315 driver, so spinlocks are already used for the regmap access.

---
 drivers/spmi/spmi-mtk-pmif.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)
drivers/spmi/spmi-mtk-pmif.c +16 -4
index b3c991e1ea40..54c35f5535cb 100644
@@ -50,6 +50,7 @@ struct pmif {
 	struct clk_bulk_data clks[PMIF_MAX_CLKS];
 	size_t nclks;
 	const struct pmif_data *data;
+	raw_spinlock_t lock;
 };
 
 static const char * const pmif_clock_names[] = {
@@ -314,6 +315,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct ch_reg *inf_reg;
 	int ret;
 	u32 data, cmd;
+	unsigned long flags;
 
 	/* Check for argument validation. */
 	if (sid & ~0xf) {
@@ -334,6 +336,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -343,6 +346,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
@@ -350,6 +354,7 @@ static int pmif_spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	/* Send the command. */
 	cmd = (opc << 30) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	/*
 	 * Wait for Software Interface FSM state to be WFVLDCLR,
@@ -376,7 +381,8 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	struct pmif *arb = spmi_controller_get_drvdata(ctrl);
 	struct ch_reg *inf_reg;
 	int ret;
-	u32 data, cmd;
+	u32 data, wdata, cmd;
+	unsigned long flags;
 
 	if (len > 4) {
 		dev_err(&ctrl->dev, "pmif supports 1..4 bytes per trans, but:%zu requested", len);
@@ -394,6 +400,10 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 	else
 		return -EINVAL;
 
+	/* Set the write data. */
+	memcpy(&wdata, buf, len);
+
+	raw_spin_lock_irqsave(&arb->lock, flags);
 	/* Wait for Software Interface FSM state to be IDLE. */
 	inf_reg = &arb->chan;
 	ret = readl_poll_timeout_atomic(arb->base + arb->data->regs[inf_reg->ch_sta],
@@ -403,17 +413,17 @@ static int pmif_spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
 		/* set channel ready if the data has transferred */
 		if (pmif_is_fsm_vldclr(arb))
 			pmif_writel(arb, 1, inf_reg->ch_rdy);
+		raw_spin_unlock_irqrestore(&arb->lock, flags);
 		dev_err(&ctrl->dev, "failed to wait for SWINF_IDLE\n");
 		return ret;
 	}
 
-	/* Set the write data. */
-	memcpy(&data, buf, len);
-	pmif_writel(arb, data, inf_reg->wdata);
+	pmif_writel(arb, wdata, inf_reg->wdata);
 
 	/* Send the command. */
 	cmd = (opc << 30) | BIT(29) | (sid << 24) | ((len - 1) << 16) | addr;
 	pmif_writel(arb, cmd, inf_reg->ch_send);
+	raw_spin_unlock_irqrestore(&arb->lock, flags);
 
 	return 0;
 }
@@ -488,6 +498,8 @@ static int mtk_spmi_probe(struct platform_device *pdev)
 	arb->chan.ch_send = PMIF_SWINF_0_ACC + chan_offset;
 	arb->chan.ch_rdy = PMIF_SWINF_0_VLD_CLR + chan_offset;
 
+	raw_spin_lock_init(&arb->lock);
+
 	platform_set_drvdata(pdev, ctrl);
 
 	err = spmi_controller_add(ctrl);
Signature · 1 line
2.43.0
author maintainer
#504 lore raw

PATCH 498/583 usb: gadget: webcam: Make g_webcam loadable again

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrzej Pietrasiewicz <[email protected]>

[ Upstream commit f1fd91a0924b6bff91ca1287461fb8e3b3b61d92 ]

commit 588b9e85609b ("usb: gadget: uvc: add v4l2 enumeration api calls") has rendered the precomposed (aka legacy) webcam gadget unloadable.

uvc_alloc() since then has depended on certain config groups being available in configfs tree related to the UVC function. However, legacy gadgets do not create anything in configfs, so uvc_alloc() must fail with -ENOENT no matter what.

This patch mimics the required configfs hierarchy to satisfy the code which inspects formats and frames found in uvcg_streaming_header.

This has been tested with guvcview on the host side, using vivid as a source of video stream on the device side and using the userspace program found at https://gitlab.freedesktop.org/camera/uvc-gadget.git.

Fixes 588b9e85609b ("usb: gadget: uvc: add v4l2 enumeration api calls")
---
 drivers/usb/gadget/function/f_uvc.c |  45 ++--
 drivers/usb/gadget/function/u_uvc.h |   6 +
 drivers/usb/gadget/legacy/webcam.c  | 333 +++++++++++++++++++++-------
 3 files changed, 284 insertions(+), 100 deletions(-)
drivers/usb/gadget/function/f_uvc.c +25 -20
index 3d5c03e1361e..2e6bafb2a554 100644
@@ -966,7 +966,8 @@ static void uvc_free(struct usb_function *f)
 	struct uvc_device *uvc = to_uvc(f);
 	struct f_uvc_opts *opts = container_of(f->fi, struct f_uvc_opts,
 					       func_inst);
-	config_item_put(&uvc->header->item);
+	if (!opts->header)
+		config_item_put(&uvc->header->item);
 	--opts->refcnt;
 	kfree(uvc);
 }
@@ -1058,25 +1059,29 @@ static struct usb_function *uvc_alloc(struct usb_function_instance *fi)
 	uvc->desc.hs_streaming = opts->hs_streaming;
 	uvc->desc.ss_streaming = opts->ss_streaming;
 
-	streaming = config_group_find_item(&opts->func_inst.group, "streaming");
-	if (!streaming)
-		goto err_config;
-
-	header = config_group_find_item(to_config_group(streaming), "header");
-	config_item_put(streaming);
-	if (!header)
-		goto err_config;
-
-	h = config_group_find_item(to_config_group(header), "h");
-	config_item_put(header);
-	if (!h)
-		goto err_config;
-
-	uvc->header = to_uvcg_streaming_header(h);
-	if (!uvc->header->linked) {
-		mutex_unlock(&opts->lock);
-		kfree(uvc);
-		return ERR_PTR(-EBUSY);
+	if (opts->header) {
+		uvc->header = opts->header;
+	} else {
+		streaming = config_group_find_item(&opts->func_inst.group, "streaming");
+		if (!streaming)
+			goto err_config;
+
+		header = config_group_find_item(to_config_group(streaming), "header");
+		config_item_put(streaming);
+		if (!header)
+			goto err_config;
+
+		h = config_group_find_item(to_config_group(header), "h");
+		config_item_put(header);
+		if (!h)
+			goto err_config;
+
+		uvc->header = to_uvcg_streaming_header(h);
+		if (!uvc->header->linked) {
+			mutex_unlock(&opts->lock);
+			kfree(uvc);
+			return ERR_PTR(-EBUSY);
+		}
 	}
 
 	uvc->desc.extension_units = &opts->extension_units;
drivers/usb/gadget/function/u_uvc.h +6 -0
index 1ce58f61253c..3ac392cbb779 100644
@@ -98,6 +98,12 @@ struct f_uvc_opts {
 	 */
 	struct mutex			lock;
 	int				refcnt;
+
+	/*
+	 * Only for legacy gadget. Shall be NULL for configfs-composed gadgets,
+	 * which is guaranteed by alloc_inst implementation of f_uvc doing kzalloc.
+	 */
+	struct uvcg_streaming_header	*header;
 };
 
 #endif /* U_UVC_H */
drivers/usb/gadget/legacy/webcam.c +253 -80

423 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#505 lore raw

PATCH 499/583 iommu: Dont reserve 0-length IOVA region

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ashish Mhetre <[email protected]>

[ Upstream commit bb57f6705960bebeb832142ce9abf43220c3eab1 ]

When the bootloader/firmware doesn't setup the framebuffers, their address and size are 0 in "iommu-addresses" property. If IOVA region is reserved with 0 length, then it ends up corrupting the IOVA rbtree with an entry which has pfn_hi < pfn_lo.
If we intend to use display driver in kernel without framebuffer then it's causing the display IOMMU mappings to fail as entire valid IOVA space is reserved when address and length are passed as 0. An ideal solution would be firmware removing the "iommu-addresses" property and corresponding "memory-region" if display is not present. But the kernel should be able to handle this by checking for size of IOVA region and skipping the IOVA reservation if size is 0. Also, add a warning if firmware is requesting 0-length IOVA region reservation.

Fixes a5bf3cfce8cb ("iommu: Implement of_iommu_get_resv_regions()")
---
 drivers/iommu/of_iommu.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/iommu/of_iommu.c +4 -0
index 47302b637cc0..42cffb0ee5e2 100644
@@ -264,6 +264,10 @@ void of_iommu_get_resv_regions(struct device *dev, struct list_head *list)
 					prot |= IOMMU_CACHE;
 
 				maps = of_translate_dma_region(np, maps, &iova, &length);
+				if (length == 0) {
+					dev_warn(dev, "Cannot reserve IOVA region of 0 size\n");
+					continue;
+				}
 				type = iommu_resv_region_get_type(dev, &phys, iova, length);
 
 				region = iommu_alloc_resv_region(iova, length, prot, type,
Signature · 1 line
2.43.0
author maintainer
#506 lore raw

PATCH 500/583 power: supply: Fix null pointer dereference in smb2_probe

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kunwu Chan <[email protected]>

[ Upstream commit 88f04bc3e737155e13caddf0ba8ed19db87f0212 ]

devm_kasprintf and devm_kzalloc return a pointer to dynamically allocated memory which can be NULL upon failure.

Fixes 8648aeb5d7b7 ("power: supply: add Qualcomm PMI8998 SMB2 Charger driver")
---
 drivers/power/supply/qcom_pmi8998_charger.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/power/supply/qcom_pmi8998_charger.c +4 -0
index 10f4dd0caca1..22c7c0e7c522 100644
@@ -973,10 +973,14 @@ static int smb2_probe(struct platform_device *pdev)
 	supply_config.of_node = pdev->dev.of_node;
 
 	desc = devm_kzalloc(chip->dev, sizeof(smb2_psy_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
 	memcpy(desc, &smb2_psy_desc, sizeof(smb2_psy_desc));
 	desc->name =
 		devm_kasprintf(chip->dev, GFP_KERNEL, "%s-charger",
 			       (const char *)device_get_match_data(chip->dev));
+	if (!desc->name)
+		return -ENOMEM;
 
 	chip->chg_psy =
 		devm_power_supply_register(chip->dev, desc, &supply_config);
Signature · 1 line
2.43.0
author maintainer
#507 lore raw

PATCH 501/583 vdpa: Fix an error handling path in eni_vdpa_probe()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit c1b9f2c66eed3261db76cccd8a22a9affae8dcbf ]

After a successful vp_legacy_probe() call, vp_legacy_remove() should be called in the error handling path, as already done in the remove function.

Add the missing call.

Fixes e85087beedca ("eni_vdpa: add vDPA driver for Alibaba ENI")

Message-Id: <a7b0ef1eabd081f1c7c894e9b11de01678e85dee.1666293559.git.christophe.jaillet@wanadoo.fr>

---
 drivers/vdpa/alibaba/eni_vdpa.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/vdpa/alibaba/eni_vdpa.c +4 -2
index 5a09a09cca70..cce3d1837104 100644
@@ -497,7 +497,7 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!eni_vdpa->vring) {
 		ret = -ENOMEM;
 		ENI_ERR(pdev, "failed to allocate virtqueues\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	for (i = 0; i < eni_vdpa->queues; i++) {
@@ -509,11 +509,13 @@ static int eni_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = vdpa_register_device(&eni_vdpa->vdpa, eni_vdpa->queues);
 	if (ret) {
 		ENI_ERR(pdev, "failed to register to vdpa bus\n");
-		goto err;
+		goto err_remove_vp_legacy;
 	}
 
 	return 0;
 
+err_remove_vp_legacy:
+	vp_legacy_remove(&eni_vdpa->ldev);
 err:
 	put_device(&eni_vdpa->vdpa.dev);
 	return ret;
Signature · 1 line
2.43.0
author maintainer
#508 lore raw

PATCH 502/583 apparmor: Fix ref count leak in task_kill

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: John Johansen <[email protected]>

[ Upstream commit 2cb54a19ac7153b9a26a72098c495187f64c2276 ]

apparmor_task_kill was not putting the task_cred reference tc, or the cred_label reference tc when dealing with a passed in cred, fix this by using a single fn exit.

Fixes 90c436a64a6e ("apparmor: pass cred through to audit info.")
---
 security/apparmor/lsm.c | 1 -
 1 file changed, 1 deletion(-)
security/apparmor/lsm.c +0 -1
index 6fdab1b5ede5..366cdfd6a7ba 100644
@@ -839,7 +839,6 @@ static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo
 		cl = aa_get_newest_cred_label(cred);
 		error = aa_may_signal(cred, cl, tc, tl, sig);
 		aa_put_label(cl);
-		return error;
 	} else {
 		cl = __begin_current_label_crit_section();
 		error = aa_may_signal(current_cred(), cl, tc, tl, sig);
Signature · 1 line
2.43.0
author maintainer
#509 lore raw

PATCH 503/583 nvmet-tcp: Fix a kernel panic when host sends an invalid H2C PDU length

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maurizio Lombardi <[email protected]>

[ Upstream commit efa56305908ba20de2104f1b8508c6a7401833be ]

If the host sends an H2CData command with an invalid DATAL, the kernel may crash in nvmet_tcp_build_pdu_iovec().

Unable to handle kernel NULL pointer dereference at
virtual address 0000000000000000
lr : nvmet_tcp_io_work+0x6ac/0x718 [nvmet_tcp]
Call trace:
  process_one_work+0x174/0x3c8
  worker_thread+0x2d0/0x3e8
  kthread+0x104/0x110

Fix the bug by raising a fatal error if DATAL isn't coherent with the packet size.
Also, the PDU length should never exceed the MAXH2CDATA parameter which has been communicated to the host in nvmet_tcp_handle_icreq().

Fixes 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
---
 drivers/nvme/target/tcp.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)
drivers/nvme/target/tcp.c +12 -1
index 197fc2ecb164..3d171061cc0f 100644
@@ -19,6 +19,7 @@
 #include "nvmet.h"
 
 #define NVMET_TCP_DEF_INLINE_DATA_SIZE	(4 * PAGE_SIZE)
+#define NVMET_TCP_MAXH2CDATA		0x400000 /* 16M arbitrary limit */
 
 static int param_store_val(const char *str, int *val, int min, int max)
 {
@@ -900,7 +901,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
 	icresp->hdr.pdo = 0;
 	icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
 	icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
-	icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
+	icresp->maxdata = cpu_to_le32(NVMET_TCP_MAXH2CDATA);
 	icresp->cpda = 0;
 	if (queue->hdr_digest)
 		icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
@@ -953,6 +954,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
+	unsigned int plen;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
@@ -976,7 +978,16 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		return -EPROTO;
 	}
 
+	plen = le32_to_cpu(data->hdr.plen);
 	cmd->pdu_len = le32_to_cpu(data->data_length);
+	if (unlikely(cmd->pdu_len != (plen - sizeof(*data)) ||
+		     cmd->pdu_len == 0 ||
+		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
+		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
+		/* FIXME: use proper transport errors */
+		nvmet_tcp_fatal_error(queue);
+		return -EPROTO;
+	}
 	cmd->pdu_recv = 0;
 	nvmet_tcp_build_pdu_iovec(cmd);
 	queue->cmd = cmd;
Signature · 1 line
2.43.0
author maintainer
#510 lore raw

PATCH 504/583 nvmet-tcp: fix a crash in nvmet_req_complete()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maurizio Lombardi <[email protected]>

[ Upstream commit 0849a5441358cef02586fb2d60f707c0db195628 ]

in nvmet_tcp_handle_h2c_data_pdu(), if the host sends a data_offset different from rbytes_done, the driver ends up calling nvmet_req_complete() passing a status error.
The problem is that at this point cmd->req is not yet initialized, the kernel will crash after dereferencing a NULL pointer.

Fix the bug by replacing the call to nvmet_req_complete() with nvmet_tcp_fatal_error().

Fixes 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver")
---
 drivers/nvme/target/tcp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/nvme/target/tcp.c +1 -2
index 3d171061cc0f..7f7fa78f0698 100644
@@ -973,8 +973,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 			data->ttag, le32_to_cpu(data->data_offset),
 			cmd->rbytes_done);
 		/* FIXME: use path and transport errors */
-		nvmet_req_complete(&cmd->req,
-			NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+		nvmet_tcp_fatal_error(queue);
 		return -EPROTO;
 	}
 
Signature · 1 line
2.43.0
author maintainer
#511 lore raw

PATCH 505/583 perf env: Avoid recursively taking env->bpf_progs.lock

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit 9c51f8788b5d4e9f46afbcf563255cfd355690b3 ]

Add variants of perf_env__insert_bpf_prog_info(), perf_env__insert_btf() and perf_env__find_btf prefixed with __ to indicate the env->bpf_progs.lock is assumed held.

Call these variants when the lock is held to avoid recursively taking it and potentially having a thread deadlock with itself.

Fixes f8dfeae009effc0b ("perf bpf: Show more BPF program info in print_bpf_prog_info()")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Huacai Chen <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc K Prateek Nayak <[email protected]>
Cc Kan Liang <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Ming Wang <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ravi Bangoria <[email protected]>
---
 tools/perf/util/bpf-event.c |  8 +++---
 tools/perf/util/bpf-event.h | 12 ++++-----
 tools/perf/util/env.c       | 50 ++++++++++++++++++++++++-------------
 tools/perf/util/env.h       |  4 +++
 tools/perf/util/header.c    |  8 +++---
 5 files changed, 50 insertions(+), 32 deletions(-)
tools/perf/util/bpf-event.c +4 -4
index 38fcf3ba5749..b00b5a2634c3 100644
@@ -542,9 +542,9 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)
 	return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env);
 }
 
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp)
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp)
 {
 	__u32 *prog_lens = (__u32 *)(uintptr_t)(info->jited_func_lens);
 	__u64 *prog_addrs = (__u64 *)(uintptr_t)(info->jited_ksyms);
@@ -560,7 +560,7 @@ void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
 	if (info->btf_id) {
 		struct btf_node *node;
 
-		node = perf_env__find_btf(env, info->btf_id);
+		node = __perf_env__find_btf(env, info->btf_id);
 		if (node)
 			btf = btf__new((__u8 *)(node->data),
 				       node->data_size);
tools/perf/util/bpf-event.h +6 -6
index 1bcbd4fb6c66..e2f0420905f5 100644
@@ -33,9 +33,9 @@ struct btf_node {
 int machine__process_bpf(struct machine *machine, union perf_event *event,
 			 struct perf_sample *sample);
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env);
-void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
-				    struct perf_env *env,
-				    FILE *fp);
+void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info,
+				      struct perf_env *env,
+				      FILE *fp);
 #else
 static inline int machine__process_bpf(struct machine *machine __maybe_unused,
 				       union perf_event *event __maybe_unused,
@@ -50,9 +50,9 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,
 	return 0;
 }
 
-static inline void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
-						  struct perf_env *env __maybe_unused,
-						  FILE *fp __maybe_unused)
+static inline void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info __maybe_unused,
+						    struct perf_env *env __maybe_unused,
+						    FILE *fp __maybe_unused)
 {
 
 }
tools/perf/util/env.c +32 -18

112 lines not on this page · raw message

tools/perf/util/env.h +4 -0
index 4566c51f2fd9..359eff51cb85 100644
@@ -164,12 +164,16 @@ const char *perf_env__raw_arch(struct perf_env *env);
 int perf_env__nr_cpus_avail(struct perf_env *env);
 
 void perf_env__init(struct perf_env *env);
+void __perf_env__insert_bpf_prog_info(struct perf_env *env,
+				      struct bpf_prog_info_node *info_node);
 void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool __perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
+struct btf_node *__perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
tools/perf/util/header.c +4 -4
index f6035c219b41..1482567e5ac1 100644
@@ -1849,8 +1849,8 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp)
 		node = rb_entry(next, struct bpf_prog_info_node, rb_node);
 		next = rb_next(&node->rb_node);
 
-		bpf_event__print_bpf_prog_info(&node->info_linear->info,
-					       env, fp);
+		__bpf_event__print_bpf_prog_info(&node->info_linear->info,
+						 env, fp);
 	}
 
 	up_read(&env->bpf_progs.lock);
@@ -3177,7 +3177,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		/* after reading from file, translate offset to address */
 		bpil_offs_to_addr(info_linear);
 		info_node->info_linear = info_linear;
-		perf_env__insert_bpf_prog_info(env, info_node);
+		__perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
 	up_write(&env->bpf_progs.lock);
@@ -3224,7 +3224,7 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 		if (__do_read(ff, node->data, data_size))
 			goto out;
 
-		perf_env__insert_btf(env, node);
+		__perf_env__insert_btf(env, node);
 		node = NULL;
 	}
 
Signature · 1 line
2.43.0
author maintainer
#512 lore raw

PATCH 506/583 perf stat: Fix hard coded LL miss units

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers <[email protected]>

[ Upstream commit f2567e12a090f0eb22553a4468d4c4fe04aad906 ]

Copy-paste error where LL cache misses are reported as l1i.

Fixes 0a57b910807ad163 ("perf stat: Use counts rather than saved_value")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ian Rogers <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc John Garry <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/stat-shadow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/stat-shadow.c +1 -1
index 1c5c3eeba4cf..e31426167852 100644
@@ -264,7 +264,7 @@ static void print_ll_miss(struct perf_stat_config *config,
 	static const double color_ratios[3] = {20.0, 10.0, 5.0};
 
 	print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios,
-		    "of all L1-icache accesses");
+		    "of all LL-cache accesses");
 }
 
 static void print_dtlb_miss(struct perf_stat_config *config,
Signature · 1 line
2.43.0
author maintainer
#513 lore raw

PATCH 507/583 cxl/region: fix x9 interleave typo

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jim Harris <[email protected]>

[ Upstream commit c7ad3dc3649730af483ee1e78be5d0362da25bfe ]

CXL supports x3, x6 and x12 - not x9.

---
 drivers/cxl/core/region.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/cxl/core/region.c +1 -1
index e7206367ec66..472bd510b5e2 100644
@@ -397,7 +397,7 @@ static ssize_t interleave_ways_store(struct device *dev,
 		return rc;
 
 	/*
-	 * Even for x3, x9, and x12 interleaves the region interleave must be a
+	 * Even for x3, x6, and x12 interleaves the region interleave must be a
 	 * power of 2 multiple of the host bridge interleave.
 	 */
 	if (!is_power_of_2(val / cxld->interleave_ways) ||
Signature · 1 line
2.43.0
author maintainer
#514 lore raw

PATCH 508/583 apparmor: fix possible memory leak in unpack_trans_table

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Fedor Pchelkin <[email protected]>

[ Upstream commit 1342ad786073e96fa813ad943c19f586157ae297 ]

If we fail to unpack the transition table then the table elements which have been already allocated are not freed on error path.

unreferenced object 0xffff88802539e000 (size 128):
comm "apparmor_parser", pid 903, jiffies 4294914938 (age 35.085s) hex dump (first 32 bytes):

    20 73 6f 6d 65 20 6e 61 73 74 79 20 73 74 72 69   some nasty stri
    6e 67 20 73 6f 6d 65 20 6e 61 73 74 79 20 73 74  ng some nasty st
  backtrace:
    [<ffffffff81ddb312>] __kmem_cache_alloc_node+0x1e2/0x2d0
    [<ffffffff81c47194>] __kmalloc_node_track_caller+0x54/0x170
    [<ffffffff81c225b9>] kmemdup+0x29/0x60
    [<ffffffff83e1ee65>] aa_unpack_strdup+0xe5/0x1b0
    [<ffffffff83e20808>] unpack_pdb+0xeb8/0x2700
    [<ffffffff83e23567>] unpack_profile+0x1507/0x4a30
    [<ffffffff83e27bfa>] aa_unpack+0x36a/0x1560
    [<ffffffff83e194c3>] aa_replace_profiles+0x213/0x33c0
    [<ffffffff83de9461>] policy_update+0x261/0x370
    [<ffffffff83de978e>] profile_replace+0x20e/0x2a0
    [<ffffffff81eac8bf>] vfs_write+0x2af/0xe00
    [<ffffffff81eaddd6>] ksys_write+0x126/0x250
    [<ffffffff88f34fb6>] do_syscall_64+0x46/0xf0
    [<ffffffff890000ea>] entry_SYSCALL_64_after_hwframe+0x6e/0x76

Call aa_free_str_table() on error path as was done before the blamed commit. It implements all necessary checks, frees str_table if it is available and nullifies the pointers.

Found by Linux Verification Center (linuxtesting.org).

Fixes a0792e2ceddc ("apparmor: make transition table unpack generic so it can be reused")
---
 security/apparmor/lib.c           | 1 +
 security/apparmor/policy_unpack.c | 7 +++----
 2 files changed, 4 insertions(+), 4 deletions(-)
security/apparmor/lib.c +1 -0
index c87bccafff44..7182a8b821fb 100644
@@ -41,6 +41,7 @@ void aa_free_str_table(struct aa_str_table *t)
 			kfree_sensitive(t->table[i]);
 		kfree_sensitive(t->table);
 		t->table = NULL;
+		t->size = 0;
 	}
 }
 
security/apparmor/policy_unpack.c +3 -4
index dbc83455d900..a904bca24026 100644
@@ -478,6 +478,8 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 		if (!table)
 			goto fail;
 
+		strs->table = table;
+		strs->size = size;
 		for (i = 0; i < size; i++) {
 			char *str;
 			int c, j, pos, size2 = aa_unpack_strdup(e, &str, NULL);
@@ -520,14 +522,11 @@ static bool unpack_trans_table(struct aa_ext *e, struct aa_str_table *strs)
 			goto fail;
 		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
 			goto fail;
-
-		strs->table = table;
-		strs->size = size;
 	}
 	return true;
 
 fail:
-	kfree_sensitive(table);
+	aa_free_str_table(strs);
 	e->pos = saved_pos;
 	return false;
 }
Signature · 1 line
2.43.0
author maintainer
#515 lore raw

PATCH 509/583 apparmor: avoid crash when parsed profile name is empty

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Fedor Pchelkin <[email protected]>

[ Upstream commit 55a8210c9e7d21ff2644809699765796d4bfb200 ]

When processing a packed profile in unpack_profile() described like

"profile :ns::samba-dcerpcd /usr/lib*/samba/{,samba/}samba-dcerpcd {...}"

a string ":samba-dcerpcd" is unpacked as a fully-qualified name and then passed to aa_splitn_fqname().

aa_splitn_fqname() treats ":samba-dcerpcd" as only containing a namespace. Thus it returns NULL for tmpname, meanwhile tmpns is non-NULL. Later aa_alloc_profile() crashes as the new profile name is NULL now.

general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 6 PID: 1657 Comm: apparmor_parser Not tainted 6.7.0-rc2-dirty #16
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014
RIP: 0010:strlen+0x1e/0xa0
Call Trace:
 <TASK>
 ? strlen+0x1e/0xa0
 aa_policy_init+0x1bb/0x230
 aa_alloc_profile+0xb1/0x480
 unpack_profile+0x3bc/0x4960
 aa_unpack+0x309/0x15e0
 aa_replace_profiles+0x213/0x33c0
 policy_update+0x261/0x370
 profile_replace+0x20e/0x2a0
 vfs_write+0x2af/0xe00
 ksys_write+0x126/0x250
 do_syscall_64+0x46/0xf0
 entry_SYSCALL_64_after_hwframe+0x6e/0x76
 </TASK>
---[ end trace 0000000000000000 ]---
RIP: 0010:strlen+0x1e/0xa0

It seems such behaviour of aa_splitn_fqname() is expected and checked in other places where it is called (e.g. aa_remove_profiles). Well, there is an explicit comment "a ns name without a following profile is allowed" inside.

AFAICS, nothing can prevent unpacked "name" to be in form like ":samba-dcerpcd" - it is passed from userspace.

Deny the whole profile set replacement in such case and inform user with EPROTO and an explaining message.

Found by Linux Verification Center (linuxtesting.org).

Fixes 04dc715e24d0 ("apparmor: audit policy ns specified in policy load")
---
 security/apparmor/policy_unpack.c | 4 ++++
 1 file changed, 4 insertions(+)
security/apparmor/policy_unpack.c +4 -0
index a904bca24026..d92788da6704 100644
@@ -825,6 +825,10 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
 
 	tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
 	if (tmpns) {
+		if (!tmpname) {
+			info = "empty profile name";
+			goto fail;
+		}
 		*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
 		if (!*ns_name) {
 			info = "out of memory";
Signature · 1 line
2.43.0
author maintainer
#516 lore raw

PATCH 510/583 usb: xhci-mtk: fix a short packet issue of gen1 isoc-in transfer

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chunfeng Yun <[email protected]>

[ Upstream commit 017dbfc05c31284150819890b4cc86a699cbdb71 ]

For Gen1 isoc-in transfer, host still send out unexpected ACK after device finish the burst with a short packet, this will cause an exception on the connected device, such as, a usb 4k camera.
It can be fixed by setting rxfifo depth less than 4k bytes, prefer to use 3k here, the side-effect is that may cause performance drop about 10%, including bulk transfer.

Fixes 926d60ae64a6 ("usb: xhci-mtk: modify the SOF/ITP interval for mt8195")
---
 drivers/usb/host/xhci-mtk.c | 40 +++++++++++++++++++++++++++++++++++--
 drivers/usb/host/xhci-mtk.h |  2 ++
 2 files changed, 40 insertions(+), 2 deletions(-)
drivers/usb/host/xhci-mtk.c +38 -2
index bbdf1b0b7be1..3252e3d2d79c 100644
@@ -7,6 +7,7 @@
  *  Chunfeng Yun <[email protected]>
  */
 
+#include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
@@ -73,6 +74,9 @@
 #define FRMCNT_LEV1_RANG	(0x12b << 8)
 #define FRMCNT_LEV1_RANG_MASK	GENMASK(19, 8)
 
+#define HSCH_CFG1		0x960
+#define SCH3_RXFIFO_DEPTH_MASK	GENMASK(21, 20)
+
 #define SS_GEN2_EOF_CFG		0x990
 #define SSG2EOF_OFFSET		0x3c
 
@@ -114,6 +118,8 @@
 #define SSC_IP_SLEEP_EN	BIT(4)
 #define SSC_SPM_INT_EN		BIT(1)
 
+#define SCH_FIFO_TO_KB(x)	((x) >> 10)
+
 enum ssusb_uwk_vers {
 	SSUSB_UWK_V1 = 1,
 	SSUSB_UWK_V2,
@@ -165,6 +171,35 @@ static void xhci_mtk_set_frame_interval(struct xhci_hcd_mtk *mtk)
 	writel(value, hcd->regs + SS_GEN2_EOF_CFG);
 }
 
+/*
+ * workaround: usb3.2 gen1 isoc rx hw issue
+ * host send out unexpected ACK afer device fininsh a burst transfer with
+ * a short packet.
+ */
+static void xhci_mtk_rxfifo_depth_set(struct xhci_hcd_mtk *mtk)
+{
+	struct usb_hcd *hcd = mtk->hcd;
+	u32 value;
+
+	if (!mtk->rxfifo_depth)
+		return;
+
+	value = readl(hcd->regs + HSCH_CFG1);
+	value &= ~SCH3_RXFIFO_DEPTH_MASK;
+	value |= FIELD_PREP(SCH3_RXFIFO_DEPTH_MASK,
+			    SCH_FIFO_TO_KB(mtk->rxfifo_depth) - 1);
+	writel(value, hcd->regs + HSCH_CFG1);
+}
+
+static void xhci_mtk_init_quirk(struct xhci_hcd_mtk *mtk)
+{
+	/* workaround only for mt8195 */
+	xhci_mtk_set_frame_interval(mtk);
+
+	/* workaround for SoCs using SSUSB about before IPM v1.6.0 */
+	xhci_mtk_rxfifo_depth_set(mtk);
+}
+
 static int xhci_mtk_host_enable(struct xhci_hcd_mtk *mtk)
 {
 	struct mu3c_ippc_regs __iomem *ippc = mtk->ippc_regs;
@@ -448,8 +483,7 @@ static int xhci_mtk_setup(struct usb_hcd *hcd)
 		if (ret)
 			return ret;
 
-		/* workaround only for mt8195 */
-		xhci_mtk_set_frame_interval(mtk);
+		xhci_mtk_init_quirk(mtk);
 	}
 
 	ret = xhci_gen_setup(hcd, xhci_mtk_quirks);
@@ -527,6 +561,8 @@ static int xhci_mtk_probe(struct platform_device *pdev)
 	of_property_read_u32(node, "mediatek,u2p-dis-msk",
 			     &mtk->u2p_dis_msk);
 
+	of_property_read_u32(node, "rx-fifo-depth", &mtk->rxfifo_depth);
+
 	ret = usb_wakeup_of_property_parse(mtk, node);
 	if (ret) {
 		dev_err(dev, "failed to parse uwk property\n");
drivers/usb/host/xhci-mtk.h +2 -0
index faaaf05e36ce..ac042077db8c 100644
@@ -160,6 +160,8 @@ struct xhci_hcd_mtk {
 	struct regmap *uwk;
 	u32 uwk_reg_base;
 	u32 uwk_vers;
+	/* quirk */
+	u32 rxfifo_depth;
 };
 
 static inline struct xhci_hcd_mtk *hcd_to_mtk(struct usb_hcd *hcd)
Signature · 1 line
2.43.0
author maintainer
#517 lore raw

PATCH 511/583 serial: imx: Correct clock error message in function probe()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Niedermaier <[email protected]>

[ Upstream commit 3e189470cad27d41a3a9dc02649f965b7ed1c90f ]

Correct the clock error message by changing the clock name.

---
 drivers/tty/serial/imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/imx.c +1 -1
index c084ac3bb441..cd36251ba1c0 100644
@@ -2323,7 +2323,7 @@ static int imx_uart_probe(struct platform_device *pdev)
 	/* For register access, we only need to enable the ipg clock. */
 	ret = clk_prepare_enable(sport->clk_ipg);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to enable per clk: %d\n", ret);
+		dev_err(&pdev->dev, "failed to enable ipg clk: %d\n", ret);
 		return ret;
 	}
 
Signature · 1 line
2.43.0
author maintainer
#518 lore raw

PATCH 512/583 serial: apbuart: fix console prompt on qemu

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sam Ravnborg <[email protected]>

[ Upstream commit c6dcd8050fb7c2efec6946ae9c49bc186b0a7475 ]

When using a leon kernel with qemu there where no console prompt. The root cause is the handling of the fifo size in the tx part of the apbuart driver.

The qemu uart driver only have a very rudimentary status handling and do not report the number of chars queued in the tx fifo in the status register. So the driver ends up with a fifo size of 1.

In the tx path the fifo size is divided by 2 - resulting in a fifo size of zero.

The original implementation would always try to send one char, but after the introduction of uart_port_tx_limited() the fifo size is respected even for the first char.

There seems to be no good reason to divide the fifo size with two - so remove this. It looks like something copied from the original amba driver.

With qemu we now have a minimum fifo size of one char, so we show the prompt.

Fixes d11cc8c3c4b6 ("tty: serial: use uart_port_tx_limited()")
Cc Andreas Larsson <[email protected]>
Cc Greg Kroah-Hartman <[email protected]>
Cc Jiri Slaby <[email protected]>
---
 drivers/tty/serial/apbuart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/apbuart.c +1 -1
index d7658f380838..d3cb341f2c55 100644
@@ -122,7 +122,7 @@ static void apbuart_tx_chars(struct uart_port *port)
 {
 	u8 ch;
 
-	uart_port_tx_limited(port, ch, port->fifosize >> 1,
+	uart_port_tx_limited(port, ch, port->fifosize,
 		true,
 		UART_PUT_CHAR(port, ch),
 		({}));
Signature · 1 line
2.43.0
author maintainer
#519 lore raw

PATCH 513/583 perf db-export: Fix missing reference count get in call_path_from_sample()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ben Gainey <[email protected]>

[ Upstream commit 1e24ce402c97dc3c0ab050593f1d5f6fde524564 ]

The addr_location map and maps fields in the inner loop were missing calls to map__get()/maps__get(). The subsequent addr_location__exit() call in each loop puts the map/maps fields causing use-after-free aborts.

This issue reproduces on at least arm64 and x86_64 with something simple like perf record -g ls followed by perf script -s script.py with the following script:

perf_db_export_mode = True
perf_db_export_calls = False
perf_db_export_callchains = True

def sample_table(*args):
print(f'sample_table({args})')

def call_path_table(*args):
print(f'call_path_table({args}')

Committer testing:

This test, just introduced by Ian Rogers, now passes, not segfaulting anymore:

  # perf test "perf script tests"
   95: perf script tests                                               : Ok
  #
Fixes 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/db-export.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/perf/util/db-export.c +2 -2
index b9fb71ab7a73..106429155c2e 100644
@@ -253,8 +253,8 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		 */
 		addr_location__init(&al);
 		al.sym = node->ms.sym;
-		al.map = node->ms.map;
-		al.maps = thread__maps(thread);
+		al.map = map__get(node->ms.map);
+		al.maps = maps__get(thread__maps(thread));
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
Signature · 1 line
2.43.0
author maintainer
#520 lore raw

PATCH 514/583 cxl/port: Fix missing target list lock

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dan Williams <[email protected]>

[ Upstream commit 5459e186a5c9f412334321cff58d70dcb0e48a04 ]

cxl_port_setup_targets() modifies the ->targets[] array of a switch decoder. target_list_show() expects to be able to emit a coherent snapshot of that array by "holding" ->target_lock for read. The target_lock is held for write during initialization of the ->targets[] array, but it is not held for write during cxl_port_setup_targets().

The ->target_lock() predates the introduction of @cxl_region_rwsem. That semaphore protects changes to host-physical-address (HPA) decode which is precisely what writes to a switch decoder's target list affects.

Replace ->target_lock with @cxl_region_rwsem.

Now the side-effect of snapshotting a unstable view of a decoder's target list is likely benign so the Fixes: tag is presumptive.

Fixes 27b3f8d13830 ("cxl/region: Program target lists")
---
 drivers/cxl/core/port.c | 22 +++++++---------------
 drivers/cxl/cxl.h       |  2 --
 2 files changed, 7 insertions(+), 17 deletions(-)
drivers/cxl/core/port.c +7 -15
index 4081052bb385..c67cc8c9d5cc 100644
@@ -172,14 +172,10 @@ static ssize_t target_list_show(struct device *dev,
 {
 	struct cxl_switch_decoder *cxlsd = to_cxl_switch_decoder(dev);
 	ssize_t offset;
-	unsigned int seq;
 	int rc;
 
-	do {
-		seq = read_seqbegin(&cxlsd->target_lock);
-		rc = emit_target_list(cxlsd, buf);
-	} while (read_seqretry(&cxlsd->target_lock, seq));
-
+	guard(rwsem_read)(&cxl_region_rwsem);
+	rc = emit_target_list(cxlsd, buf);
 	if (rc < 0)
 		return rc;
 	offset = rc;
@@ -1579,7 +1575,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_find_port, CXL);
 static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 				    struct cxl_port *port, int *target_map)
 {
-	int i, rc = 0;
+	int i;
 
 	if (!target_map)
 		return 0;
@@ -1589,19 +1585,16 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 	if (xa_empty(&port->dports))
 		return -EINVAL;
 
-	write_seqlock(&cxlsd->target_lock);
+	guard(rwsem_write)(&cxl_region_rwsem);
 	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
 		struct cxl_dport *dport = find_dport(port, target_map[i]);
 
-		if (!dport) {
-			rc = -ENXIO;
-			break;
-		}
+		if (!dport)
+			return -ENXIO;
 		cxlsd->target[i] = dport;
 	}
-	write_sequnlock(&cxlsd->target_lock);
 
-	return rc;
+	return 0;
 }
 
 struct cxl_dport *cxl_hb_modulo(struct cxl_root_decoder *cxlrd, int pos)
@@ -1671,7 +1664,6 @@ static int cxl_switch_decoder_init(struct cxl_port *port,
 		return -EINVAL;
 
 	cxlsd->nr_targets = nr_targets;
-	seqlock_init(&cxlsd->target_lock);
 	return cxl_decoder_init(port, &cxlsd->cxld);
 }
 
drivers/cxl/cxl.h +0 -2
index 6c6afda0e4c6..de2c250c894b 100644
@@ -404,7 +404,6 @@ struct cxl_endpoint_decoder {
 /**
  * struct cxl_switch_decoder - Switch specific CXL HDM Decoder
  * @cxld: base cxl_decoder object
- * @target_lock: coordinate coherent reads of the target list
  * @nr_targets: number of elements in @target
  * @target: active ordered target list in current decoder configuration
  *
@@ -416,7 +415,6 @@ struct cxl_endpoint_decoder {
  */
 struct cxl_switch_decoder {
 	struct cxl_decoder cxld;
-	seqlock_t target_lock;
 	int nr_targets;
 	struct cxl_dport *target[];
 };
Signature · 1 line
2.43.0
author maintainer
#521 lore raw

PATCH 515/583 spi: coldfire-qspi: Remove an erroneous clk_disable_unprepare() from the remove function

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit 17dc11a02d8dacc7e78968daa2a8c16281eb7d1e ]

The commit in Fixes has changed a devm_clk_get()/clk_prepare_enable() into a devm_clk_get_enabled().
It has updated the error handling path of the probe accordingly, but the remove has been left unchanged.

Remove now the redundant clk_disable_unprepare() call from the remove function.

---
 drivers/spi/spi-coldfire-qspi.c | 1 -
 1 file changed, 1 deletion(-)
drivers/spi/spi-coldfire-qspi.c +0 -1
index f0b630fe16c3..b341b6908df0 100644
@@ -441,7 +441,6 @@ static void mcfqspi_remove(struct platform_device *pdev)
 	mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR);
 
 	mcfqspi_cs_teardown(mcfqspi);
-	clk_disable_unprepare(mcfqspi->clk);
 }
 
 #ifdef CONFIG_PM_SLEEP
Signature · 1 line
2.43.0
author maintainer
#522 lore raw

PATCH 516/583 hisi_acc_vfio_pci: Update migration data pointer correctly on saving/resume

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shameer Kolothum <[email protected]>

[ Upstream commit be12ad45e15b5ee0e2526a50266ba1d295d26a88 ]

When the optional PRE_COPY support was added to speed up the device compatibility check, it failed to update the saving/resuming data pointers based on the fd offset. This results in migration data corruption and when the device gets started on the destination the following error is reported in some cases,

[  478.907684] arm-smmu-v3 arm-smmu-v3.2.auto: event 0x10 received:
[  478.913691] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000310200000010
[  478.919603] arm-smmu-v3 arm-smmu-v3.2.auto:  0x000002088000007f
[  478.925515] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000000000000000
[  478.931425] arm-smmu-v3 arm-smmu-v3.2.auto:  0x0000000000000000
[  478.947552] hisi_zip 0000:31:00.0: qm_axi_rresp [error status=0x1] found
[  478.955930] hisi_zip 0000:31:00.0: qm_db_timeout [error status=0x400] found
[  478.955944] hisi_zip 0000:31:00.0: qm sq doorbell timeout in function 2
Fixes d9a871e4a143 ("hisi_acc_vfio_pci: Introduce support for PRE_COPY state transitions")
---
 drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +5 -2
index b2f9778c8366..4d27465c8f1a 100644
@@ -694,6 +694,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 					size_t len, loff_t *pos)
 {
 	struct hisi_acc_vf_migration_file *migf = filp->private_data;
+	u8 *vf_data = (u8 *)&migf->vf_data;
 	loff_t requested_length;
 	ssize_t done = 0;
 	int ret;
@@ -715,7 +716,7 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 		goto out_unlock;
 	}
 
-	ret = copy_from_user(&migf->vf_data, buf, len);
+	ret = copy_from_user(vf_data + *pos, buf, len);
 	if (ret) {
 		done = -EFAULT;
 		goto out_unlock;
@@ -835,7 +836,9 @@ static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t
 
 	len = min_t(size_t, migf->total_length - *pos, len);
 	if (len) {
-		ret = copy_to_user(buf, &migf->vf_data, len);
+		u8 *vf_data = (u8 *)&migf->vf_data;
+
+		ret = copy_to_user(buf, vf_data + *pos, len);
 		if (ret) {
 			done = -EFAULT;
 			goto out_unlock;
Signature · 1 line
2.43.0
author maintainer
#523 lore raw

PATCH 517/583 nvmet: re-fix tracing strncpy() warning

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit 4ee7ffeb4ce50c80bc4504db6f39b25a2df6bcf4 ]

An earlier patch had tried to address a warning about a string copy with missing zero termination:

drivers/nvme/target/trace.h:52:3: warning: ‘strncpy’ specified bound 32 equals destination size [-Wstringop-truncation]

The new version causes a different warning with some compiler versions, notably gcc-9 and gcc-10, and also misses the zero padding that was apparently done intentionally in the original code:

drivers/nvme/target/trace.h:56:2: error: 'strncpy' specified bound depends on the length of the source argument [-Werror=stringop-overflow=]

Change it to use strscpy_pad() with the original length, which will give a properly padded and zero-terminated string as well as avoiding the warning.

Fixes d86481e924a7 ("nvmet: use min of device_path and disk len")
---
 drivers/nvme/target/trace.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/nvme/target/trace.h +1 -2
index 6109b3806b12..155334ddc13f 100644
@@ -53,8 +53,7 @@ static inline void __assign_req_name(char *name, struct nvmet_req *req)
 		return;
 	}
 
-	strncpy(name, req->ns->device_path,
-		min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path)));
+	strscpy_pad(name, req->ns->device_path, DISK_NAME_LEN);
 }
 #endif
 
Signature · 1 line
2.43.0
author maintainer
#524 lore raw

PATCH 518/583 nvme: trace: avoid memcpy overflow warning

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit a7de1dea76cd6a3707707af4ea2f8bc3cdeaeb11 ]

A previous patch introduced a struct_group() in nvme_common_command to help stringop fortification figure out the length of the fields, but one function is not currently using them:

In file included from drivers/nvme/target/core.c:7:
In file included from include/linux/string.h:254:
include/linux/fortify-string.h:592:4: error: call to '__read_overflow2_field' declared with 'warning' attribute: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]

                        __read_overflow2_field(q_size_field, size);
                        ^

Change this one to use the correct field name to avoid the warning.

Fixes 5c629dc9609dc ("nvme: use struct group for generic command dwords")
---
 drivers/nvme/target/trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/nvme/target/trace.h +1 -1
index 155334ddc13f..974d99d47f51 100644
@@ -84,7 +84,7 @@ TRACE_EVENT(nvmet_req_init,
 		__entry->flags = cmd->common.flags;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
-		memcpy(__entry->cdw10, &cmd->common.cdw10,
+		memcpy(__entry->cdw10, &cmd->common.cdws,
 			sizeof(__entry->cdw10));
 	),
 	TP_printk("nvmet%s: %sqid=%d, cmdid=%u, nsid=%u, flags=%#x, "
Signature · 1 line
2.43.0
author maintainer
#525 lore raw

PATCH 519/583 nvmet-tcp: Fix the H2C expected PDU len calculation

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Maurizio Lombardi <[email protected]>

[ Upstream commit 9a1abc24850eb759e36a2f8869161c3b7254c904 ]

The nvmet_tcp_handle_h2c_data_pdu() function should take into consideration the possibility that the header digest and/or the data digests are enabled when calculating the expected PDU length, before comparing it to the value stored in cmd->pdu_len.

Fixes efa56305908b ("nvmet-tcp: Fix a kernel panic when host sends an invalid H2C PDU length")
---
 drivers/nvme/target/tcp.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
drivers/nvme/target/tcp.c +7 -3
index 7f7fa78f0698..a4f802790ca0 100644
@@ -954,7 +954,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 {
 	struct nvme_tcp_data_pdu *data = &queue->pdu.data;
 	struct nvmet_tcp_cmd *cmd;
-	unsigned int plen;
+	unsigned int exp_data_len;
 
 	if (likely(queue->nr_cmds)) {
 		if (unlikely(data->ttag >= queue->nr_cmds)) {
@@ -977,9 +977,13 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue)
 		return -EPROTO;
 	}
 
-	plen = le32_to_cpu(data->hdr.plen);
+	exp_data_len = le32_to_cpu(data->hdr.plen) -
+			nvmet_tcp_hdgst_len(queue) -
+			nvmet_tcp_ddgst_len(queue) -
+			sizeof(*data);
+
 	cmd->pdu_len = le32_to_cpu(data->data_length);
-	if (unlikely(cmd->pdu_len != (plen - sizeof(*data)) ||
+	if (unlikely(cmd->pdu_len != exp_data_len ||
 		     cmd->pdu_len == 0 ||
 		     cmd->pdu_len > NVMET_TCP_MAXH2CDATA)) {
 		pr_err("H2CData PDU len %u is invalid\n", cmd->pdu_len);
Signature · 1 line
2.43.0
author maintainer
#526 lore raw

PATCH 520/583 PCI: keystone: Fix race condition when initializing PHYs

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Siddharth Vadapalli <[email protected]>

[ Upstream commit c12ca110c613a81cb0f0099019c839d078cd0f38 ]

The PCI driver invokes the PHY APIs using the ks_pcie_enable_phy() function. The PHY in this case is the Serdes. It is possible that the PCI instance is configured for two lane operation across two different Serdes instances, using one lane of each Serdes.

In such a configuration, if the reference clock for one Serdes is provided by the other Serdes, it results in a race condition. After the Serdes providing the reference clock is initialized by the PCI driver by invoking its PHY APIs, it is not guaranteed that this Serdes remains powered on long enough for the PHY APIs based initialization of the dependent Serdes. In such cases, the PLL of the dependent Serdes fails to lock due to the absence of the reference clock from the former Serdes which has been powered off by the PM Core.

Fix this by obtaining reference to the PHYs before invoking the PHY initialization APIs and releasing reference after the initialization is complete.

---
 drivers/pci/controller/dwc/pci-keystone.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/pci/controller/dwc/pci-keystone.c +9 -0
index 0def919f89fa..cf3836561316 100644
@@ -1218,7 +1218,16 @@ static int ks_pcie_probe(struct platform_device *pdev)
 		goto err_link;
 	}
 
+	/* Obtain references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_get_sync(ks_pcie->phy[i]);
+
 	ret = ks_pcie_enable_phy(ks_pcie);
+
+	/* Release references to the PHYs */
+	for (i = 0; i < num_lanes; i++)
+		phy_pm_runtime_put_sync(ks_pcie->phy[i]);
+
 	if (ret) {
 		dev_err(dev, "failed to enable phy\n");
 		goto err_link;
Signature · 1 line
2.43.0
author maintainer
#527 lore raw

PATCH 521/583 PCI: mediatek-gen3: Fix translation window size calculation

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jianjun Wang <[email protected]>

[ Upstream commit 9ccc1318cf4bd90601f221268e42c3374703d681 ]

When using the fls() helper, the translation table should be a power of two; otherwise, the resulting value will not be correct.

For example, given fls(0x3e00000) - 1 = 25, the PCIe translation window size will be set to 0x2000000 instead of the expected size 0x3e00000.

Fix the translation window by splitting the MMIO space into multiple tables if its size is not a power of two.

[kwilczynski: commit log]
Fixes d3bf75b579b9 ("PCI: mediatek-gen3: Add MediaTek Gen3 driver for MT8192")
---
 drivers/pci/controller/pcie-mediatek-gen3.c | 85 ++++++++++++---------
 1 file changed, 50 insertions(+), 35 deletions(-)
drivers/pci/controller/pcie-mediatek-gen3.c +50 -35
index e0e27645fdf4..975b3024fb08 100644
@@ -245,35 +245,60 @@ static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie,
 				    resource_size_t cpu_addr,
 				    resource_size_t pci_addr,
 				    resource_size_t size,
-				    unsigned long type, int num)
+				    unsigned long type, int *num)
 {
+	resource_size_t remaining = size;
+	resource_size_t table_size;
+	resource_size_t addr_align;
+	const char *range_type;
 	void __iomem *table;
 	u32 val;
 
-	if (num >= PCIE_MAX_TRANS_TABLES) {
-		dev_err(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
-			(unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
-		return -ENODEV;
-	}
+	while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) {
+		/* Table size needs to be a power of 2 */
+		table_size = BIT(fls(remaining) - 1);
+
+		if (cpu_addr > 0) {
+			addr_align = BIT(ffs(cpu_addr) - 1);
+			table_size = min(table_size, addr_align);
+		}
+
+		/* Minimum size of translate table is 4KiB */
+		if (table_size < 0x1000) {
+			dev_err(pcie->dev, "illegal table size %#llx\n",
+				(unsigned long long)table_size);
+			return -EINVAL;
+		}
 
-	table = pcie->base + PCIE_TRANS_TABLE_BASE_REG +
-		num * PCIE_ATR_TLB_SET_OFFSET;
+		table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET;
+		writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table);
+		writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
+		writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
+		writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
 
-	writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1),
-		       table);
-	writel_relaxed(upper_32_bits(cpu_addr),
-		       table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
-	writel_relaxed(lower_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
-	writel_relaxed(upper_32_bits(pci_addr),
-		       table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
+		if (type == IORESOURCE_IO) {
+			val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
+			range_type = "IO";
+		} else {
+			val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+			range_type = "MEM";
+		}
 
-	if (type == IORESOURCE_IO)
-		val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
-	else
-		val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+		writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
 
-	writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
+		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
+			range_type, *num, (unsigned long long)cpu_addr,
+			(unsigned long long)pci_addr, (unsigned long long)table_size);
+
+		cpu_addr += table_size;
+		pci_addr += table_size;
+		remaining -= table_size;
+		(*num)++;
+	}
+
+	if (remaining)
+		dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
+			 (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
 
 	return 0;
 }
@@ -380,30 +405,20 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 		resource_size_t cpu_addr;
 		resource_size_t pci_addr;
 		resource_size_t size;
-		const char *range_type;
 
-		if (type == IORESOURCE_IO) {
+		if (type == IORESOURCE_IO)
 			cpu_addr = pci_pio_to_address(res->start);
-			range_type = "IO";
-		} else if (type == IORESOURCE_MEM) {
+		else if (type == IORESOURCE_MEM)
 			cpu_addr = res->start;
-			range_type = "MEM";
-		} else {
+		else
 			continue;
-		}
 
 		pci_addr = res->start - entry->offset;
 		size = resource_size(res);
 		err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size,
-					       type, table_index);
+					       type, &table_index);
 		if (err)
 			return err;
-
-		dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
-			range_type, table_index, (unsigned long long)cpu_addr,
-			(unsigned long long)pci_addr, (unsigned long long)size);
-
-		table_index++;
 	}
 
 	return 0;
Signature · 1 line
2.43.0
author maintainer
#528 lore raw

PATCH 522/583 ASoC: mediatek: sof-common: Add NULL check for normal_link string

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: AngeloGioacchino Del Regno <[email protected]>

[ Upstream commit e3b3ec967a7d93b9010a5af9a2394c8b5c8f31ed ]

It's not granted that all entries of struct sof_conn_stream declare a normal_link (a non-SOF, direct link) string, and this is the case for SoCs that support only SOF paths (hence do not support both direct and SOF usecases).

For example, in the case of MT8188 there is no normal_link string in any of the sof_conn_stream entries and there will be more drivers doing that in the future.

To avoid possible NULL pointer KPs, add a NULL check for normal_link.

Fixes 0caf1120c583 ("ASoC: mediatek: mt8195: extract SOF common code")
---
 sound/soc/mediatek/common/mtk-dsp-sof-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/soc/mediatek/common/mtk-dsp-sof-common.c +1 -1
index 6fef16306f74..21a9403b7e92 100644
@@ -24,7 +24,7 @@ int mtk_sof_dai_link_fixup(struct snd_soc_pcm_runtime *rtd,
 		struct snd_soc_dai_link *sof_dai_link = NULL;
 		const struct sof_conn_stream *conn = &sof_priv->conn_streams[i];
 
-		if (strcmp(rtd->dai_link->name, conn->normal_link))
+		if (conn->normal_link && strcmp(rtd->dai_link->name, conn->normal_link))
 			continue;
 
 		for_each_card_rtds(card, runtime) {
Signature · 1 line
2.43.0
author maintainer
#529 lore raw

PATCH 523/583 s390/pci: fix max size calculation in zpci_memcpy_toio()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Niklas Schnelle <[email protected]>

[ Upstream commit 80df7d6af7f6d229b34cf237b2cc9024c07111cd ]

The zpci_get_max_write_size() helper is used to determine the maximum size a PCI store or load can use at a given __iomem address.

For the PCI block store the following restrictions apply:

1. The dst + len must not cross a 4K boundary in the (pseudo-)MMIO space
2. len must not exceed ZPCI_MAX_WRITE_SIZE
3. len must be a multiple of 8 bytes
4. The src address must be double word (8 byte) aligned
5. The dst address must be double word (8 byte) aligned

Otherwise only a normal PCI store which takes its src value from a register can be used. For these PCI store restriction 1 still applies. Similarly 1 also applies to PCI loads.

It turns out zpci_max_write_size() instead implements stricter conditions which prevents PCI block stores from being used where they can and should be used. In particular instead of conditions 4 and 5 it wrongly enforces both dst and src to be size aligned. This indirectly covers condition 1 but also prevents many legal PCI block stores.

On top of the functional shortcomings the zpci_get_max_write_size() is misnamed as it is used for both read and write size calculations. Rename it to zpci_get_max_io_size() and implement the listed conditions explicitly.

Fixes cd24834130ac ("s390/pci: base support")
[[email protected] replaced spaces with tabs]
---
 arch/s390/include/asm/pci_io.h | 32 ++++++++++++++++++--------------
 arch/s390/pci/pci_mmio.c       | 12 ++++++------
 2 files changed, 24 insertions(+), 20 deletions(-)
arch/s390/include/asm/pci_io.h +18 -14
index 287bb88f7698..2686bee800e3 100644
@@ -11,6 +11,8 @@
 /* I/O size constraints */
 #define ZPCI_MAX_READ_SIZE	8
 #define ZPCI_MAX_WRITE_SIZE	128
+#define ZPCI_BOUNDARY_SIZE	(1 << 12)
+#define ZPCI_BOUNDARY_MASK	(ZPCI_BOUNDARY_SIZE - 1)
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
@@ -125,16 +127,18 @@ static inline int zpci_read_single(void *dst, const volatile void __iomem *src,
 int zpci_write_block(volatile void __iomem *dst, const void *src,
 		     unsigned long len);
 
-static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
+static inline int zpci_get_max_io_size(u64 src, u64 dst, int len, int max)
 {
-	int count = len > max ? max : len, size = 1;
+	int offset = dst & ZPCI_BOUNDARY_MASK;
+	int size;
 
-	while (!(src & 0x1) && !(dst & 0x1) && ((size << 1) <= count)) {
-		dst = dst >> 1;
-		src = src >> 1;
-		size = size << 1;
-	}
-	return size;
+	size = min3(len, ZPCI_BOUNDARY_SIZE - offset, max);
+	if (IS_ALIGNED(src, 8) && IS_ALIGNED(dst, 8) && IS_ALIGNED(size, 8))
+		return size;
+
+	if (size >= 8)
+		return 8;
+	return rounddown_pow_of_two(size);
 }
 
 static inline int zpci_memcpy_fromio(void *dst,
@@ -144,9 +148,9 @@ static inline int zpci_memcpy_fromio(void *dst,
 	int size, rc = 0;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
@@ -166,9 +170,9 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = zpci_write_block(dst, src, size);
 		else
arch/s390/pci/pci_mmio.c +6 -6
index 588089332931..a90499c087f0 100644
@@ -97,9 +97,9 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
 		return -EINVAL;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) dst,
-					       (u64 __force) src, n,
-					       ZPCI_MAX_WRITE_SIZE);
+		size = zpci_get_max_io_size((u64 __force) dst,
+					    (u64 __force) src, n,
+					    ZPCI_MAX_WRITE_SIZE);
 		if (size > 8) /* main path */
 			rc = __pcistb_mio_inuser(dst, src, size, &status);
 		else
@@ -242,9 +242,9 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
 	u8 status;
 
 	while (n > 0) {
-		size = zpci_get_max_write_size((u64 __force) src,
-					       (u64 __force) dst, n,
-					       ZPCI_MAX_READ_SIZE);
+		size = zpci_get_max_io_size((u64 __force) src,
+					    (u64 __force) dst, n,
+					    ZPCI_MAX_READ_SIZE);
 		rc = __pcilg_mio_inuser(dst, src, size, &status);
 		if (rc)
 			break;
Signature · 1 line
2.43.0
author maintainer
#530 lore raw

PATCH 524/583 net: qualcomm: rmnet: fix global oob in rmnet_policy

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Lin Ma <[email protected]>

[ Upstream commit b33fb5b801c6db408b774a68e7c8722796b59ecc ]

The variable rmnet_link_ops assign a *bigger* maxtype which leads to a global out-of-bounds read when parsing the netlink attributes. See bug trace below:

==================================================================

BUG: KASAN: global-out-of-bounds in validate_nla lib/nlattr.c:386 [inline]
BUG: KASAN: global-out-of-bounds in __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
Read of size 1 at addr ffffffff92c438d0 by task syz-executor.6/84207

CPU: 0 PID: 84207 Comm: syz-executor.6 Tainted: G                 N 6.1.0 #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x8b/0xb3 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:284 [inline]
 print_report+0x172/0x475 mm/kasan/report.c:395
 kasan_report+0xbb/0x1c0 mm/kasan/report.c:495
 validate_nla lib/nlattr.c:386 [inline]
 __nla_validate_parse+0x24af/0x2750 lib/nlattr.c:600
 __nla_parse+0x3e/0x50 lib/nlattr.c:697
 nla_parse_nested_deprecated include/net/netlink.h:1248 [inline]
 __rtnl_newlink+0x50a/0x1880 net/core/rtnetlink.c:3485
 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3594
 rtnetlink_rcv_msg+0x43c/0xd70 net/core/rtnetlink.c:6091
 netlink_rcv_skb+0x14f/0x410 net/netlink/af_netlink.c:2540
 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
 netlink_unicast+0x54e/0x800 net/netlink/af_netlink.c:1345
 netlink_sendmsg+0x930/0xe50 net/netlink/af_netlink.c:1921
 sock_sendmsg_nosec net/socket.c:714 [inline]
 sock_sendmsg+0x154/0x190 net/socket.c:734
 ____sys_sendmsg+0x6df/0x840 net/socket.c:2482
 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536
 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fdcf2072359
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 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:00007fdcf13e3168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007fdcf219ff80 RCX: 00007fdcf2072359
RDX: 0000000000000000 RSI: 0000000020000200 RDI: 0000000000000003
RBP: 00007fdcf20bd493 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fffbb8d7bdf R14: 00007fdcf13e3300 R15: 0000000000022000
 </TASK>

The buggy address belongs to the variable:
 rmnet_policy+0x30/0xe0

The buggy address belongs to the physical page:
page:0000000065bdeb3c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x155243
flags: 0x200000000001000(reserved|node=0|zone=2)
raw: 0200000000001000 ffffea00055490c8 ffffea00055490c8 0000000000000000
raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffffffff92c43780: f9 f9 f9 f9 00 00 00 02 f9 f9 f9 f9 00 00 00 07
 ffffffff92c43800: f9 f9 f9 f9 00 00 00 05 f9 f9 f9 f9 06 f9 f9 f9
>ffffffff92c43880: f9 f9 f9 f9 00 00 00 00 00 00 f9 f9 f9 f9 f9 f9
                                                 ^
 ffffffff92c43900: 00 00 00 00 00 00 00 00 07 f9 f9 f9 f9 f9 f9 f9
 ffffffff92c43980: 00 00 00 07 f9 f9 f9 f9 00 00 00 05 f9 f9 f9 f9

According to the comment of nla_parse_nested_deprecated, the maxtype should be len(destination array) - 1. Hence use IFLA_RMNET_MAX here.

---
 drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +1 -1
index 39d24e07f306..5b69b9268c75 100644
@@ -396,7 +396,7 @@ static int rmnet_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 struct rtnl_link_ops rmnet_link_ops __read_mostly = {
 	.kind		= "rmnet",
-	.maxtype	= __IFLA_RMNET_MAX,
+	.maxtype	= IFLA_RMNET_MAX,
 	.priv_size	= sizeof(struct rmnet_priv),
 	.setup		= rmnet_vnd_setup,
 	.validate	= rmnet_rtnl_validate,
Signature · 1 line
2.43.0
author maintainer
#531 lore raw

PATCH 525/583 rxrpc: Fix use of Dont Fragment flag

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Howells <[email protected]>

[ Upstream commit 8722014311e613244f33952354956a82fa4b0472 ]

rxrpc normally has the Don't Fragment flag set on the UDP packets it transmits, except when it has decided that DATA packets aren't getting through - in which case it turns it off just for the DATA transmissions. This can be a problem, however, for RESPONSE packets that convey authentication and crypto data from the client to the server as ticket may be larger than can fit in the MTU.

In such a case, rxrpc gets itself into an infinite loop as the sendmsg returns an error (EMSGSIZE), which causes rxkad_send_response() to return -EAGAIN - and the CHALLENGE packet is put back on the Rx queue to retry, leading to the I/O thread endlessly attempting to perform the transmission.

Fix this by disabling DF on RESPONSE packets for now. The use of DF and best data MTU determination needs reconsidering at some point in the future.

Fixes 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
---
 net/rxrpc/ar-internal.h  |  1 +
 net/rxrpc/local_object.c | 13 ++++++++++++-
 net/rxrpc/output.c       |  6 ++----
 net/rxrpc/rxkad.c        |  2 ++
 4 files changed, 17 insertions(+), 5 deletions(-)
net/rxrpc/ar-internal.h +1 -0
index e8e14c6f904d..e8b43408136a 100644
@@ -1076,6 +1076,7 @@ void rxrpc_send_version_request(struct rxrpc_local *local,
 /*
  * local_object.c
  */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set);
 struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *);
 struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace);
 struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace);
net/rxrpc/local_object.c +12 -1
index c553a30e9c83..34d307368135 100644
@@ -36,6 +36,17 @@ static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err,
 		return ipv6_icmp_error(sk, skb, err, port, info, payload);
 }
 
+/*
+ * Set or clear the Don't Fragment flag on a socket.
+ */
+void rxrpc_local_dont_fragment(const struct rxrpc_local *local, bool set)
+{
+	if (set)
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DO);
+	else
+		ip_sock_set_mtu_discover(local->socket->sk, IP_PMTUDISC_DONT);
+}
+
 /*
  * Compare a local to an address.  Return -ve, 0 or +ve to indicate less than,
  * same or greater than.
@@ -203,7 +214,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
 		ip_sock_set_recverr(usk);
 
 		/* we want to set the don't fragment bit */
-		ip_sock_set_mtu_discover(usk, IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(local, true);
 
 		/* We want receive timestamps. */
 		sock_enable_timestamps(usk);
net/rxrpc/output.c +2 -4
index 5e53429c6922..a0906145e829 100644
@@ -494,14 +494,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
 	switch (conn->local->srx.transport.family) {
 	case AF_INET6:
 	case AF_INET:
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DONT);
+		rxrpc_local_dont_fragment(conn->local, false);
 		rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag);
 		ret = do_udp_sendmsg(conn->local->socket, &msg, len);
 		conn->peer->last_tx_at = ktime_get_seconds();
 
-		ip_sock_set_mtu_discover(conn->local->socket->sk,
-					 IP_PMTUDISC_DO);
+		rxrpc_local_dont_fragment(conn->local, true);
 		break;
 
 	default:
net/rxrpc/rxkad.c +2 -0
index 1bf571a66e02..b52dedcebce0 100644
@@ -724,7 +724,9 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 	serial = atomic_inc_return(&conn->serial);
 	whdr.serial = htonl(serial);
 
+	rxrpc_local_dont_fragment(conn->local, false);
 	ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len);
+	rxrpc_local_dont_fragment(conn->local, true);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
 				    rxrpc_tx_point_rxkad_response);
Signature · 1 line
2.43.0
author maintainer
#532 lore raw

PATCH 526/583 octeontx2-af: CN10KB: Fix FIFO length calculation for RPM2

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nithin Dabilpuram <[email protected]>

[ Upstream commit a0cb76a770083a22167659e64ba69af6425b1d9b ]

RPM0 and RPM1 on the CN10KB SoC have 8 LMACs each, whereas RPM2 has only 4 LMACs. Similarly, the RPM0 and RPM1 have 256KB FIFO, whereas RPM2 has 128KB FIFO. This patch fixes an issue with improper TX credit programming for the RPM2 link.

---
 drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/ethernet/marvell/octeontx2/af/rpm.c +6 -1
index 4728ba34b0e3..76218f1cb459 100644
@@ -506,6 +506,7 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	rpm_t *rpm = rpmd;
 	u8 num_lmacs;
 	u32 fifo_len;
+	u16 max_lmac;
 
 	lmac_info = rpm_read(rpm, 0, RPM2_CMRX_RX_LMACS);
 	/* LMACs are divided into two groups and each group
@@ -513,7 +514,11 @@ u32 rpm2_get_lmac_fifo_len(void *rpmd, int lmac_id)
 	 * Group0 lmac_id range {0..3}
 	 * Group1 lmac_id range {4..7}
 	 */
-	fifo_len = rpm->mac_ops->fifo_len / 2;
+	max_lmac = (rpm_read(rpm, 0, CGX_CONST) >> 24) & 0xFF;
+	if (max_lmac > 4)
+		fifo_len = rpm->mac_ops->fifo_len / 2;
+	else
+		fifo_len = rpm->mac_ops->fifo_len;
 
 	if (lmac_id < 4) {
 		num_lmacs = hweight8(lmac_info & 0xF);
Signature · 1 line
2.43.0
author maintainer
#533 lore raw

PATCH 527/583 net: ethernet: ti: am65-cpsw: Fix max mtu to fit ethernet frames

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sanjuán García, Jorge <[email protected]>

[ Upstream commit 64e47d8afb5ca533b27efc006405e5bcae2c4a7b ]

The value of AM65_CPSW_MAX_PACKET_SIZE represents the maximum length of a received frame. This value is written to the register AM65_CPSW_PORT_REG_RX_MAXLEN.

The maximum MTU configured on the network device should then leave some room for the ethernet headers and frame check. Otherwise, if the network interface is configured to its maximum mtu possible, the frames will be larger than AM65_CPSW_MAX_PACKET_SIZE and will get dropped as oversized.

The switch supports ethernet frame sizes between 64 and 2024 bytes (including VLAN) as stated in the technical reference manual, so define AM65_CPSW_MAX_PACKET_SIZE with that maximum size.

Fixes 93a76530316a ("net: ethernet: ti: introduce am65x/j721e gigabit eth subsystem driver")
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/ti/am65-cpsw-nuss.c +3 -2
index 24120605502f..c62b0f99f2bc 100644
@@ -56,7 +56,7 @@
 #define AM65_CPSW_MAX_PORTS	8
 
 #define AM65_CPSW_MIN_PACKET_SIZE	VLAN_ETH_ZLEN
-#define AM65_CPSW_MAX_PACKET_SIZE	(VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
+#define AM65_CPSW_MAX_PACKET_SIZE	2024
 
 #define AM65_CPSW_REG_CTL		0x004
 #define AM65_CPSW_REG_STAT_PORT_EN	0x014
@@ -2167,7 +2167,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	eth_hw_addr_set(port->ndev, port->slave.mac_addr);
 
 	port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE;
-	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE;
+	port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE -
+			      (VLAN_ETH_HLEN + ETH_FCS_LEN);
 	port->ndev->hw_features = NETIF_F_SG |
 				  NETIF_F_RXCSUM |
 				  NETIF_F_HW_CSUM |
Signature · 1 line
2.43.0
author maintainer
#534 lore raw

PATCH 528/583 amt: do not use overwrapped cb area

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Taehee Yoo <[email protected]>

[ Upstream commit bec161add35b478a7746bf58bcdea6faa19129ef ]

amt driver uses skb->cb for storing tunnel information.
This job is worked before TC layer and then amt driver load tunnel info from skb->cb after TC layer.
So, its cb area should not be overwrapped with CB area used by TC. In order to not use cb area used by TC, it skips the biggest cb structure used by TC, which was qdisc_skb_cb.
But it's not anymore.
Currently, biggest structure of TC's CB is tc_skb_cb.
So, it should skip size of tc_skb_cb instead of qdisc_skb_cb.

Fixes ec624fe740b4 ("net/sched: Extend qdisc control block with tc control block")
---
 drivers/net/amt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/amt.c +3 -3
index 2d20be6ffb7e..ddd087c2c3ed 100644
@@ -11,7 +11,7 @@
 #include <linux/net.h>
 #include <linux/igmp.h>
 #include <linux/workqueue.h>
-#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
 #include <net/net_namespace.h>
 #include <net/ip.h>
 #include <net/udp.h>
@@ -80,11 +80,11 @@ static struct mld2_grec mldv2_zero_grec;
 
 static struct amt_skb_cb *amt_skb_cb(struct sk_buff *skb)
 {
-	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct qdisc_skb_cb) >
+	BUILD_BUG_ON(sizeof(struct amt_skb_cb) + sizeof(struct tc_skb_cb) >
 		     sizeof_field(struct sk_buff, cb));
 
 	return (struct amt_skb_cb *)((void *)skb->cb +
-		sizeof(struct qdisc_skb_cb));
+		sizeof(struct tc_skb_cb));
 }
 
 static void __amt_source_gc_work(void)
Signature · 1 line
2.43.0
author maintainer
#535 lore raw

PATCH 529/583 net: micrel: Fix PTP frame parsing for lan8841

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Horatiu Vultur <[email protected]>

[ Upstream commit acd66c2126eb9b5da2d89ae07dbcd73b909c2111 ]

The HW has the capability to check each frame if it is a PTP frame, which domain it is, which ptp frame type it is, different ip address in the frame. And if one of these checks fail then the frame is not timestamp. Most of these checks were disabled except checking the field minorVersionPTP inside the PTP header. Meaning that once a partner sends a frame compliant to 8021AS which has minorVersionPTP set to 1, then the frame was not timestamp because the HW expected by default a value of 0 in minorVersionPTP.
Fix this issue by removing this check so the userspace can decide on this.

Fixes cafc3662ee3f ("net: micrel: Add PHC support for lan8841")
---
 drivers/net/phy/micrel.c | 8 ++++++++
 1 file changed, 8 insertions(+)
drivers/net/phy/micrel.c +8 -0
index 927d3d54658e..a345d02a9edf 100644
@@ -3313,8 +3313,10 @@ static int lan8814_probe(struct phy_device *phydev)
 #define LAN8841_ADC_CHANNEL_MASK		198
 #define LAN8841_PTP_RX_PARSE_L2_ADDR_EN		370
 #define LAN8841_PTP_RX_PARSE_IP_ADDR_EN		371
+#define LAN8841_PTP_RX_VERSION			374
 #define LAN8841_PTP_TX_PARSE_L2_ADDR_EN		434
 #define LAN8841_PTP_TX_PARSE_IP_ADDR_EN		435
+#define LAN8841_PTP_TX_VERSION			438
 #define LAN8841_PTP_CMD_CTL			256
 #define LAN8841_PTP_CMD_CTL_PTP_ENABLE		BIT(2)
 #define LAN8841_PTP_CMD_CTL_PTP_DISABLE		BIT(1)
@@ -3358,6 +3360,12 @@ static int lan8841_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
 		      LAN8841_PTP_RX_PARSE_IP_ADDR_EN, 0);
 
+	/* Disable checking for minorVersionPTP field */
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_RX_VERSION, 0xff00);
+	phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG,
+		      LAN8841_PTP_TX_VERSION, 0xff00);
+
 	/* 100BT Clause 40 improvenent errata */
 	phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG,
 		      LAN8841_ANALOG_CONTROL_1,
Signature · 1 line
2.43.0
author maintainer
#536 lore raw

PATCH 530/583 net: phy: micrel: populate .soft_reset for KSZ9131

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Claudiu Beznea <[email protected]>

[ Upstream commit e398822c4751017fe401f57409488f5948d12fb5 ]

The RZ/G3S SMARC Module has 2 KSZ9131 PHYs. In this setup, the KSZ9131 PHY is used with the ravb Ethernet driver. It has been discovered that when bringing the Ethernet interface down/up continuously, e.g., with the following sh script:

$ while :; do ifconfig eth0 down; ifconfig eth0 up; done

the link speed and duplex are wrong after interrupting the bring down/up operation even though the Ethernet interface is up. To recover from this state the following configuration sequence is necessary (executed manually):

$ ifconfig eth0 down
$ ifconfig eth0 up

The behavior has been identified also on the Microchip SAMA7G5-EK board which runs the macb driver and uses the same PHY.

The order of PHY-related operations in ravb_open() is as follows:
ravb_open() ->
ravb_phy_start() ->

    ravb_phy_init() ->
      of_phy_connect() ->
        phy_connect_direct() ->
	  phy_attach_direct() ->
	    phy_init_hw() ->
	      phydev->drv->soft_reset()
	      phydev->drv->config_init()
	      phydev->drv->config_intr()
	    phy_resume()
	      kszphy_resume()

The order of PHY-related operations in ravb_close is as follows:
ravb_close() ->
phy_stop() ->

    phy_suspend() ->
      kszphy_suspend() ->
        genphy_suspend()
	  // set BMCR_PDOWN bit in MII_BMCR

In genphy_suspend() setting the BMCR_PDWN bit in MII_BMCR switches the PHY to Software Power-Down (SPD) mode (according to the KSZ9131 datasheet). Thus, when opening the interface after it has been previously closed (via ravb_close()), the phydev->drv->config_init() and phydev->drv->config_intr() reach the KSZ9131 PHY driver via the ksz9131_config_init() and kszphy_config_intr() functions.

KSZ9131 specifies that the MII management interface remains operational during SPD (Software Power-Down), but (according to manual):
- Only access to the standard registers (0 through 31) is supported.
- Access to MMD address spaces other than MMD address space 1 is possible if the spd_clock_gate_override bit is set.
- Access to MMD address space 1 is not possible.

The spd_clock_gate_override bit is not used in the KSZ9131 driver.

ksz9131_config_init() configures RGMII delay, pad skews and LEDs by accessesing MMD registers other than those in address space 1.

The datasheet for the KSZ9131 does not specify what happens if registers from an unsupported address space are accessed while the PHY is in SPD.

To fix the issue the .soft_reset method has been instantiated for KSZ9131, too. This resets the PHY to the default state before doing any configurations to it, thus switching it out of SPD.

Fixes bff5b4b37372 ("net: phy: micrel: add Microchip KSZ9131 initial driver")
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/phy/micrel.c +1 -0
index a345d02a9edf..dfd5f8e78e29 100644
@@ -4828,6 +4828,7 @@ static struct phy_driver ksphy_driver[] = {
 	.flags		= PHY_POLL_CABLE_TEST,
 	.driver_data	= &ksz9131_type,
 	.probe		= kszphy_probe,
+	.soft_reset	= genphy_soft_reset,
 	.config_init	= ksz9131_config_init,
 	.config_intr	= kszphy_config_intr,
 	.config_aneg	= ksz9131_config_aneg,
Signature · 1 line
2.43.0
author maintainer
#537 lore raw

PATCH 531/583 ALSA: hda: Properly setup HDMI stream

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Amadeusz Sławiński <[email protected]>

[ Upstream commit 454abb80e26ab85323a30e52aa7b0ee9aae1d38a ]

Since commit 4005d1ba0a7e ("ASoC: soc-dai: don't call PCM audio ops if the stream is not supported") HDMI playback is broken with avs driver. This happens because for HDMI stream (unlike generic HDA one) channels_min for stream is not set when creating PCMs. Fix this by setting the value based on first available converter.

Fixes 4005d1ba0a7e ("ASoC: soc-dai: don't call PCM audio ops if the stream is not supported")
---
 sound/pci/hda/patch_hdmi.c | 6 ++++++
 1 file changed, 6 insertions(+)
sound/pci/hda/patch_hdmi.c +6 -0
index 78cee53fee02..038db8902c9e 100644
@@ -2301,6 +2301,7 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
 
 	for (idx = 0; idx < pcm_num; idx++) {
+		struct hdmi_spec_per_cvt *per_cvt;
 		struct hda_pcm *info;
 		struct hda_pcm_stream *pstr;
 
@@ -2316,6 +2317,11 @@ static int generic_hdmi_build_pcms(struct hda_codec *codec)
 		pstr = &info->stream[SNDRV_PCM_STREAM_PLAYBACK];
 		pstr->substreams = 1;
 		pstr->ops = generic_ops;
+
+		per_cvt = get_cvt(spec, 0);
+		pstr->channels_min = per_cvt->channels_min;
+		pstr->channels_max = per_cvt->channels_max;
+
 		/* pcm number is less than pcm_rec array size */
 		if (spec->pcm_used >= ARRAY_SIZE(spec->pcm_rec))
 			break;
Signature · 1 line
2.43.0
author maintainer
#538 lore raw

PATCH 532/583 mptcp: mptcp_parse_option() fix for MPTCPOPT_MP_JOIN

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 89e23277f9c16df6f9f9c1a1a07f8f132339c15c ]

mptcp_parse_option() currently sets OPTIONS_MPTCP_MPJ, for the three possible cases handled for MPTCPOPT_MP_JOIN option.

OPTIONS_MPTCP_MPJ is the combination of three flags:
- OPTION_MPTCP_MPJ_SYN
- OPTION_MPTCP_MPJ_SYNACK
- OPTION_MPTCP_MPJ_ACK

This is a problem, because backup, join_id, token, nonce and/or hmac fields could be left uninitialized in some cases.

Distinguish the three cases, as following patches will need this step.

Fixes f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Cc Florian Westphal <[email protected]>
Cc Peter Krystad <[email protected]>
Cc Matthieu Baerts <[email protected]>
Cc Mat Martineau <[email protected]>
Cc Geliang Tang <[email protected]>
---
 net/mptcp/options.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
net/mptcp/options.c +3 -3
index c53914012d01..d2527d189a79 100644
@@ -123,8 +123,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		break;
 
 	case MPTCPOPT_MP_JOIN:
-		mp_opt->suboptions |= OPTIONS_MPTCP_MPJ;
 		if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->token = get_unaligned_be32(ptr);
@@ -135,6 +135,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->token, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK;
 			mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
 			mp_opt->join_id = *ptr++;
 			mp_opt->thmac = get_unaligned_be64(ptr);
@@ -145,11 +146,10 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 				 mp_opt->backup, mp_opt->join_id,
 				 mp_opt->thmac, mp_opt->nonce);
 		} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
+			mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
 			ptr += 2;
 			memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
 			pr_debug("MP_JOIN hmac");
-		} else {
-			mp_opt->suboptions &= ~OPTIONS_MPTCP_MPJ;
 		}
 		break;
 
Signature · 1 line
2.43.0
author maintainer
#539 lore raw

PATCH 533/583 mptcp: strict validation before using mp_opt->hmac

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit c1665273bdc7c201766c65e561c06711f2e050dc ]

mp_opt->hmac contains uninitialized data unless OPTION_MPTCP_MPJ_ACK was set in mptcp_parse_option().

We must refine the condition before we call subflow_hmac_valid().

Fixes f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Cc Florian Westphal <[email protected]>
Cc Peter Krystad <[email protected]>
Cc Matthieu Baerts <[email protected]>
Cc Mat Martineau <[email protected]>
Cc Geliang Tang <[email protected]>
---
 net/mptcp/subflow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/subflow.c +1 -1
index 45b8115b363b..d6ee0e52ea41 100644
@@ -788,7 +788,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) ||
 		    !subflow_hmac_valid(req, &mp_opt) ||
 		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
Signature · 1 line
2.43.0
author maintainer
#540 lore raw

PATCH 534/583 mptcp: use OPTION_MPTCP_MPJ_SYNACK in subflow_finish_connect()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit be1d9d9d38da922bd4beeec5b6dd821ff5a1dfeb ]

subflow_finish_connect() uses four fields (backup, join_id, thmac, none) that may contain garbage unless OPTION_MPTCP_MPJ_SYNACK has been set in mptcp_parse_option()

Fixes f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Cc Florian Westphal <[email protected]>
Cc Peter Krystad <[email protected]>
Cc Matthieu Baerts <[email protected]>
Cc Mat Martineau <[email protected]>
Cc Geliang Tang <[email protected]>
---
 net/mptcp/subflow.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/subflow.c +1 -1
index d6ee0e52ea41..5b37fee2a85a 100644
@@ -506,7 +506,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYNACK)) {
 			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
 		}
Signature · 1 line
2.43.0
author maintainer
#541 lore raw

PATCH 535/583 mptcp: use OPTION_MPTCP_MPJ_SYN in subflow_check_req()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 66ff70df1a919a066942844bb095d6fcb748d78d ]

syzbot reported that subflow_check_req() was using uninitialized data in subflow_check_req() [1]

This is because mp_opt.token is only set when OPTION_MPTCP_MPJ_SYN is also set.

While we are are it, fix mptcp_subflow_init_cookie_req() to test for OPTION_MPTCP_MPJ_ACK.

[1]

BUG: KMSAN: uninit-value in subflow_token_join_request net/mptcp/subflow.c:91 [inline]
 BUG: KMSAN: uninit-value in subflow_check_req+0x1028/0x15d0 net/mptcp/subflow.c:209
  subflow_token_join_request net/mptcp/subflow.c:91 [inline]
  subflow_check_req+0x1028/0x15d0 net/mptcp/subflow.c:209
  subflow_v6_route_req+0x269/0x410 net/mptcp/subflow.c:367
  tcp_conn_request+0x153a/0x4240 net/ipv4/tcp_input.c:7164
 subflow_v6_conn_request+0x3ee/0x510
  tcp_rcv_state_process+0x2e1/0x4ac0 net/ipv4/tcp_input.c:6659
  tcp_v6_do_rcv+0x11bf/0x1fe0 net/ipv6/tcp_ipv6.c:1669
  tcp_v6_rcv+0x480b/0x4fb0 net/ipv6/tcp_ipv6.c:1900
  ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438
  ip6_input_finish net/ipv6/ip6_input.c:483 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492
  dst_input include/net/dst.h:461 [inline]
  ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5532 [inline]
  __netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5646
  netif_receive_skb_internal net/core/dev.c:5732 [inline]
  netif_receive_skb+0x58/0x660 net/core/dev.c:5791
  tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1555
  tun_get_user+0x53af/0x66d0 drivers/net/tun.c:2002
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2020 [inline]
  new_sync_write fs/read_write.c:491 [inline]
  vfs_write+0x8ef/0x1490 fs/read_write.c:584
  ksys_write+0x20f/0x4c0 fs/read_write.c:637
  __do_sys_write fs/read_write.c:649 [inline]
  __se_sys_write fs/read_write.c:646 [inline]
  __x64_sys_write+0x93/0xd0 fs/read_write.c:646
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Local variable mp_opt created at:

  subflow_check_req+0x6d/0x15d0 net/mptcp/subflow.c:145
  subflow_v6_route_req+0x269/0x410 net/mptcp/subflow.c:367

CPU: 1 PID: 5924 Comm: syz-executor.3 Not tainted 6.7.0-rc8-syzkaller-00055-g5eff55d725a4 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Fixes f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests")
Cc Florian Westphal <[email protected]>
Cc Peter Krystad <[email protected]>
Cc Matthieu Baerts <[email protected]>
Cc Mat Martineau <[email protected]>
Cc Geliang Tang <[email protected]>
---
 net/mptcp/subflow.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/mptcp/subflow.c +2 -2
index 5b37fee2a85a..93f43a5cce40 100644
@@ -158,7 +158,7 @@ static int subflow_check_req(struct request_sock *req,
 	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN);
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
@@ -255,7 +255,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	mptcp_get_options(skb, &mp_opt);
 
 	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
-	opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
+	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK);
 	if (opt_mp_capable && opt_mp_join)
 		return -EINVAL;
 
Signature · 1 line
2.43.0
author maintainer
#542 lore raw

PATCH 536/583 mptcp: refine opt_mp_capable determination

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 724b00c12957973656d312dce2a110c75ae2c680 ]

OPTIONS_MPTCP_MPC is a combination of three flags.

It would be better to be strict about testing what flag is expected, at least for code readability.

mptcp_parse_option() already makes the distinction.

- subflow_check_req() should use OPTION_MPTCP_MPC_SYN.

- mptcp_subflow_init_cookie_req() should use OPTION_MPTCP_MPC_ACK.

- subflow_finish_connect() should use OPTION_MPTCP_MPC_SYNACK

- subflow_syn_recv_sock should use OPTION_MPTCP_MPC_ACK

---
 net/mptcp/subflow.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
net/mptcp/subflow.c +4 -4
index 93f43a5cce40..70b7a47a53c7 100644
@@ -157,7 +157,7 @@ static int subflow_check_req(struct request_sock *req,
 
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYN);
 	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_SYN);
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
@@ -254,7 +254,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 	subflow_init_req(req, sk_listener);
 	mptcp_get_options(skb, &mp_opt);
 
-	opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
+	opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK);
 	opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK);
 	if (opt_mp_capable && opt_mp_join)
 		return -EINVAL;
@@ -486,7 +486,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	mptcp_get_options(skb, &mp_opt);
 	if (subflow->request_mptcp) {
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_SYNACK)) {
 			MPTCP_INC_STATS(sock_net(sk),
 					MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
 			mptcp_do_fallback(sk);
@@ -783,7 +783,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC))
+		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK))
 			fallback = true;
 
 	} else if (subflow_req->mp_join) {
Signature · 1 line
2.43.0
author maintainer
#543 lore raw

PATCH 537/583 block: ensure we hold a queue reference when using queue limits

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jens Axboe <[email protected]>

[ Upstream commit 7b4f36cd22a65b750b4cb6ac14804fb7d6e6c67d ]

q_usage_counter is the only thing preventing us from the limits changing under us in __bio_split_to_limits, but blk_mq_submit_bio doesn't hold it while calling into it.

Move the splitting inside the region where we know we've got a queue reference. Ideally this could still remain a shared section of code, but let's keep the fix simple and defer any refactoring here to later.

Fixes 900e08075202 ("block: move queue enter logic into blk_mq_submit_bio()")
---
 block/blk-mq.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)
block/blk-mq.c +10 -6
index 20ecd0ab616f..6041e17492ec 100644
@@ -2968,12 +2968,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
-		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-		if (!bio)
-			return;
-	}
-
 	bio_set_ioprio(bio);
 
 	if (plug) {
@@ -2982,6 +2976,11 @@ void blk_mq_submit_bio(struct bio *bio)
 			rq = NULL;
 	}
 	if (rq) {
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				return;
+		}
 		if (!bio_integrity_prep(bio))
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
@@ -2992,6 +2991,11 @@ void blk_mq_submit_bio(struct bio *bio)
 	} else {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				goto fail;
+		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
 	}
Signature · 1 line
2.43.0
author maintainer
#544 lore raw

PATCH 538/583 net: stmmac: Fix ethool link settings ops for integrated PCS

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sneh Shah <[email protected]>

[ Upstream commit 08300adac3b8dab9e2fd3be0155c7d3093c755f4 ]

Currently get/set_link_ksettings ethtool ops are dependent on PCS. When PCS is integrated, it will not have separate link config. Bypass configuring and checking PCS for integrated PCS.

Fixes aa571b6275fb ("net: stmmac: add new switch to struct plat_stmmacenet_data")
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +6 -4
index aea5f898ebf4..419efe43951e 100644
@@ -311,8 +311,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		struct rgmii_adv adv;
 		u32 supported, advertising, lp_advertising;
 
@@ -397,8 +398,9 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev,
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (priv->hw->pcs & STMMAC_PCS_RGMII ||
-	    priv->hw->pcs & STMMAC_PCS_SGMII) {
+	if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) &&
+	    (priv->hw->pcs & STMMAC_PCS_RGMII ||
+	     priv->hw->pcs & STMMAC_PCS_SGMII)) {
 		/* Only support ANE */
 		if (cmd->base.autoneg != AUTONEG_ENABLE)
 			return -EINVAL;
Signature · 1 line
2.43.0
author maintainer
#545 lore raw

PATCH 539/583 udp: annotate data-races around up->pending

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 482521d8e0c6520429478aa6866cd44128b33d5d ]

up->pending can be read without holding the socket lock, as pointed out by syzbot [1]

Add READ_ONCE() in lockless contexts, and WRITE_ONCE() on write side.

[1]

BUG: KCSAN: data-race in udpv6_sendmsg / udpv6_sendmsg

write to 0xffff88814e5eadf0 of 4 bytes by task 15547 on cpu 1:

 udpv6_sendmsg+0x1405/0x1530 net/ipv6/udp.c:1596
 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:657
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 __sys_sendto+0x257/0x310 net/socket.c:2192
 __do_sys_sendto net/socket.c:2204 [inline]
 __se_sys_sendto net/socket.c:2200 [inline]
 __x64_sys_sendto+0x78/0x90 net/socket.c:2200
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

read to 0xffff88814e5eadf0 of 4 bytes by task 15551 on cpu 0:

 udpv6_sendmsg+0x22c/0x1530 net/ipv6/udp.c:1373
 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:657
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x37c/0x4d0 net/socket.c:2586
 ___sys_sendmsg net/socket.c:2640 [inline]
 __sys_sendmmsg+0x269/0x500 net/socket.c:2726
 __do_sys_sendmmsg net/socket.c:2755 [inline]
 __se_sys_sendmmsg net/socket.c:2752 [inline]
 __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2752
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

value changed: 0x00000000 -> 0x0000000a

Reported by Kernel Concurrency Sanitizer on:

CPU: 0 PID: 15551 Comm: syz-executor.1 Tainted: G        W          6.7.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
---
 net/ipv4/udp.c | 12 ++++++------
 net/ipv6/udp.c | 16 ++++++++--------
 2 files changed, 14 insertions(+), 14 deletions(-)
net/ipv4/udp.c +6 -6
index c3ff984b6354..bd12a7658213 100644
@@ -805,7 +805,7 @@ void udp_flush_pending_frames(struct sock *sk)
 
 	if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip_flush_pending_frames(sk);
 	}
 }
@@ -993,7 +993,7 @@ int udp_push_pending_frames(struct sock *sk)
 
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 EXPORT_SYMBOL(udp_push_pending_frames);
@@ -1069,7 +1069,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
 	fl4 = &inet->cork.fl.u.ip4;
-	if (up->pending) {
+	if (READ_ONCE(up->pending)) {
 		/*
 		 * There are pending frames.
 		 * The socket lock must be held while it's corked.
@@ -1265,7 +1265,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl4->saddr = saddr;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = inet->inet_sport;
-	up->pending = AF_INET;
+	WRITE_ONCE(up->pending, AF_INET);
 
 do_append_data:
 	up->len += ulen;
@@ -1277,7 +1277,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	else if (!corkreq)
 		err = udp_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 	release_sock(sk);
 
 out:
@@ -1315,7 +1315,7 @@ void udp_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
net/ipv6/udp.c +8 -8
index f60ba4295435..f1170dcc21d9 100644
@@ -1134,7 +1134,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 		udp_flush_pending_frames(sk);
 	else if (up->pending) {
 		up->len = 0;
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 		ip6_flush_pending_frames(sk);
 	}
 }
@@ -1312,7 +1312,7 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 			      &inet_sk(sk)->cork.base);
 out:
 	up->len = 0;
-	up->pending = 0;
+	WRITE_ONCE(up->pending, 0);
 	return err;
 }
 
@@ -1369,7 +1369,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		default:
 			return -EINVAL;
 		}
-	} else if (!up->pending) {
+	} else if (!READ_ONCE(up->pending)) {
 		if (sk->sk_state != TCP_ESTABLISHED)
 			return -EDESTADDRREQ;
 		daddr = &sk->sk_v6_daddr;
@@ -1400,8 +1400,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return -EMSGSIZE;
 
 	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
-	if (up->pending) {
-		if (up->pending == AF_INET)
+	if (READ_ONCE(up->pending)) {
+		if (READ_ONCE(up->pending) == AF_INET)
 			return udp_sendmsg(sk, msg, len);
 		/*
 		 * There are pending frames.
@@ -1591,7 +1591,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		goto out;
 	}
 
-	up->pending = AF_INET6;
+	WRITE_ONCE(up->pending, AF_INET6);
 
 do_append_data:
 	if (ipc6.dontfrag < 0)
@@ -1605,7 +1605,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	else if (!corkreq)
 		err = udp_v6_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
-		up->pending = 0;
+		WRITE_ONCE(up->pending, 0);
 
 	if (err > 0)
 		err = np->recverr ? net_xmit_errno(err) : 0;
@@ -1646,7 +1646,7 @@ static void udpv6_splice_eof(struct socket *sock)
 	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
 
-	if (!up->pending || udp_test_bit(CORK, sk))
+	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
 		return;
 
 	lock_sock(sk);
Signature · 1 line
2.43.0
author maintainer
#546 lore raw

PATCH 540/583 erofs: simplify compression configuration parser

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gao Xiang <[email protected]>

[ Upstream commit efb4fb02cef3ab410b603c8f0e1c67f61d55f542 ]

Move erofs_load_compr_cfgs() into decompressor.c as well as introduce a callback instead of a hard-coded switch for each algorithm for simplicity.

Stable-dep-of: 118a8cf504d7 ("erofs: fix inconsistent per-file compression format")

---
 fs/erofs/compress.h             |  6 +++
 fs/erofs/decompressor.c         | 62 ++++++++++++++++++++++++++--
 fs/erofs/decompressor_deflate.c |  5 ++-
 fs/erofs/decompressor_lzma.c    |  4 +-
 fs/erofs/internal.h             | 38 +----------------
 fs/erofs/super.c                | 72 ++++-----------------------------
 6 files changed, 79 insertions(+), 108 deletions(-)
fs/erofs/compress.h +6 -0
index 349c3316ae6b..279933e007d2 100644
@@ -21,6 +21,8 @@ struct z_erofs_decompress_req {
 };
 
 struct z_erofs_decompressor {
+	int (*config)(struct super_block *sb, struct erofs_super_block *dsb,
+		      void *data, int size);
 	int (*decompress)(struct z_erofs_decompress_req *rq,
 			  struct page **pagepool);
 	char *name;
@@ -92,6 +94,10 @@ int z_erofs_fixup_insize(struct z_erofs_decompress_req *rq, const char *padbuf,
 extern const struct z_erofs_decompressor erofs_decompressors[];
 
 /* prototypes for specific algorithms */
+int z_erofs_load_lzma_config(struct super_block *sb,
+			struct erofs_super_block *dsb, void *data, int size);
+int z_erofs_load_deflate_config(struct super_block *sb,
+			struct erofs_super_block *dsb, void *data, int size);
 int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq,
 			    struct page **pagepool);
 int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
fs/erofs/decompressor.c +59 -3

89 lines not on this page · raw message

fs/erofs/decompressor_deflate.c +3 -2
index 19e5bdeb30b6..0e1946a6bda5 100644
@@ -77,9 +77,10 @@ int __init z_erofs_deflate_init(void)
 }
 
 int z_erofs_load_deflate_config(struct super_block *sb,
-				struct erofs_super_block *dsb,
-				struct z_erofs_deflate_cfgs *dfl, int size)
+			struct erofs_super_block *dsb, void *data, int size)
 {
+	struct z_erofs_deflate_cfgs *dfl = data;
+
 	if (!dfl || size < sizeof(struct z_erofs_deflate_cfgs)) {
 		erofs_err(sb, "invalid deflate cfgs, size=%u", size);
 		return -EINVAL;
fs/erofs/decompressor_lzma.c +2 -2
index dee10d22ada9..ba4ec73f4aae 100644
@@ -72,10 +72,10 @@ int __init z_erofs_lzma_init(void)
 }
 
 int z_erofs_load_lzma_config(struct super_block *sb,
-			     struct erofs_super_block *dsb,
-			     struct z_erofs_lzma_cfgs *lzma, int size)
+			struct erofs_super_block *dsb, void *data, int size)
 {
 	static DEFINE_MUTEX(lzma_resize_mutex);
+	struct z_erofs_lzma_cfgs *lzma = data;
 	unsigned int dict_size, i;
 	struct z_erofs_lzma *strm, *head = NULL;
 	int err;
fs/erofs/internal.h +1 -37
index 4ff88d0dd980..d8de61350dc0 100644
@@ -469,9 +469,6 @@ int __init z_erofs_init_zip_subsystem(void);
 void z_erofs_exit_zip_subsystem(void);
 int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
 				       struct erofs_workgroup *egrp);
-int z_erofs_load_lz4_config(struct super_block *sb,
-			    struct erofs_super_block *dsb,
-			    struct z_erofs_lz4_cfgs *lz4, int len);
 int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			    int flags);
 void *erofs_get_pcpubuf(unsigned int requiredpages);
@@ -480,6 +477,7 @@ int erofs_pcpubuf_growsize(unsigned int nrpages);
 void __init erofs_pcpubuf_init(void);
 void erofs_pcpubuf_exit(void);
 int erofs_init_managed_cache(struct super_block *sb);
+int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb);
 #else
 static inline void erofs_shrinker_register(struct super_block *sb) {}
 static inline void erofs_shrinker_unregister(struct super_block *sb) {}
@@ -487,16 +485,6 @@ static inline int erofs_init_shrinker(void) { return 0; }
 static inline void erofs_exit_shrinker(void) {}
 static inline int z_erofs_init_zip_subsystem(void) { return 0; }
 static inline void z_erofs_exit_zip_subsystem(void) {}
-static inline int z_erofs_load_lz4_config(struct super_block *sb,
-				  struct erofs_super_block *dsb,
-				  struct z_erofs_lz4_cfgs *lz4, int len)
-{
-	if (lz4 || dsb->u1.lz4_max_distance) {
-		erofs_err(sb, "lz4 algorithm isn't enabled");
-		return -EINVAL;
-	}
-	return 0;
-}
 static inline void erofs_pcpubuf_init(void) {}
 static inline void erofs_pcpubuf_exit(void) {}
 static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; }
@@ -505,41 +493,17 @@ static inline int erofs_init_managed_cache(struct super_block *sb) { return 0; }
 #ifdef CONFIG_EROFS_FS_ZIP_LZMA
 int __init z_erofs_lzma_init(void);
 void z_erofs_lzma_exit(void);
-int z_erofs_load_lzma_config(struct super_block *sb,
-			     struct erofs_super_block *dsb,
-			     struct z_erofs_lzma_cfgs *lzma, int size);
 #else
 static inline int z_erofs_lzma_init(void) { return 0; }
 static inline int z_erofs_lzma_exit(void) { return 0; }
-static inline int z_erofs_load_lzma_config(struct super_block *sb,
-			     struct erofs_super_block *dsb,
-			     struct z_erofs_lzma_cfgs *lzma, int size) {
-	if (lzma) {
-		erofs_err(sb, "lzma algorithm isn't enabled");
-		return -EINVAL;
-	}
-	return 0;
-}
 #endif	/* !CONFIG_EROFS_FS_ZIP_LZMA */
 
 #ifdef CONFIG_EROFS_FS_ZIP_DEFLATE
 int __init z_erofs_deflate_init(void);
 void z_erofs_deflate_exit(void);
-int z_erofs_load_deflate_config(struct super_block *sb,
-				struct erofs_super_block *dsb,
-				struct z_erofs_deflate_cfgs *dfl, int size);
 #else
 static inline int z_erofs_deflate_init(void) { return 0; }
 static inline int z_erofs_deflate_exit(void) { return 0; }
-static inline int z_erofs_load_deflate_config(struct super_block *sb,
-			struct erofs_super_block *dsb,
-			struct z_erofs_deflate_cfgs *dfl, int size) {
-	if (dfl) {
-		erofs_err(sb, "deflate algorithm isn't enabled");
-		return -EINVAL;
-	}
-	return 0;
-}
 #endif	/* !CONFIG_EROFS_FS_ZIP_DEFLATE */
 
 #ifdef CONFIG_EROFS_FS_ONDEMAND
fs/erofs/super.c +8 -64

86 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#547 lore raw

PATCH 541/583 erofs: fix inconsistent per-file compression format

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gao Xiang <[email protected]>

[ Upstream commit 118a8cf504d7dfa519562d000f423ee3ca75d2c4 ]

EROFS can select compression algorithms on a per-file basis, and each per-file compression algorithm needs to be marked in the on-disk superblock for initialization.

However, syzkaller can generate inconsistent crafted images that use an unsupported algorithmtype for specific inodes, e.g. use MicroLZMA algorithmtype even it's not set in sbi->available_compr_algs. This can lead to an unexpected "BUG: kernel NULL pointer dereference" if the corresponding decompressor isn't built-in.

Fix this by checking against sbi->available_compr_algs for each m_algorithmformat request. Incorrect !erofs_sb_has_compr_cfgs preset bitmap is now fixed together since it was harmless previously.

Fixes 8f89926290c4 ("erofs: get compression algorithms directly on mapping")
Fixes 622ceaddb764 ("erofs: lzma compression support")
---
 fs/erofs/decompressor.c |  2 +-
 fs/erofs/zmap.c         | 23 +++++++++++++----------
 2 files changed, 14 insertions(+), 11 deletions(-)
fs/erofs/decompressor.c +1 -1
index e75edc8f1753..8d1f86487d6e 100644
@@ -399,7 +399,7 @@ int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb)
 	int size, ret = 0;
 
 	if (!erofs_sb_has_compr_cfgs(sbi)) {
-		sbi->available_compr_algs = Z_EROFS_COMPRESSION_LZ4;
+		sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4;
 		return z_erofs_load_lz4_config(sb, dsb, NULL, 0);
 	}
 
fs/erofs/zmap.c +13 -10
index 7b55111fd533..7a1a24ae4a2d 100644
@@ -458,7 +458,7 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 		.map = map,
 	};
 	int err = 0;
-	unsigned int lclusterbits, endoff;
+	unsigned int lclusterbits, endoff, afmt;
 	unsigned long initial_lcn;
 	unsigned long long ofs, end;
 
@@ -547,17 +547,20 @@ static int z_erofs_do_map_blocks(struct inode *inode,
 			err = -EFSCORRUPTED;
 			goto unmap_out;
 		}
-		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_INTERLACED;
-		else
-			map->m_algorithmformat =
-				Z_EROFS_COMPRESSION_SHIFTED;
-	} else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
-		map->m_algorithmformat = vi->z_algorithmtype[1];
+		afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ?
+			Z_EROFS_COMPRESSION_INTERLACED :
+			Z_EROFS_COMPRESSION_SHIFTED;
 	} else {
-		map->m_algorithmformat = vi->z_algorithmtype[0];
+		afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ?
+			vi->z_algorithmtype[1] : vi->z_algorithmtype[0];
+		if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) {
+			erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu",
+				  afmt, vi->nid);
+			err = -EFSCORRUPTED;
+			goto unmap_out;
+		}
 	}
+	map->m_algorithmformat = afmt;
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
Signature · 1 line
2.43.0
author maintainer
#548 lore raw

PATCH 542/583 net: add more sanity check in virtio_net_hdr_to_skb()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 9181d6f8a2bb32d158de66a84164fac05e3ddd18 ]

syzbot/KMSAN reports access to uninitialized data from gso_features_check() [1]

The repro use af_packet, injecting a gso packet and hdrlen == 0.

We could fix the issue making gso_features_check() more careful while dealing with NETIF_F_TSO_MANGLEID in fast path.

Or we can make sure virtio_net_hdr_to_skb() pulls minimal network and transport headers as intended.

Note that for GSO packets coming from untrusted sources, SKB_GSO_DODGY bit forces a proper header validation (and pull) before the packet can hit any device ndo_start_xmit(), thus we do not need a precise disection at virtio_net_hdr_to_skb() stage.

[1]

BUG: KMSAN: uninit-value in skb_gso_segment include/net/gso.h:83 [inline]
BUG: KMSAN: uninit-value in validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 skb_gso_segment include/net/gso.h:83 [inline]
 validate_xmit_skb+0x10f2/0x1930 net/core/dev.c:3629
 __dev_queue_xmit+0x1eac/0x5130 net/core/dev.c:4341
 dev_queue_xmit include/linux/netdevice.h:3134 [inline]
 packet_xmit+0x9c/0x6b0 net/packet/af_packet.c:276
 packet_snd net/packet/af_packet.c:3087 [inline]
 packet_sendmsg+0x8b1d/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

Uninit was created at:

 slab_post_alloc_hook+0x129/0xa70 mm/slab.h:768
 slab_alloc_node mm/slub.c:3478 [inline]
 kmem_cache_alloc_node+0x5e9/0xb10 mm/slub.c:3523
 kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:560
 __alloc_skb+0x318/0x740 net/core/skbuff.c:651
 alloc_skb include/linux/skbuff.h:1286 [inline]
 alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6334
 sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2780
 packet_alloc_skb net/packet/af_packet.c:2936 [inline]
 packet_snd net/packet/af_packet.c:3030 [inline]
 packet_sendmsg+0x70e8/0x9f30 net/packet/af_packet.c:3119
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 ____sys_sendmsg+0x9c2/0xd60 net/socket.c:2584
 ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
 __sys_sendmsg net/socket.c:2667 [inline]
 __do_sys_sendmsg net/socket.c:2676 [inline]
 __se_sys_sendmsg net/socket.c:2674 [inline]
 __x64_sys_sendmsg+0x307/0x490 net/socket.c:2674
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0x44/0x110 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x63/0x6b

CPU: 0 PID: 5025 Comm: syz-executor279 Not tainted 6.7.0-rc7-syzkaller-00003-gfbafc3e621c3 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023
Reported-by [email protected]
Fixes 9274124f023b ("net: stricter validation of untrusted gso packets")
Cc Willem de Bruijn <[email protected]>
---
 include/linux/virtio_net.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
include/linux/virtio_net.h +7 -2
index 27cc1d464321..4dfa9b69ca8d 100644
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 #include <linux/udp.h>
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
@@ -49,6 +51,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					const struct virtio_net_hdr *hdr,
 					bool little_endian)
 {
+	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
 	unsigned int thlen = 0;
 	unsigned int p_off = 0;
@@ -65,6 +68,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			gso_type = SKB_GSO_TCPV6;
 			ip_proto = IPPROTO_TCP;
 			thlen = sizeof(struct tcphdr);
+			nh_min_len = sizeof(struct ipv6hdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
@@ -100,7 +104,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
 
-		p_off = skb_transport_offset(skb) + thlen;
+		nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb));
+		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;
 	} else {
@@ -140,7 +145,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 			skb_set_transport_header(skb, keys.control.thoff);
 		} else if (gso_type) {
-			p_off = thlen;
+			p_off = nh_min_len + thlen;
 			if (!pskb_may_pull(skb, p_off))
 				return -EINVAL;
 		}
Signature · 1 line
2.43.0
author maintainer
#549 lore raw

PATCH 543/583 net: netdev_queue: netdev_txq_completed_mb(): fix wake condition

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marc Kleine-Budde <[email protected]>

[ Upstream commit 894d7508316e7ad722df597d68b4b1797a9eee11 ]

netif_txq_try_stop() uses "get_desc >= start_thrs" as the check for the call to netif_tx_start_queue().

Use ">=" i netdev_txq_completed_mb(), too.

Fixes c91c46de6bbc ("net: provide macros for commonly copied lockless queue stop/wake code")
---
 include/net/netdev_queues.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/net/netdev_queues.h +1 -1
index d68b0a483431..8b8ed4e13d74 100644
@@ -128,7 +128,7 @@ netdev_txq_completed_mb(struct netdev_queue *dev_queue,
 		netdev_txq_completed_mb(txq, pkts, bytes);		\
 									\
 		_res = -1;						\
-		if (pkts && likely(get_desc > start_thrs)) {		\
+		if (pkts && likely(get_desc >= start_thrs)) {		\
 			_res = 1;					\
 			if (unlikely(netif_tx_queue_stopped(txq)) &&	\
 			    !(down_cond)) {				\
Signature · 1 line
2.43.0
author maintainer
#550 lore raw

PATCH 544/583 bpf: iter_udp: Retry with a larger batch size without going back to the previous bucket

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin KaFai Lau <[email protected]>

[ Upstream commit 19ca0823f6eaad01d18f664a00550abe912c034c ]

The current logic is to use a default size 16 to batch the whole bucket. If it is too small, it will retry with a larger batch size.

The current code accidentally does a state->bucket-- before retrying. This goes back to retry with the previous bucket which has already been done. This patch fixed it.

It is hard to create a selftest. I added a WARN_ON(state->bucket < 0), forced a particular port to be hashed to the first bucket, created >16 sockets, and observed the for-loop went back
to the "-1" bucket.

---
 net/ipv4/udp.c | 1 -
 1 file changed, 1 deletion(-)
net/ipv4/udp.c +0 -1
index bd12a7658213..a4857c85a020 100644
@@ -3192,7 +3192,6 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 		/* After allocating a larger batch, retry one more time to grab
 		 * the whole bucket.
 		 */
-		state->bucket--;
 		goto again;
 	}
 done:
Signature · 1 line
2.43.0
author maintainer
#551 lore raw

PATCH 545/583 bpf: Avoid iter->offset making backward progress in bpf_iter_udp

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Martin KaFai Lau <[email protected]>

[ Upstream commit 2242fd537fab52d5f4d2fbb1845f047c01fad0cf ]

There is a bug in the bpf_iter_udp_batch() function that stops the userspace from making forward progress.

The case that triggers the bug is the userspace passed in a very small read buffer. When the bpf prog does bpf_seq_printf, the userspace read buffer is not enough to capture the whole bucket.

When the read buffer is not large enough, the kernel will remember the offset of the bucket in iter->offset such that the next userspace read() can continue from where it left off.

The kernel will skip the number (== "iter->offset") of sockets in the next read(). However, the code directly decrements the "--iter->offset". This is incorrect because the next read() may not consume the whole bucket either and then the next-next read() will start from offset 0. The net effect is the userspace will keep reading from the beginning of a bucket and the process will never finish. "iter->offset" must always go forward until the whole bucket is consumed.

This patch fixes it by using a local variable "resume_offset" and "resume_bucket". "iter->offset" is always reset to 0 before it may be used. "iter->offset" will be advanced to the "resume_offset" when it continues from the "resume_bucket" (i.e. "state->bucket == resume_bucket"). This brings it closer to the bpf_iter_tcp's offset handling which does not suffer the same bug.

---
 net/ipv4/udp.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)
net/ipv4/udp.c +10 -11
index a4857c85a020..9cb22a6ae1dc 100644
@@ -3116,16 +3116,18 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
 	struct net *net = seq_file_net(seq);
+	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
 	bool resized = false;
 	struct sock *sk;
 
+	resume_bucket = state->bucket;
+	resume_offset = iter->offset;
+
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done) {
+	if (iter->st_bucket_done)
 		state->bucket++;
-		iter->offset = 0;
-	}
 
 	udptable = udp_get_table_seq(seq, net);
 
@@ -3145,19 +3147,19 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket];
 
-		if (hlist_empty(&hslot2->head)) {
-			iter->offset = 0;
+		if (hlist_empty(&hslot2->head))
 			continue;
-		}
 
+		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
 		udp_portaddr_for_each_entry(sk, &hslot2->head) {
 			if (seq_sk_match(seq, sk)) {
 				/* Resume from the last iterated socket at the
 				 * offset in the bucket before iterator was stopped.
 				 */
-				if (iter->offset) {
-					--iter->offset;
+				if (state->bucket == resume_bucket &&
+				    iter->offset < resume_offset) {
+					++iter->offset;
 					continue;
 				}
 				if (iter->end_sk < iter->max_sk) {
@@ -3171,9 +3173,6 @@ static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 
 		if (iter->end_sk)
 			break;
-
-		/* Reset the current bucket's offset before moving to the next bucket. */
-		iter->offset = 0;
 	}
 
 	/* All done: no batch made. */
Signature · 1 line
2.43.0
author maintainer
#552 lore raw

PATCH 546/583 net: tls, fix WARNIING in __sk_msg_free

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: John Fastabend <[email protected]>

[ Upstream commit dc9dfc8dc629e42f2234e3327b75324ffc752bc9 ]

A splice with MSG_SPLICE_PAGES will cause tls code to use the tls_sw_sendmsg_splice path in the TLS sendmsg code to move the user provided pages from the msg into the msg_pl. This will loop over the msg until msg_pl is full, checked by sk_msg_full(msg_pl). The user can also set the MORE flag to hint stack to delay sending until receiving more pages and ideally a full buffer.

If the user adds more pages to the msg than can fit in the msg_pl scatterlist (MAX_MSG_FRAGS) we should ignore the MORE flag and send the buffer anyways.

What actually happens though is we abort the msg to msg_pl scatterlist setup and then because we forget to set 'full record' indicating we can no longer consume data without a send we fallthrough to the 'continue' path which will check if msg_data_left(msg) has more bytes to send and then attempts to fit them in the already full msg_pl. Then next iteration of sender doing send will encounter a full msg_pl and throw the warning in the syzbot report.

To fix simply check if we have a full_record in splice code path and if not send the msg regardless of MORE flag.

Reported-and-tested-by [email protected]
Fixes fe1e81d4f73b ("tls/sw: Support MSG_SPLICE_PAGES")
---
 net/tls/tls_sw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
net/tls/tls_sw.c +5 -1
index 27cc0f0a90e1..dba523cdc73d 100644
@@ -1052,7 +1052,11 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			if (ret < 0)
 				goto send_end;
 			tls_ctx->pending_open_record_frags = true;
-			if (full_record || eor || sk_msg_full(msg_pl))
+
+			if (sk_msg_full(msg_pl))
+				full_record = true;
+
+			if (full_record || eor)
 				goto copied;
 			continue;
 		}
Signature · 1 line
2.43.0
author maintainer
#553 lore raw

PATCH 547/583 net: ravb: Fix dma_addr_t truncation in error case

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nikita Yushchenko <[email protected]>

[ Upstream commit e327b2372bc0f18c30433ac40be07741b59231c5 ]

In ravb_start_xmit(), ravb driver uses u32 variable to store result of dma_map_single() call. Since ravb hardware has 32-bit address fields in descriptors, this works properly when mapping is successful - it is platform's job to provide mapping addresses that fit into hardware limitations.

However, in failure case dma_map_single() returns DMA_MAPPING_ERROR constant that is 64-bit when dma_addr_t is 64-bit. Storing this constant in u32 leads to truncation, and further call to dma_mapping_error() fails to notice the error.

Fix that by storing result of dma_map_single() in a dma_addr_t variable.

---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/renesas/ravb_main.c +1 -1
index 3c2a6b23c202..8fec0dbbbe7b 100644
@@ -1949,7 +1949,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct ravb_tstamp_skb *ts_skb;
 	struct ravb_tx_desc *desc;
 	unsigned long flags;
-	u32 dma_addr;
+	dma_addr_t dma_addr;
 	void *buffer;
 	u32 entry;
 	u32 len;
Signature · 1 line
2.43.0
author maintainer
#554 lore raw

PATCH 548/583 dt-bindings: gpio: xilinx: Fix node address in gpio

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michal Simek <[email protected]>

[ Upstream commit 314c020c4ed3de72b15603eb6892250bc4b51702 ]

Node address doesn't match reg property which is not correct.

Fixes ba96b2e7974b ("dt-bindings: gpio: gpio-xilinx: Convert Xilinx axi gpio binding to YAML")
---
 Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml +1 -1
index c1060e5fcef3..d3d8a2e143ed 100644
@@ -126,7 +126,7 @@ examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
-        gpio@e000a000 {
+        gpio@a0020000 {
             compatible = "xlnx,xps-gpio-1.00.a";
             reg = <0xa0020000 0x10000>;
             #gpio-cells = <2>;
Signature · 1 line
2.43.0
author maintainer
#555 lore raw

PATCH 549/583 gpio: mlxbf3: add an error code check in mlxbf3_gpio_probe

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Su Hui <[email protected]>

[ Upstream commit d460e9c2075164e9b1fa9c4c95f8c05517bd8752 ]

Clang static checker warning: Value stored to 'ret' is never read. bgpio_init() returns error code if failed, it's better to add this check.

Fixes cd33f216d241 ("gpio: mlxbf3: Add gpio driver support")
[Bartosz: add the Fixes: tag]
---
 drivers/gpio/gpio-mlxbf3.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/gpio/gpio-mlxbf3.c +2 -0
index 7a3e1760fc5b..d5906d419b0a 100644
@@ -215,6 +215,8 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 			gs->gpio_clr_io + MLXBF_GPIO_FW_DATA_OUT_CLEAR,
 			gs->gpio_set_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_SET,
 			gs->gpio_clr_io + MLXBF_GPIO_FW_OUTPUT_ENABLE_CLEAR, 0);
+	if (ret)
+		return dev_err_probe(dev, ret, "%s: bgpio_init() failed", __func__);
 
 	gc->request = gpiochip_generic_request;
 	gc->free = gpiochip_generic_free;
Signature · 1 line
2.43.0
author maintainer
#556 lore raw

PATCH 550/583 ASoC: SOF: ipc4-loader: remove the CPC check warnings

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kai Vehmanen <[email protected]>

[ Upstream commit ab09fb9c629ed3aaea6a82467f08595dbc549726 ]

Warnings related to missing data in firmware manifest have proven to be too verbose. This relates to description of DSP module cost expressed in cycles per chunk (CPC). If a matching value is not found in the manifest, kernel will pass a zero value and DSP firmware will use a conservative value in its place.

Downgrade the warnings to dev_dbg().

---
 sound/soc/sof/ipc4-loader.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)
sound/soc/sof/ipc4-loader.c +4 -7
index eaa04762eb11..4d37e89b592a 100644
@@ -479,13 +479,10 @@ void sof_ipc4_update_cpc_from_manifest(struct snd_sof_dev *sdev,
 		msg = "No CPC match in the firmware file's manifest";
 
 no_cpc:
-	dev_warn(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
-		 fw_module->man4_module_entry.name,
-		 &fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
-		 basecfg->obs);
-	dev_warn_once(sdev->dev, "Please try to update the firmware.\n");
-	dev_warn_once(sdev->dev, "If the issue persists, file a bug at\n");
-	dev_warn_once(sdev->dev, "https://github.com/thesofproject/sof/issues/\n");
+	dev_dbg(sdev->dev, "%s (UUID: %pUL): %s (ibs/obs: %u/%u)\n",
+		fw_module->man4_module_entry.name,
+		&fw_module->man4_module_entry.uuid, msg, basecfg->ibs,
+		basecfg->obs);
 }
 
 const struct sof_ipc_fw_loader_ops ipc4_loader_ops = {
Signature · 1 line
2.43.0
author maintainer
#557 lore raw

PATCH 551/583 drm/amdkfd: fixes for HMM mem allocation

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dafna Hirschfeld <[email protected]>

[ Upstream commit 02eed83abc1395a1207591aafad9bcfc5cb1abcb ]

Fix err return value and reset pgmap->type after checking it.

Fixes c83dee9b6394 ("drm/amdkfd: add SPM support for SVM")
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +3 -3
index 7d82c7da223a..659313648b20 100644
@@ -1021,7 +1021,7 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	} else {
 		res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
 		if (IS_ERR(res))
-			return -ENOMEM;
+			return PTR_ERR(res);
 		pgmap->range.start = res->start;
 		pgmap->range.end = res->end;
 		pgmap->type = MEMORY_DEVICE_PRIVATE;
@@ -1037,10 +1037,10 @@ int kgd2kfd_init_zone_device(struct amdgpu_device *adev)
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
-		/* Disable SVM support capability */
-		pgmap->type = 0;
 		if (pgmap->type == MEMORY_DEVICE_PRIVATE)
 			devm_release_mem_region(adev->dev, res->start, resource_size(res));
+		/* Disable SVM support capability */
+		pgmap->type = 0;
 		return PTR_ERR(r);
 	}
 
Signature · 1 line
2.43.0
author maintainer
#558 lore raw

PATCH 552/583 drm/amdgpu: fall back to INPUT power for AVG power via INFO IOCTL

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Deucher <[email protected]>

[ Upstream commit d02069850fc102b07ae923535d5e212f2c8a34e9 ]

For backwards compatibility with userspace.

Fixes 47f1724db4fe ("drm/amd: Introduce `AMDGPU_PP_SENSOR_GPU_INPUT_POWER`")
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +6 -1
index d30dc0b718c7..58dab4f73a9a 100644
@@ -1026,7 +1026,12 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			if (amdgpu_dpm_read_sensor(adev,
 						   AMDGPU_PP_SENSOR_GPU_AVG_POWER,
 						   (void *)&ui32, &ui32_size)) {
-				return -EINVAL;
+				/* fall back to input power for backwards compat */
+				if (amdgpu_dpm_read_sensor(adev,
+							   AMDGPU_PP_SENSOR_GPU_INPUT_POWER,
+							   (void *)&ui32, &ui32_size)) {
+					return -EINVAL;
+				}
 			}
 			ui32 >>= 8;
 			break;
Signature · 1 line
2.43.0
author maintainer
#559 lore raw

PATCH 553/583 selftests: bonding: Change script interpreter

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Benjamin Poirier <[email protected]>

[ Upstream commit c2518da8e6b0e248cfff1d4b6682e14020bd4d3f ]

The tests changed by this patch, as well as the scripts they source, use features which are not part of POSIX sh (ex. 'source' and 'local'). As a result, these tests fail when /bin/sh is dash such as on Debian. Change the interpreter to bash so that these tests can run successfully.

Fixes d43eff0b85ae ("selftests: bonding: up/down delay w/ slave link flapping")
---
 .../selftests/drivers/net/bonding/mode-1-recovery-updelay.sh    | 2 +-
 .../selftests/drivers/net/bonding/mode-2-recovery-updelay.sh    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh +1 -1
index ad4c845a4ac7..b76bf5030952 100755
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh +1 -1
index 2330d37453f9..8c2619002147 100755
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
Signature · 1 line
2.43.0
author maintainer
#560 lore raw

PATCH 554/583 net: stmmac: ethtool: Fixed calltrace caused by unbalanced disable_irq_wake calls

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Qiang Ma <[email protected]>

[ Upstream commit a23aa04042187cbde16f470b49d4ad60d32e9206 ]

We found the following dmesg calltrace when testing the GMAC NIC notebook:

[9.448656] ------------[ cut here ]------------
[9.448658] Unbalanced IRQ 43 wake disable
[9.448673] WARNING: CPU: 3 PID: 1083 at kernel/irq/manage.c:688 irq_set_irq_wake+0xe0/0x128
[9.448717] CPU: 3 PID: 1083 Comm: ethtool Tainted: G           O      4.19 #1
[9.448773]         ...
[9.448774] Call Trace:
[9.448781] [<9000000000209b5c>] show_stack+0x34/0x140
[9.448788] [<9000000000d52700>] dump_stack+0x98/0xd0
[9.448794] [<9000000000228610>] __warn+0xa8/0x120
[9.448797] [<9000000000d2fb60>] report_bug+0x98/0x130
[9.448800] [<900000000020a418>] do_bp+0x248/0x2f0
[9.448805] [<90000000002035f4>] handle_bp_int+0x4c/0x78
[9.448808] [<900000000029ea40>] irq_set_irq_wake+0xe0/0x128
[9.448813] [<9000000000a96a7c>] stmmac_set_wol+0x134/0x150
[9.448819] [<9000000000be6ed0>] dev_ethtool+0x1368/0x2440
[9.448824] [<9000000000c08350>] dev_ioctl+0x1f8/0x3e0
[9.448827] [<9000000000bb2a34>] sock_ioctl+0x2a4/0x450
[9.448832] [<900000000046f044>] do_vfs_ioctl+0xa4/0x738
[9.448834] [<900000000046f778>] ksys_ioctl+0xa0/0xe8
[9.448837] [<900000000046f7d8>] sys_ioctl+0x18/0x28
[9.448840] [<9000000000211ab4>] syscall_common+0x20/0x34
[9.448842] ---[ end trace 40c18d9aec863c3e ]---

Multiple disable_irq_wake() calls will keep decreasing the IRQ wake_depth, When wake_depth is 0, calling disable_irq_wake() again, will report the above calltrace.

Due to the need to appear in pairs, we cannot call disable_irq_wake() without calling enable_irq_wake(). Fix this by making sure there are no unbalanced disable_irq_wake() calls.

Fixes 3172d3afa998 ("stmmac: support wake up irq from external sources (v3)")
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h         |  1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 10 ++++++++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c    |  1 +
 3 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/ethernet/stmicro/stmmac/stmmac.h +1 -0
index cd7a9768de5f..b8c93b881a65 100644
@@ -255,6 +255,7 @@ struct stmmac_priv {
 	u32 msg_enable;
 	int wolopts;
 	int wol_irq;
+	bool wol_irq_disabled;
 	int clk_csr;
 	struct timer_list eee_ctrl_timer;
 	int lpi_irq;
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +8 -2
index 419efe43951e..69c8c2528524 100644
@@ -822,10 +822,16 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (wol->wolopts) {
 		pr_info("stmmac: wakeup enable\n");
 		device_set_wakeup_enable(priv->device, 1);
-		enable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced enable_irq_wake calls */
+		if (priv->wol_irq_disabled)
+			enable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = false;
 	} else {
 		device_set_wakeup_enable(priv->device, 0);
-		disable_irq_wake(priv->wol_irq);
+		/* Avoid unbalanced disable_irq_wake calls */
+		if (!priv->wol_irq_disabled)
+			disable_irq_wake(priv->wol_irq);
+		priv->wol_irq_disabled = true;
 	}
 
 	mutex_lock(&priv->lock);
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +1 -0
index 69b9c71f0ede..1bfcf673b3ce 100644
@@ -3549,6 +3549,7 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 	/* Request the Wake IRQ in case of another line
 	 * is used for WoL
 	 */
+	priv->wol_irq_disabled = true;
 	if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) {
 		int_name = priv->int_name_wol;
 		sprintf(int_name, "%s:%s", dev->name, "wol");
Signature · 1 line
2.43.0
author maintainer
#561 lore raw

PATCH 555/583 bpf: Reject variable offset alu on PTR_TO_FLOW_KEYS

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hao Sun <[email protected]>

[ Upstream commit 22c7fa171a02d310e3a3f6ed46a698ca8a0060ed ]

For PTR_TO_FLOW_KEYS, check_flow_keys_access() only uses fixed off for validation. However, variable offset ptr alu is not prohibited for this ptr kind. So the variable offset is not checked.

The following prog is accepted:

func#0 @0
0: R1=ctx() R10=fp0

  0: (bf) r6 = r1                       ; R1=ctx() R6_w=ctx()
  1: (79) r7 = *(u64 *)(r6 +144)        ; R6_w=ctx() R7_w=flow_keys()
  2: (b7) r8 = 1024                     ; R8_w=1024
  3: (37) r8 /= 1                       ; R8_w=scalar()
  4: (57) r8 &= 1024                    ; R8_w=scalar(smin=smin32=0,

smax=umax=smax32=umax32=1024,var_off=(0x0; 0x400))
5: (0f) r7 += r8
mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1
mark_precise: frame0: regs=r8 stack= before 4: (57) r8 &= 1024
mark_precise: frame0: regs=r8 stack= before 3: (37) r8 /= 1
mark_precise: frame0: regs=r8 stack= before 2: (b7) r8 = 1024 6: R7_w=flow_keys(smin=smin32=0,smax=umax=smax32=umax32=1024,var_off =(0x0; 0x400)) R8_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=1024, var_off=(0x0; 0x400))
6: (79) r0 = *(u64 *)(r7 +0) ; R0_w=scalar()
7: (95) exit

This prog loads flow_keys to r7, and adds the variable offset r8 to r7, and finally causes out-of-bounds access:

  BUG: unable to handle page fault for address: ffffc90014c80038
  [...]
  Call Trace:
   <TASK>
   bpf_dispatcher_nop_func include/linux/bpf.h:1231 [inline]
   __bpf_prog_run include/linux/filter.h:651 [inline]
   bpf_prog_run include/linux/filter.h:658 [inline]
   bpf_prog_run_pin_on_cpu include/linux/filter.h:675 [inline]
   bpf_flow_dissect+0x15f/0x350 net/core/flow_dissector.c:991
   bpf_prog_test_run_flow_dissector+0x39d/0x620 net/bpf/test_run.c:1359
   bpf_prog_test_run kernel/bpf/syscall.c:4107 [inline]
   __sys_bpf+0xf8f/0x4560 kernel/bpf/syscall.c:5475
   __do_sys_bpf kernel/bpf/syscall.c:5561 [inline]
   __se_sys_bpf kernel/bpf/syscall.c:5559 [inline]
   __x64_sys_bpf+0x73/0xb0 kernel/bpf/syscall.c:5559
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x63/0x6b

Fix this by rejecting ptr alu with variable offset on flow_keys. Applying the patch rejects the program with "R7 pointer arithmetic on flow_keys prohibited".

Fixes d58e468b1112 ("flow_dissector: implements flow dissector BPF hook")
---
 kernel/bpf/verifier.c | 4 ++++
 1 file changed, 4 insertions(+)
kernel/bpf/verifier.c +4 -0
index ed24ad2e5bd2..97fd1766818b 100644
@@ -12087,6 +12087,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	}
 
 	switch (base_type(ptr_reg->type)) {
+	case PTR_TO_FLOW_KEYS:
+		if (known)
+			break;
+		fallthrough;
 	case CONST_PTR_TO_MAP:
 		/* smin_val represents the known value */
 		if (known && smin_val == 0 && opcode == BPF_ADD)
Signature · 1 line
2.43.0
author maintainer
#562 lore raw

PATCH 556/583 net: dsa: vsc73xx: Add null pointer check to vsc73xx_gpio_probe

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kunwu Chan <[email protected]>

[ Upstream commit 776dac5a662774f07a876b650ba578d0a62d20db ]

devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure.

---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/net/dsa/vitesse-vsc73xx-core.c +2 -0
index 4f09e7438f3b..c99fb1bd4c25 100644
@@ -1118,6 +1118,8 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
 
 	vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
 				       vsc->chipid);
+	if (!vsc->gc.label)
+		return -ENOMEM;
 	vsc->gc.ngpio = 4;
 	vsc->gc.owner = THIS_MODULE;
 	vsc->gc.parent = vsc->dev;
Signature · 1 line
2.43.0
author maintainer
#563 lore raw

PATCH 557/583 LoongArch: BPF: Prevent out-of-bounds memory access

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hengqi Chen <[email protected]>

[ Upstream commit 36a87385e31c9343af9a4756598e704741250a67 ]

The test_tag test triggers an unhandled page fault:

  # ./test_tag
  [  130.640218] CPU 0 Unable to handle kernel paging request at virtual address ffff80001b898004, era == 9000000003137f7c, ra == 9000000003139e70
  [  130.640501] Oops[#3]:
  [  130.640553] CPU: 0 PID: 1326 Comm: test_tag Tainted: G      D    O       6.7.0-rc4-loong-devel-gb62ab1a397cf #47 61985c1d94084daa2432f771daa45b56b10d8d2a
  [  130.640764] Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
  [  130.640874] pc 9000000003137f7c ra 9000000003139e70 tp 9000000104cb4000 sp 9000000104cb7a40
  [  130.641001] a0 ffff80001b894000 a1 ffff80001b897ff8 a2 000000006ba210be a3 0000000000000000
  [  130.641128] a4 000000006ba210be a5 00000000000000f1 a6 00000000000000b3 a7 0000000000000000
  [  130.641256] t0 0000000000000000 t1 00000000000007f6 t2 0000000000000000 t3 9000000004091b70
  [  130.641387] t4 000000006ba210be t5 0000000000000004 t6 fffffffffffffff0 t7 90000000040913e0
  [  130.641512] t8 0000000000000005 u0 0000000000000dc0 s9 0000000000000009 s0 9000000104cb7ae0
  [  130.641641] s1 00000000000007f6 s2 0000000000000009 s3 0000000000000095 s4 0000000000000000
  [  130.641771] s5 ffff80001b894000 s6 ffff80001b897fb0 s7 9000000004090c50 s8 0000000000000000
  [  130.641900]    ra: 9000000003139e70 build_body+0x1fcc/0x4988
  [  130.642007]   ERA: 9000000003137f7c build_body+0xd8/0x4988
  [  130.642112]  CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
  [  130.642261]  PRMD: 00000004 (PPLV0 +PIE -PWE)
  [  130.642353]  EUEN: 00000003 (+FPE +SXE -ASXE -BTE)
  [  130.642458]  ECFG: 00071c1c (LIE=2-4,10-12 VS=7)
  [  130.642554] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0)
  [  130.642658]  BADV: ffff80001b898004
  [  130.642719]  PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
  [  130.642815] Modules linked in: [last unloaded: bpf_testmod(O)]
  [  130.642924] Process test_tag (pid: 1326, threadinfo=00000000f7f4015f, task=000000006499f9fd)
  [  130.643062] Stack : 0000000000000000 9000000003380724 0000000000000000 0000000104cb7be8
  [  130.643213]         0000000000000000 25af8d9b6e600558 9000000106250ea0 9000000104cb7ae0
  [  130.643378]         0000000000000000 0000000000000000 9000000104cb7be8 90000000049f6000
  [  130.643538]         0000000000000090 9000000106250ea0 ffff80001b894000 ffff80001b894000
  [  130.643685]         00007ffffb917790 900000000313ca94 0000000000000000 0000000000000000
  [  130.643831]         ffff80001b894000 0000000000000ff7 0000000000000000 9000000100468000
  [  130.643983]         0000000000000000 0000000000000000 0000000000000040 25af8d9b6e600558
  [  130.644131]         0000000000000bb7 ffff80001b894048 0000000000000000 0000000000000000
  [  130.644276]         9000000104cb7be8 90000000049f6000 0000000000000090 9000000104cb7bdc
  [  130.644423]         ffff80001b894000 0000000000000000 00007ffffb917790 90000000032acfb0
  [  130.644572]         ...
  [  130.644629] Call Trace:
  [  130.644641] [<9000000003137f7c>] build_body+0xd8/0x4988
  [  130.644785] [<900000000313ca94>] bpf_int_jit_compile+0x228/0x4ec
  [  130.644891] [<90000000032acfb0>] bpf_prog_select_runtime+0x158/0x1b0
  [  130.645003] [<90000000032b3504>] bpf_prog_load+0x760/0xb44
  [  130.645089] [<90000000032b6744>] __sys_bpf+0xbb8/0x2588
  [  130.645175] [<90000000032b8388>] sys_bpf+0x20/0x2c
  [  130.645259] [<9000000003f6ab38>] do_syscall+0x7c/0x94
  [  130.645369] [<9000000003121c5c>] handle_syscall+0xbc/0x158
  [  130.645507]
  [  130.645539] Code: 380839f6  380831f9  28412bae <24000ca6> 004081ad  0014cb50  004083e8  02bff34c  58008e91
  [  130.645729]
  [  130.646418] ---[ end trace 0000000000000000 ]---

On my machine, which has CONFIG_PAGE_SIZE_16KB=y, the test failed at loading a BPF prog with 2039 instructions:

prog = (struct bpf_prog *)ffff80001b894000
insn = (struct bpf_insn *)(prog->insnsi)ffff80001b894048 insn + 2039 = (struct bpf_insn *)ffff80001b898000 <- end of the page

In the build_insn() function, we are trying to access next instruction unconditionally, i.e. (insn + 1)->imm. The address lies in the next page and can be not owned by the current process, thus an page fault is inevitable and then segfault.

So, let's access next instruction only under dst = imm64 context.

With this fix, we have:

  # ./test_tag
  test_tag: OK (40945 tests)
Fixes bbfddb904df6f82 ("LoongArch: BPF: Avoid declare variables in switch-case")
---
 arch/loongarch/net/bpf_jit.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
arch/loongarch/net/bpf_jit.c +4 -1
index 00915fb3cb82..9eb7753d117d 100644
@@ -461,7 +461,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	const u8 dst = regmap[insn->dst_reg];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
-	const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
 	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
 
 	switch (code) {
@@ -865,8 +864,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
+	{
+		const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+
 		move_imm(ctx, dst, imm64, is32);
 		return 1;
+	}
 
 	/* dst = *(size *)(src + off) */
 	case BPF_LDX | BPF_MEM | BPF_B:
Signature · 1 line
2.43.0
author maintainer
#564 lore raw

PATCH 558/583 mptcp: relax check on MPC passive fallback

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni <[email protected]>

[ Upstream commit c0f5aec28edf98906d28f08daace6522adf9ee7a ]

While testing the blamed commit below, I was able to miss (!) packetdrill failures in the fastopen test-cases.

On passive fastopen the child socket is created by incoming TCP MPC syn, allow for both MPC_SYN and MPC_ACK header.

Fixes 724b00c12957 ("mptcp: refine opt_mp_capable determination")
---
 net/mptcp/subflow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/mptcp/subflow.c +2 -1
index 70b7a47a53c7..d3c5ecf8ddf5 100644
@@ -783,7 +783,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * options.
 		 */
 		mptcp_get_options(skb, &mp_opt);
-		if (!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK))
+		if (!(mp_opt.suboptions &
+		      (OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_ACK)))
 			fallback = true;
 
 	} else if (subflow_req->mp_join) {
Signature · 1 line
2.43.0
author maintainer
#565 lore raw

PATCH 559/583 net: netdevsim: dont try to destroy PHC on VFs

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

[ Upstream commit ea937f77208323d35ffe2f8d8fc81b00118bfcda ]

PHC gets initialized in nsim_init_netdevsim(), which is only called if (nsim_dev_port_is_pf()).

Create a counterpart of nsim_init_netdevsim() and move the mock_phc_destroy() there.

This fixes a crash trying to destroy netdevsim with VFs instantiated, as caught by running the devlink.sh test:

    BUG: kernel NULL pointer dereference, address: 00000000000000b8
    RIP: 0010:mock_phc_destroy+0xd/0x30
    Call Trace:
     <TASK>
     nsim_destroy+0x4a/0x70 [netdevsim]
     __nsim_dev_port_del+0x47/0x70 [netdevsim]
     nsim_dev_reload_destroy+0x105/0x120 [netdevsim]
     nsim_drv_remove+0x2f/0xb0 [netdevsim]
     device_release_driver_internal+0x1a1/0x210
     bus_remove_device+0xd5/0x120
     device_del+0x159/0x490
     device_unregister+0x12/0x30
     del_device_store+0x11a/0x1a0 [netdevsim]
     kernfs_fop_write_iter+0x130/0x1d0
     vfs_write+0x30b/0x4b0
     ksys_write+0x69/0xf0
     do_syscall_64+0xcc/0x1e0
     entry_SYSCALL_64_after_hwframe+0x6f/0x77
Fixes b63e78fca889 ("net: netdevsim: use mock PHC driver")
---
 drivers/net/netdevsim/netdev.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/net/netdevsim/netdev.c +7 -2
index 2eac92f49631..d8ca82addfe1 100644
@@ -369,6 +369,12 @@ static int nsim_init_netdevsim_vf(struct netdevsim *ns)
 	return err;
 }
 
+static void nsim_exit_netdevsim(struct netdevsim *ns)
+{
+	nsim_udp_tunnels_info_destroy(ns->netdev);
+	mock_phc_destroy(ns->phc);
+}
+
 struct netdevsim *
 nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 {
@@ -417,8 +423,7 @@ void nsim_destroy(struct netdevsim *ns)
 	}
 	rtnl_unlock();
 	if (nsim_dev_port_is_pf(ns->nsim_dev_port))
-		nsim_udp_tunnels_info_destroy(dev);
-	mock_phc_destroy(ns->phc);
+		nsim_exit_netdevsim(ns);
 	free_netdev(dev);
 }
 
Signature · 1 line
2.43.0
author maintainer
#566 lore raw

PATCH 560/583 netfilter: nf_tables: reject invalid set policy

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 0617c3de9b4026b87be12b0cb5c35f42c7c66fcb ]

Report -EINVAL in case userspace provides a unsupported set backend policy.

Fixes c50b960ccc59 ("netfilter: nf_tables: implement proper set selection")
---
 net/netfilter/nf_tables_api.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
net/netfilter/nf_tables_api.c +9 -1
index 5200bd804954..55cd82190888 100644
@@ -4990,8 +4990,16 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 	}
 
 	desc.policy = NFT_SET_POL_PERFORMANCE;
-	if (nla[NFTA_SET_POLICY] != NULL)
+	if (nla[NFTA_SET_POLICY] != NULL) {
 		desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+		switch (desc.policy) {
+		case NFT_SET_POL_PERFORMANCE:
+		case NFT_SET_POL_MEMORY:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
 
 	if (nla[NFTA_SET_DESC] != NULL) {
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
Signature · 1 line
2.43.0
author maintainer
#567 lore raw

PATCH 561/583 netfilter: nft_limit: do not ignore unsupported flags

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 91a139cee1202a4599a380810d93c69b5bac6197 ]

Bail out if userspace provides unsupported flags, otherwise future extensions to the limit expression will be silently ignored by the kernel.

Fixes c7862a5f0de5 ("netfilter: nft_limit: allow to invert matching criteria")
---
 net/netfilter/nft_limit.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)
net/netfilter/nft_limit.c +12 -7
index 145dc62c6247..79039afde34e 100644
@@ -58,6 +58,7 @@ static inline bool nft_limit_eval(struct nft_limit_priv *priv, u64 cost)
 static int nft_limit_init(struct nft_limit_priv *priv,
 			  const struct nlattr * const tb[], bool pkts)
 {
+	bool invert = false;
 	u64 unit, tokens;
 
 	if (tb[NFTA_LIMIT_RATE] == NULL ||
@@ -90,19 +91,23 @@ static int nft_limit_init(struct nft_limit_priv *priv,
 				 priv->rate);
 	}
 
+	if (tb[NFTA_LIMIT_FLAGS]) {
+		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
+
+		if (flags & ~NFT_LIMIT_F_INV)
+			return -EOPNOTSUPP;
+
+		if (flags & NFT_LIMIT_F_INV)
+			invert = true;
+	}
+
 	priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT);
 	if (!priv->limit)
 		return -ENOMEM;
 
 	priv->limit->tokens = tokens;
 	priv->tokens_max = priv->limit->tokens;
-
-	if (tb[NFTA_LIMIT_FLAGS]) {
-		u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS]));
-
-		if (flags & NFT_LIMIT_F_INV)
-			priv->invert = true;
-	}
+	priv->invert = invert;
 	priv->limit->last = ktime_get_ns();
 	spin_lock_init(&priv->limit->lock);
 
Signature · 1 line
2.43.0
author maintainer
#568 lore raw

PATCH 562/583 netfilter: nfnetlink_log: use proper helper for fetching physinif

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Tikhomirov <[email protected]>

[ Upstream commit c3f9fd54cd87233f53bdf0e191a86b3a5e960e02 ]

We don't use physindev in __build_packet_message except for getting physinif from it. So let's switch to nf_bridge_get_physinif to get what we want directly.

Stable-dep-of: 9874808878d9 ("netfilter: bridge: replace physindev with physinif in nf_bridge_info")

---
 net/netfilter/nfnetlink_log.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
net/netfilter/nfnetlink_log.c +4 -4
index f03f4d4d7d88..134e05d31061 100644
@@ -508,7 +508,7 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
 				goto nla_put_failure;
 		} else {
-			struct net_device *physindev;
+			int physinif;
 
 			/* Case 2: indev is bridge group, we need to look for
 			 * physical device (when called from ipv4) */
@@ -516,10 +516,10 @@ __build_packet_message(struct nfnl_log_net *log,
 					 htonl(indev->ifindex)))
 				goto nla_put_failure;
 
-			physindev = nf_bridge_get_physindev(skb);
-			if (physindev &&
+			physinif = nf_bridge_get_physinif(skb);
+			if (physinif &&
 			    nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
-					 htonl(physindev->ifindex)))
+					 htonl(physinif)))
 				goto nla_put_failure;
 		}
 #endif
Signature · 1 line
2.43.0
author maintainer
#569 lore raw

PATCH 563/583 netfilter: nf_queue: remove excess nf_bridge variable

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Tikhomirov <[email protected]>

[ Upstream commit aeaa44075f8e49e2e0ad4507d925e690b7950145 ]

We don't really need nf_bridge variable here. And nf_bridge_info_exists is better replacement for nf_bridge_info_get in case we are only checking for existence.

Stable-dep-of: 9874808878d9 ("netfilter: bridge: replace physindev with physinif in nf_bridge_info")

---
 net/netfilter/nf_queue.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
net/netfilter/nf_queue.c +1 -3
index 63d1516816b1..3dfcb3ac5cb4 100644
@@ -82,10 +82,8 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	const struct sk_buff *skb = entry->skb;
-	struct nf_bridge_info *nf_bridge;
 
-	nf_bridge = nf_bridge_info_get(skb);
-	if (nf_bridge) {
+	if (nf_bridge_info_exists(skb)) {
 		entry->physin = nf_bridge_get_physindev(skb);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
Signature · 1 line
2.43.0
author maintainer
#570 lore raw

PATCH 564/583 netfilter: propagate net to nf_bridge_get_physindev

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Tikhomirov <[email protected]>

[ Upstream commit a54e72197037d2c9bfcd70dddaac8c8ccb5b41ba ]

This is a preparation patch for replacing physindev with physinif on nf_bridge_info structure. We will use dev_get_by_index_rcu to resolve device, when needed, and it requires net to be available.

Stable-dep-of: 9874808878d9 ("netfilter: bridge: replace physindev with physinif in nf_bridge_info")

---
 include/linux/netfilter_bridge.h           |  2 +-
 net/ipv4/netfilter/nf_reject_ipv4.c        |  2 +-
 net/ipv6/netfilter/nf_reject_ipv6.c        |  2 +-
 net/netfilter/ipset/ip_set_hash_netiface.c |  8 ++++----
 net/netfilter/nf_log_syslog.c              | 13 +++++++------
 net/netfilter/nf_queue.c                   |  2 +-
 net/netfilter/xt_physdev.c                 |  2 +-
 7 files changed, 16 insertions(+), 15 deletions(-)
include/linux/netfilter_bridge.h +1 -1
index f980edfdd278..e927b9a15a55 100644
@@ -56,7 +56,7 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 }
 
 static inline struct net_device *
-nf_bridge_get_physindev(const struct sk_buff *skb)
+nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
net/ipv4/netfilter/nf_reject_ipv4.c +1 -1
index f33aeab9424f..297000b05f18 100644
@@ -289,7 +289,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
net/ipv6/netfilter/nf_reject_ipv6.c +1 -1
index 58ccdb08c0fd..0a5ef7abf583 100644
@@ -354,7 +354,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb);
+	br_indev = nf_bridge_get_physindev(oldskb, net);
 	if (br_indev) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
 
net/netfilter/ipset/ip_set_hash_netiface.c +4 -4
index 95aeb31c60e0..30a655e5c4fd 100644
@@ -138,9 +138,9 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #include "ip_set_hash_gen.h"
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-static const char *get_physindev_name(const struct sk_buff *skb)
+static const char *get_physindev_name(const struct sk_buff *skb, struct net *net)
 {
-	struct net_device *dev = nf_bridge_get_physindev(skb);
+	struct net_device *dev = nf_bridge_get_physindev(skb, net);
 
 	return dev ? dev->name : NULL;
 }
@@ -177,7 +177,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
@@ -395,7 +395,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const char *eiface = SRCDIR ? get_physindev_name(skb) :
+		const char *eiface = SRCDIR ? get_physindev_name(skb, xt_net(par)) :
 					      get_physoutdev_name(skb);
 
 		if (!eiface)
net/netfilter/nf_log_syslog.c +7 -6
index c66689ad2b49..58402226045e 100644
@@ -111,7 +111,8 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			  unsigned int hooknum, const struct sk_buff *skb,
 			  const struct net_device *in,
 			  const struct net_device *out,
-			  const struct nf_loginfo *loginfo, const char *prefix)
+			  const struct nf_loginfo *loginfo, const char *prefix,
+			  struct net *net)
 {
 	const struct net_device *physoutdev __maybe_unused;
 	const struct net_device *physindev __maybe_unused;
@@ -121,7 +122,7 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u8 pf,
 			in ? in->name : "",
 			out ? out->name : "");
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	physindev = nf_bridge_get_physindev(skb);
+	physindev = nf_bridge_get_physindev(skb, net);
 	if (physindev && in != physindev)
 		nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
 	physoutdev = nf_bridge_get_physoutdev(skb);
@@ -148,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 	dump_arp_packet(m, loginfo, skb, skb_network_offset(skb));
 
 	nf_log_buf_close(m);
@@ -845,7 +846,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in,
-				  out, loginfo, prefix);
+				  out, loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -880,7 +881,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out,
-				  loginfo, prefix);
+				  loginfo, prefix, net);
 
 	if (in)
 		dump_mac_header(m, loginfo, skb);
@@ -916,7 +917,7 @@ static void nf_log_unknown_packet(struct net *net, u_int8_t pf,
 		loginfo = &default_loginfo;
 
 	nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo,
-				  prefix);
+				  prefix, net);
 
 	dump_mac_header(m, loginfo, skb);
 
net/netfilter/nf_queue.c +1 -1
index 3dfcb3ac5cb4..e2f334f70281 100644
@@ -84,7 +84,7 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry)
 	const struct sk_buff *skb = entry->skb;
 
 	if (nf_bridge_info_exists(skb)) {
-		entry->physin = nf_bridge_get_physindev(skb);
+		entry->physin = nf_bridge_get_physindev(skb, entry->state.net);
 		entry->physout = nf_bridge_get_physoutdev(skb);
 	} else {
 		entry->physin = NULL;
net/netfilter/xt_physdev.c +1 -1
index ec6ed6fda96c..343e65f377d4 100644
@@ -59,7 +59,7 @@ physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	    (!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
 		return false;
 
-	physdev = nf_bridge_get_physindev(skb);
+	physdev = nf_bridge_get_physindev(skb, xt_net(par));
 	indev = physdev ? physdev->name : NULL;
 
 	if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
Signature · 1 line
2.43.0
author maintainer
#571 lore raw

PATCH 565/583 netfilter: bridge: replace physindev with physinif in nf_bridge_info

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Tikhomirov <[email protected]>

[ Upstream commit 9874808878d9eed407e3977fd11fee49de1e1d86 ]

An skb can be added to a neigh->arp_queue while waiting for an arp reply. Where original skb's skb->dev can be different to neigh's neigh->dev. For instance in case of bridging dnated skb from one veth to another, the skb would be added to a neigh->arp_queue of the bridge.

As skb->dev can be reset back to nf_bridge->physindev and used, and as there is no explicit mechanism that prevents this physindev from been freed under us (for instance neigh_flush_dev doesn't cleanup skbs from different device's neigh queue) we can crash on e.g. this stack:

arp_process
neigh_update

    skb = __skb_dequeue(&neigh->arp_queue)
      neigh_resolve_output(..., skb)
        ...
          br_nf_dev_xmit
            br_nf_pre_routing_finish_bridge_slow
              skb->dev = nf_bridge->physindev
              br_handle_frame_finish

Let's use plain ifindex instead of net_device link. To peek into the original net_device we will use dev_get_by_index_rcu(). Thus either we get device and are safe to use it or we don't get it and drop skb.

Fixes c4e70a87d975 ("netfilter: bridge: rename br_netfilter.c to br_netfilter_hooks.c")
---
 include/linux/netfilter_bridge.h    |  4 +--
 include/linux/skbuff.h              |  2 +-
 net/bridge/br_netfilter_hooks.c     | 42 +++++++++++++++++++++++------
 net/bridge/br_netfilter_ipv6.c      | 14 +++++++---
 net/ipv4/netfilter/nf_reject_ipv4.c |  9 ++++---
 net/ipv6/netfilter/nf_reject_ipv6.c | 11 +++++---
 6 files changed, 61 insertions(+), 21 deletions(-)
include/linux/netfilter_bridge.h +2 -2
index e927b9a15a55..743475ca7e9d 100644
@@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 	if (!nf_bridge)
 		return 0;
 
-	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
+	return nf_bridge->physinif;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
@@ -60,7 +60,7 @@ nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	return nf_bridge ? nf_bridge->physindev : NULL;
+	return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL;
 }
 
 static inline struct net_device *
include/linux/skbuff.h +1 -1
index 97bfef071255..ddfe86deb4e7 100644
@@ -295,7 +295,7 @@ struct nf_bridge_info {
 	u8			bridged_dnat:1;
 	u8			sabotage_in_done:1;
 	__u16			frag_max_size;
-	struct net_device	*physindev;
+	int			physinif;
 
 	/* always valid & non-NULL from FORWARD on, for physdev match */
 	struct net_device	*physoutdev;
net/bridge/br_netfilter_hooks.c +34 -8

102 lines not on this page · raw message

net/bridge/br_netfilter_ipv6.c +10 -4
index 550039dfc31a..ad268bd19d5b 100644
@@ -102,9 +102,15 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
-	struct net_device *dev = skb->dev;
+	struct net_device *dev = skb->dev, *br_indev;
 	const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 
+	br_indev = nf_bridge_get_physindev(skb, net);
+	if (!br_indev) {
+		kfree_skb(skb);
+		return 0;
+	}
+
 	nf_bridge->frag_max_size = IP6CB(skb)->frag_max_size;
 
 	if (nf_bridge->pkt_otherhost) {
@@ -122,7 +128,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		}
 
 		if (skb_dst(skb)->dev == dev) {
-			skb->dev = nf_bridge->physindev;
+			skb->dev = br_indev;
 			nf_bridge_update_protocol(skb);
 			nf_bridge_push_encap_header(skb);
 			br_nf_hook_thresh(NF_BR_PRE_ROUTING,
@@ -133,7 +139,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
 		skb->pkt_type = PACKET_HOST;
 	} else {
-		rt = bridge_parent_rtable(nf_bridge->physindev);
+		rt = bridge_parent_rtable(br_indev);
 		if (!rt) {
 			kfree_skb(skb);
 			return 0;
@@ -142,7 +148,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc
 		skb_dst_set_noref(skb, &rt->dst);
 	}
 
-	skb->dev = nf_bridge->physindev;
+	skb->dev = br_indev;
 	nf_bridge_update_protocol(skb);
 	nf_bridge_push_encap_header(skb);
 	br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb,
net/ipv4/netfilter/nf_reject_ipv4.c +6 -3
index 297000b05f18..fc761915c5f6 100644
@@ -239,7 +239,6 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		   int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct iphdr *niph;
 	const struct tcphdr *oth;
@@ -289,9 +288,13 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev)
+			goto free_nskb;
 
 		nskb->dev = br_indev;
 		niph->tot_len = htons(nskb->len);
net/ipv6/netfilter/nf_reject_ipv6.c +8 -3
index 0a5ef7abf583..71d692728230 100644
@@ -278,7 +278,6 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 		    int hook)
 {
-	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
 	struct tcphdr _otcph;
 	const struct tcphdr *otcph;
@@ -354,9 +353,15 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	 * build the eth header using the original destination's MAC as the
 	 * source, and send the RST packet directly.
 	 */
-	br_indev = nf_bridge_get_physindev(oldskb, net);
-	if (br_indev) {
+	if (nf_bridge_info_exists(oldskb)) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
+		struct net_device *br_indev;
+
+		br_indev = nf_bridge_get_physindev(oldskb, net);
+		if (!br_indev) {
+			kfree_skb(nskb);
+			return;
+		}
 
 		nskb->dev = br_indev;
 		nskb->protocol = htons(ETH_P_IPV6);
Signature · 1 line
2.43.0
author maintainer
#572 lore raw

PATCH 566/583 netfilter: nf_tables: do not allow mismatch field size and set key length

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 3ce67e3793f48c1b9635beb9bb71116ca1e51b58 ]

The set description provides the size of each field in the set whose sum should not mismatch the set key length, bail out otherwise.

I did not manage to crash nft_set_pipapo with mismatch fields and set key length so far, but this is UB which must be disallowed.

Fixes f3a2181e16f1 ("netfilter: nf_tables: Support for sets with multiple ranged fields")
---
 net/netfilter/nf_tables_api.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
net/netfilter/nf_tables_api.c +5 -1
index 55cd82190888..5730f9a1f47d 100644
@@ -4753,8 +4753,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr,
 static int nft_set_desc_concat(struct nft_set_desc *desc,
 			       const struct nlattr *nla)
 {
+	u32 num_regs = 0, key_num_regs = 0;
 	struct nlattr *attr;
-	u32 num_regs = 0;
 	int rem, err, i;
 
 	nla_for_each_nested(attr, nla, rem) {
@@ -4769,6 +4769,10 @@ static int nft_set_desc_concat(struct nft_set_desc *desc,
 	for (i = 0; i < desc->field_count; i++)
 		num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32));
 
+	key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32));
+	if (key_num_regs != num_regs)
+		return -EINVAL;
+
 	if (num_regs > NFT_REG32_COUNT)
 		return -E2BIG;
 
Signature · 1 line
2.43.0
author maintainer
#573 lore raw

PATCH 567/583 netfilter: nf_tables: skip dead set elements in netlink dump

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 6b1ca88e4bb63673dc9f9c7f23c899f22c3cb17a ]

Delete from packet path relies on the garbage collector to purge elements with NFT_SET_ELEM_DEAD_BIT on.

Skip these dead elements from nf_tables_dump_setelem() path, I very rarely see tests/shell/testcases/maps/typeof_maps_add_delete reports [DUMP FAILED] showing a mismatch in the expected output with an element that should not be there.

If the netlink dump happens before GC worker run, it might show dead elements in the ruleset listing.

nft_rhash_get() already skips dead elements in nft_rhash_cmp(), therefore, it already does not show the element when getting a single element via netlink control plane.

Fixes 5f68718b34a5 ("netfilter: nf_tables: GC transaction API to avoid race with control plane")
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/nf_tables_api.c +1 -1
index 5730f9a1f47d..1f6d5ffbe34a 100644
@@ -5662,7 +5662,7 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_set_dump_args *args;
 
-	if (nft_set_elem_expired(ext))
+	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
 	args = container_of(iter, struct nft_set_dump_args, iter);
Signature · 1 line
2.43.0
author maintainer
#574 lore raw

PATCH 568/583 netfilter: nf_tables: reject NFT_SET_CONCAT with not field length description

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 113661e07460a6604aacc8ae1b23695a89e7d4b3 ]

It is still possible to set on the NFT_SET_CONCAT flag by specifying a set size and no field description, report EINVAL in such case.

Fixes 1b6345d4160e ("netfilter: nf_tables: check NFT_SET_CONCAT flag if field_count is specified")
---
 net/netfilter/nf_tables_api.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
net/netfilter/nf_tables_api.c +5 -1
index 1f6d5ffbe34a..b28fbcb86e94 100644
@@ -5010,8 +5010,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 		if (err < 0)
 			return err;
 
-		if (desc.field_count > 1 && !(flags & NFT_SET_CONCAT))
+		if (desc.field_count > 1) {
+			if (!(flags & NFT_SET_CONCAT))
+				return -EINVAL;
+		} else if (flags & NFT_SET_CONCAT) {
 			return -EINVAL;
+		}
 	} else if (flags & NFT_SET_CONCAT) {
 		return -EINVAL;
 	}
Signature · 1 line
2.43.0
author maintainer
#575 lore raw

PATCH 569/583 ipvs: avoid stat macros calls from preemptible context

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Fedor Pchelkin <[email protected]>

[ Upstream commit d6938c1c76c64f42363d0d1f051e1b4641c2ad40 ]

Inside decrement_ttl() upon discovering that the packet ttl has exceeded, __IP_INC_STATS and __IP6_INC_STATS macros can be called from preemptible context having the following backtrace:

check_preemption_disabled: 48 callbacks suppressed

BUG: using __this_cpu_add() in preemptible [00000000] code: curl/1177
caller is decrement_ttl+0x217/0x830
CPU: 5 PID: 1177 Comm: curl Not tainted 6.7.0+ #34
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0xbd/0xe0
 check_preemption_disabled+0xd1/0xe0
 decrement_ttl+0x217/0x830
 __ip_vs_get_out_rt+0x4e0/0x1ef0
 ip_vs_nat_xmit+0x205/0xcd0
 ip_vs_in_hook+0x9b1/0x26a0
 nf_hook_slow+0xc2/0x210
 nf_hook+0x1fb/0x770
 __ip_local_out+0x33b/0x640
 ip_local_out+0x2a/0x490
 __ip_queue_xmit+0x990/0x1d10
 __tcp_transmit_skb+0x288b/0x3d10
 tcp_connect+0x3466/0x5180
 tcp_v4_connect+0x1535/0x1bb0
 __inet_stream_connect+0x40d/0x1040
 inet_stream_connect+0x57/0xa0
 __sys_connect_file+0x162/0x1a0
 __sys_connect+0x137/0x160
 __x64_sys_connect+0x72/0xb0
 do_syscall_64+0x6f/0x140
 entry_SYSCALL_64_after_hwframe+0x6e/0x76
RIP: 0033:0x7fe6dbbc34e0

Use the corresponding preemption-aware variants: IP_INC_STATS and IP6_INC_STATS.

Found by Linux Verification Center (linuxtesting.org).

---
 net/netfilter/ipvs/ip_vs_xmit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/ipvs/ip_vs_xmit.c +2 -2
index 9193e109e6b3..65e0259178da 100644
@@ -271,7 +271,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 			skb->dev = dst->dev;
 			icmpv6_send(skb, ICMPV6_TIME_EXCEED,
 				    ICMPV6_EXC_HOPLIMIT, 0);
-			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
 			return false;
 		}
@@ -286,7 +286,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 	{
 		if (ip_hdr(skb)->ttl <= 1) {
 			/* Tell the sender its packet died... */
-			__IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
+			IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS);
 			icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
 			return false;
 		}
Signature · 1 line
2.43.0
author maintainer
#576 lore raw

PATCH 570/583 io_uring: adjust defer tw counting

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Begunkov <[email protected]>

[ Upstream commit dc12d1799ce710fd90abbe0ced71e7e1ae0894fc ]

The UINT_MAX work item counting bias in io_req_local_work_add() in case of !IOU_F_TWQ_LAZY_WAKE works in a sense that we will not miss a wake up, however it's still eerie. In particular, if we add a lazy work item after a non-lazy one, we'll increment it and get nr_tw==0, and subsequent adds may try to unnecessarily wake up the task, which is though not so likely to happen in real workloads.

Half the bias, it's still large enough to be larger than any valid ->cq_wait_nr, which is limited by IORING_MAX_CQ_ENTRIES, but further have a good enough of space before it overflows.

---
 io_uring/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
io_uring/io_uring.c +1 -1
index 1cc4c7b05949..ea772a02c140 100644
@@ -1339,7 +1339,7 @@ static inline void io_req_local_work_add(struct io_kiocb *req, unsigned flags)
 		nr_tw = nr_tw_prev + 1;
 		/* Large enough to fail the nr_wait comparison below */
 		if (!(flags & IOU_F_TWQ_LAZY_WAKE))
-			nr_tw = -1U;
+			nr_tw = INT_MAX;
 
 		req->nr_tw = nr_tw;
 		req->io_task_work.node.next = first;
Signature · 1 line
2.43.0
author maintainer
#577 lore raw

PATCH 571/583 kdb: Fix a potential buffer overflow in kdb_local()

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

[ Upstream commit 4f41d30cd6dc865c3cbc1a852372321eba6d4e4c ]

When appending "[defcmd]" to 'kdb_prompt_str', the size of the string already in the buffer should be taken into account.

An option could be to switch from strncat() to strlcat() which does the correct test to avoid such an overflow.

However, this actually looks as dead code, because 'defcmd_in_progress' can't be true here.
See a more detailed explanation at [1].

[1]: https://lore.kernel.org/all/CAD=FV=WSh7wKN7Yp-3wWiDgX4E3isQ8uh0LCzTmd1v9Cg9j+nQ@mail.gmail.com/

Fixes 5d5314d6795f ("kdb: core for kgdb back end (1 of 2)")
---
 kernel/debug/kdb/kdb_main.c | 2 --
 1 file changed, 2 deletions(-)
kernel/debug/kdb/kdb_main.c +0 -2
index 438b868cbfa9..35aa2e98a92a 100644
@@ -1349,8 +1349,6 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs,
 		/* PROMPT can only be set if we have MEM_READ permission. */
 		snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"),
 			 raw_smp_processor_id());
-		if (defcmd_in_progress)
-			strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN);
 
 		/*
 		 * Fetch command from keyboard
Signature · 1 line
2.43.0
author maintainer
#578 lore raw

PATCH 572/583 arm64/ptrace: Dont flush ZA/ZT storage when writing ZA via ptrace

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mark Brown <[email protected]>

[ Upstream commit b7c510d049049409e8945b932f4b0b357fa17415 ]

When writing ZA we currently unconditionally flush the buffer used to store it as part of ensuring that it is allocated. Since this buffer is shared with ZT0 this means that a write to ZA when PSTATE.ZA is already set will corrupt the value of ZT0 on a SME2 system. Fix this by only flushing the backing storage if PSTATE.ZA was not previously set.

This will mean that short or failed writes may leave stale data in the buffer, this seems as correct as our current behaviour and unlikely to be something that userspace will rely on.

Fixes f90b529bcbe5 ("arm64/sme: Implement ZT0 ptrace support")
---
 arch/arm64/kernel/ptrace.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)
arch/arm64/kernel/ptrace.c +7 -6
index 20d7ef82de90..b3f64144b5cd 100644
@@ -1107,12 +1107,13 @@ static int za_set(struct task_struct *target,
 		}
 	}
 
-	/* Allocate/reinit ZA storage */
-	sme_alloc(target, true);
-	if (!target->thread.sme_state) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	/*
+	 * Only flush the storage if PSTATE.ZA was not already set,
+	 * otherwise preserve any existing data.
+	 */
+	sme_alloc(target, !thread_za_enabled(&target->thread));
+	if (!target->thread.sme_state)
+		return -ENOMEM;
 
 	/* If there is no data then disable ZA */
 	if (!count) {
Signature · 1 line
2.43.0
author maintainer
#579 lore raw

PATCH 573/583 ethtool: netlink: Add missing ethnl_ops_begin/complete

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ludvig Pärsson <[email protected]>

[ Upstream commit f1172f3ee3a98754d95b968968920a7d03fdebcc ]

Accessing an ethernet device that is powered off or clock gated might cause the CPU to hang. Add ethnl_ops_begin/complete in ethnl_set_features() to protect against this.

Fixes 0980bfcd6954 ("ethtool: set netdev features with FEATURES_SET request")
---
 net/ethtool/features.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
net/ethtool/features.c +7 -2
index a79af8c25a07..b6cb101d7f19 100644
@@ -234,17 +234,20 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl;
 	ethnl_features_to_bitmap(old_active, dev->features);
 	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
 				 tb[ETHTOOL_A_FEATURES_WANTED],
 				 netdev_features_strings, info->extack);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_ops;
 	if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) {
 		GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features");
 		ret = -EINVAL;
-		goto out_rtnl;
+		goto out_ops;
 	}
 
 	/* set req_wanted bits not in req_mask from old_wanted */
@@ -281,6 +284,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	if (mod)
 		netdev_features_change(dev);
 
+out_ops:
+	ethnl_ops_complete(dev);
 out_rtnl:
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
Signature · 1 line
2.43.0
author maintainer
#580 lore raw

PATCH 574/583 loop: fix the the direct I/O support check when used on top of block devices

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christoph Hellwig <[email protected]>

[ Upstream commit baa7d536077dcdfe2b70c476a8873d1745d3de0f ]

__loop_update_dio only checks the alignment requirement for block backed file systems, but misses them for the case where the loop device is created directly on top of another block device. Due to this creating a loop device with default option plus the direct I/O flag on a > 512 byte sector size file system will lead to incorrect I/O being submitted to the lower block device and a lot of error from the lock layer. This can be seen with xfstests generic/563.

Fix the code in __loop_update_dio by factoring the alignment check into a helper, and calling that also for the struct block_device of a block device inode.

Also remove the TODO comment talking about dynamically switching between buffered and direct I/O, which is a would be a recipe for horrible performance and occasional data loss.

Fixes 2e5ab5f379f9 ("block: loop: prepare for supporing direct IO")
---
 drivers/block/loop.c | 52 +++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 27 deletions(-)
drivers/block/loop.c +25 -27
index 9f2d412fc560..552f56a84a7e 100644
@@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+		struct block_device *backing_bdev)
+{
+	unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+	if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+		return false;
+	if (lo->lo_offset & (sb_bsize - 1))
+		return false;
+	return true;
+}
+
 static void __loop_update_dio(struct loop_device *lo, bool dio)
 {
 	struct file *file = lo->lo_backing_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned short sb_bsize = 0;
-	unsigned dio_align = 0;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	bool use_dio;
 
-	if (inode->i_sb->s_bdev) {
-		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-		dio_align = sb_bsize - 1;
-	}
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
 
-	/*
-	 * We support direct I/O only if lo_offset is aligned with the
-	 * logical I/O size of backing device, and the logical block
-	 * size of loop is bigger than the backing device's.
-	 *
-	 * TODO: the above condition may be loosed in the future, and
-	 * direct I/O may be switched runtime at that time because most
-	 * of requests in sane applications should be PAGE_SIZE aligned
-	 */
-	if (dio) {
-		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-		    !(lo->lo_offset & dio_align) &&
-		    (file->f_mode & FMODE_CAN_ODIRECT))
-			use_dio = true;
-		else
-			use_dio = false;
-	} else {
-		use_dio = false;
-	}
+	use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+		(!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
 
 	if (lo->use_dio == use_dio)
 		return;
Signature · 1 line
2.43.0
author maintainer
#581 lore raw

PATCH 575/583 mlxsw: spectrum_acl_erp: Fix error flow of pool allocation failure

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Amit Cohen <[email protected]>

[ Upstream commit 6d6eeabcfaba2fcadf5443b575789ea606f9de83 ]

Lately, a bug was found when many TC filters are added - at some point, several bugs are printed to dmesg [1] and the switch is crashed with segmentation fault.

The issue starts when gen_pool_free() fails because of unexpected behavior - a try to free memory which is already freed, this leads to BUG() call which crashes the switch and makes many other bugs.

Trying to track down the unexpected behavior led to a bug in eRP code. The function mlxsw_sp_acl_erp_table_alloc() gets a pointer to the allocated index, sets the value and returns an error code. When gen_pool_alloc() fails it returns address 0, we track it and return -ENOBUFS outside, BUT the call for gen_pool_alloc() already override the index in erp_table structure. This is a problem when such allocation is done as part of table expansion. This is not a new table, which will not be used in case of allocation failure. We try to expand eRP table and override the current index (non-zero) with zero. Then, it leads to an unexpected behavior when address 0 is freed twice. Note that address 0 is valid in erp_table->base_index and indeed other tables use it.

gen_pool_alloc() fails in case that there is no space left in the pre-allocated pool, in our case, the pool is limited to ACL_MAX_ERPT_BANK_SIZE, which is read from hardware. When more than max erp entries are required, we exceed the limit and return an error, this error leads to "Failed to migrate vregion" print.

Fix this by changing erp_table->base_index only in case of a successful allocation.

Add a test case for such a scenario. Without this fix it causes segmentation fault:

$ TESTS="max_erp_entries_test" ./tc_flower.sh
./tc_flower.sh: line 988:  1560 Segmentation fault      tc filter del dev $h2 ingress chain $i protocol ip pref $i handle $j flower &>/dev/null

[1]:
kernel BUG at lib/genalloc.c:508!
invalid opcode: 0000 [#1] PREEMPT SMP

CPU: 6 PID: 3531 Comm: tc Not tainted 6.7.0-rc5-custom-ga6893f479f5e #1
Hardware name: Mellanox Technologies Ltd. MSN4700/VMOD0010, BIOS 5.11 07/12/2021
RIP: 0010:gen_pool_free_owner+0xc9/0xe0
...
Call Trace:
 <TASK>
 __mlxsw_sp_acl_erp_table_other_dec+0x70/0xa0 [mlxsw_spectrum]
 mlxsw_sp_acl_erp_mask_destroy+0xf5/0x110 [mlxsw_spectrum]
 objagg_obj_root_destroy+0x18/0x80 [objagg]
 objagg_obj_destroy+0x12c/0x130 [objagg]
 mlxsw_sp_acl_erp_mask_put+0x37/0x50 [mlxsw_spectrum]
 mlxsw_sp_acl_ctcam_region_entry_remove+0x74/0xa0 [mlxsw_spectrum]
 mlxsw_sp_acl_ctcam_entry_del+0x1e/0x40 [mlxsw_spectrum]
 mlxsw_sp_acl_tcam_ventry_del+0x78/0xd0 [mlxsw_spectrum]
 mlxsw_sp_flower_destroy+0x4d/0x70 [mlxsw_spectrum]
 mlxsw_sp_flow_block_cb+0x73/0xb0 [mlxsw_spectrum]
 tc_setup_cb_destroy+0xc1/0x180
 fl_hw_destroy_filter+0x94/0xc0 [cls_flower]
 __fl_delete+0x1ac/0x1c0 [cls_flower]
 fl_destroy+0xc2/0x150 [cls_flower]
 tcf_proto_destroy+0x1a/0xa0

...
mlxsw_spectrum3 0000:07:00.0: Failed to migrate vregion mlxsw_spectrum3 0000:07:00.0: Failed to migrate vregion

---
 .../mellanox/mlxsw/spectrum_acl_erp.c         |  8 +--
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 52 ++++++++++++++++++-
 2 files changed, 56 insertions(+), 4 deletions(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +5 -3
index 4c98950380d5..d231f4d2888b 100644
@@ -301,6 +301,7 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 			     unsigned long *p_index)
 {
 	unsigned int num_rows, entry_size;
+	unsigned long index;
 
 	/* We only allow allocations of entire rows */
 	if (num_erps % erp_core->num_erp_banks != 0)
@@ -309,10 +310,11 @@ mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
 	entry_size = erp_core->erpt_entries_size[region_type];
 	num_rows = num_erps / erp_core->num_erp_banks;
 
-	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
-	if (*p_index == 0)
+	index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (!index)
 		return -ENOBUFS;
-	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	*p_index = index - MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
 
 	return 0;
 }
tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +51 -1

64 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#582 lore raw

PATCH 576/583 mlxsw: spectrum_acl_tcam: Fix NULL pointer dereference in error path

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit efeb7dfea8ee10cdec11b6b6ba4e405edbe75809 ]

When calling mlxsw_sp_acl_tcam_region_destroy() from an error path after failing to attach the region to an ACL group, we hit a NULL pointer dereference upon 'region->group->tcam' [1].

Fix by retrieving the 'tcam' pointer using mlxsw_sp_acl_to_tcam().

[1]

BUG: kernel NULL pointer dereference, address: 0000000000000000
[...]
RIP: 0010:mlxsw_sp_acl_tcam_region_destroy+0xa0/0xd0
[...]
Call Trace:
 mlxsw_sp_acl_tcam_vchunk_get+0x88b/0xa20
 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0
 mlxsw_sp_acl_rule_add+0x47/0x240
 mlxsw_sp_flower_replace+0x1a9/0x1d0
 tc_setup_cb_add+0xdc/0x1c0
 fl_hw_replace_filter+0x146/0x1f0
 fl_change+0xc17/0x1360
 tc_new_tfilter+0x472/0xb90
 rtnetlink_rcv_msg+0x313/0x3b0
 netlink_rcv_skb+0x58/0x100
 netlink_unicast+0x244/0x390
 netlink_sendmsg+0x1e4/0x440
 ____sys_sendmsg+0x164/0x260
 ___sys_sendmsg+0x9a/0xe0
 __sys_sendmsg+0x7a/0xc0
 do_syscall_64+0x40/0xe0
 entry_SYSCALL_64_after_hwframe+0x63/0x6b
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +2 -2
index d50786b0a6ce..7d1e91196e94 100644
@@ -681,13 +681,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
+	struct mlxsw_sp_acl_tcam *tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl);
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
-					region->id);
+	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 	kfree(region);
 }
 
Signature · 1 line
2.43.0
author maintainer
#583 lore raw

PATCH 577/583 mlxsw: spectrum_acl_tcam: Fix stack corruption

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel <[email protected]>

[ Upstream commit 483ae90d8f976f8339cf81066312e1329f2d3706 ]

When tc filters are first added to a net device, the corresponding local port gets bound to an ACL group in the device. The group contains a list of ACLs. In turn, each ACL points to a different TCAM region where the filters are stored. During forwarding, the ACLs are sequentially evaluated until a match is found.

One reason to place filters in different regions is when they are added with decreasing priorities and in an alternating order so that two consecutive filters can never fit in the same region because of their key usage.

In Spectrum-2 and newer ASICs the firmware started to report that the maximum number of ACLs in a group is more than 16, but the layout of the register that configures ACL groups (PAGT) was not updated to account for that. It is therefore possible to hit stack corruption [1] in the rare case where more than 16 ACLs in a group are required.

Fix by limiting the maximum ACL group size to the minimum between what the firmware reports and the maximum ACLs that fit in the PAGT register.

Add a test case to make sure the machine does not crash when this condition is hit.

[1]

Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: mlxsw_sp_acl_tcam_group_update+0x116/0x120
[...]
 dump_stack_lvl+0x36/0x50
 panic+0x305/0x330
 __stack_chk_fail+0x15/0x20
 mlxsw_sp_acl_tcam_group_update+0x116/0x120
 mlxsw_sp_acl_tcam_group_region_attach+0x69/0x110
 mlxsw_sp_acl_tcam_vchunk_get+0x492/0xa20
 mlxsw_sp_acl_tcam_ventry_add+0x25/0xe0
 mlxsw_sp_acl_rule_add+0x47/0x240
 mlxsw_sp_flower_replace+0x1a9/0x1d0
 tc_setup_cb_add+0xdc/0x1c0
 fl_hw_replace_filter+0x146/0x1f0
 fl_change+0xc17/0x1360
 tc_new_tfilter+0x472/0xb90
 rtnetlink_rcv_msg+0x313/0x3b0
 netlink_rcv_skb+0x58/0x100
 netlink_unicast+0x244/0x390
 netlink_sendmsg+0x1e4/0x440
 ____sys_sendmsg+0x164/0x260
 ___sys_sendmsg+0x9a/0xe0
 __sys_sendmsg+0x7a/0xc0
 do_syscall_64+0x40/0xe0
 entry_SYSCALL_64_after_hwframe+0x63/0x6b
---
 .../mellanox/mlxsw/spectrum_acl_tcam.c        |  2 +
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh | 56 ++++++++++++++++++-
 2 files changed, 57 insertions(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +2 -0
index 7d1e91196e94..50ea1eff02b2 100644
@@ -1564,6 +1564,8 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						  ACL_MAX_GROUP_SIZE);
+	tcam->max_group_size = min_t(unsigned int, tcam->max_group_size,
+				     MLXSW_REG_PAGT_ACL_MAX_NUM);
 
 	err = ops->init(mlxsw_sp, tcam->priv, tcam);
 	if (err)
tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +55 -1

68 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#584 lore raw

PATCH 578/583 mlxsw: spectrum_router: Register netdevice notifier before nexthop

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Petr Machata <[email protected]>

[ Upstream commit 62bef63646c194e0f82b40304a0f2d060b28687b ]

If there are IPIP nexthops at the time when the driver is loaded (or the devlink instance reloaded), the driver looks up the corresponding IPIP entry. But IPIP entries are only created as a result of netdevice notifications. Since the netdevice notifier is registered after the nexthop notifier, mlxsw_sp_nexthop_type_init() never finds the IPIP entry, registers the nexthop MLXSW_SP_NEXTHOP_TYPE_ETH, and fails to assign a CRIF to the nexthop. Later on when the CRIF is necessary, the WARN_ON in mlxsw_sp_nexthop_rif() triggers, causing the splat [1].

In order to fix the issue, reorder the netdevice notifier to be registered before the nexthop one.

[1] (edited for clarity):

    WARNING: CPU: 1 PID: 1364 at drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3245 mlxsw_sp_nexthop_rif (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3246 (discriminator 1)) mlxsw_spectrum
    Hardware name: Mellanox Technologies Ltd. MSN4410/VMOD0010, BIOS 5.11 01/06/2019
    Call Trace:
    ? mlxsw_sp_nexthop_rif (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3246 (discriminator 1)) mlxsw_spectrum
    __mlxsw_sp_nexthop_eth_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3637) mlxsw_spectrum
    mlxsw_sp_nexthop_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3679 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3727) mlxsw_spectrum
    mlxsw_sp_nexthop_group_update (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3757) mlxsw_spectrum
    mlxsw_sp_nexthop_group_refresh (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:4112) mlxsw_spectrum
    mlxsw_sp_nexthop_obj_event (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5118 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5191 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5315 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:5500) mlxsw_spectrum
    nexthops_dump (net/ipv4/nexthop.c:217 net/ipv4/nexthop.c:440 net/ipv4/nexthop.c:3609)
    register_nexthop_notifier (net/ipv4/nexthop.c:3624)
    mlxsw_sp_router_init (drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:11486) mlxsw_spectrum
    mlxsw_sp_init (drivers/net/ethernet/mellanox/mlxsw/spectrum.c:3267) mlxsw_spectrum
    __mlxsw_core_bus_device_register (drivers/net/ethernet/mellanox/mlxsw/core.c:2202) mlxsw_core
    mlxsw_devlink_core_bus_device_reload_up (drivers/net/ethernet/mellanox/mlxsw/core.c:2265 drivers/net/ethernet/mellanox/mlxsw/core.c:1603) mlxsw_core
    devlink_reload (net/devlink/dev.c:314 net/devlink/dev.c:475)
    [...]
---
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +12 -12
index debd2c466f11..ae2fb9efbc50 100644
@@ -11458,6 +11458,13 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_netevent_notifier;
 
+	mlxsw_sp->router->netdevice_nb.notifier_call =
+		mlxsw_sp_router_netdevice_event;
+	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					      &mlxsw_sp->router->netdevice_nb);
+	if (err)
+		goto err_register_netdev_notifier;
+
 	mlxsw_sp->router->nexthop_nb.notifier_call =
 		mlxsw_sp_nexthop_obj_event;
 	err = register_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
@@ -11473,22 +11480,15 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_register_fib_notifier;
 
-	mlxsw_sp->router->netdevice_nb.notifier_call =
-		mlxsw_sp_router_netdevice_event;
-	err = register_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					      &mlxsw_sp->router->netdevice_nb);
-	if (err)
-		goto err_register_netdev_notifier;
-
 	return 0;
 
-err_register_netdev_notifier:
-	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp),
-				&mlxsw_sp->router->fib_nb);
 err_register_fib_notifier:
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &mlxsw_sp->router->nexthop_nb);
 err_register_nexthop_notifier:
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
+err_register_netdev_notifier:
 	unregister_netevent_notifier(&mlxsw_sp->router->netevent_nb);
 err_register_netevent_notifier:
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
@@ -11536,11 +11536,11 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_router *router = mlxsw_sp->router;
 
-	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
-					  &router->netdevice_nb);
 	unregister_fib_notifier(mlxsw_sp_net(mlxsw_sp), &router->fib_nb);
 	unregister_nexthop_notifier(mlxsw_sp_net(mlxsw_sp),
 				    &router->nexthop_nb);
+	unregister_netdevice_notifier_net(mlxsw_sp_net(mlxsw_sp),
+					  &router->netdevice_nb);
 	unregister_netevent_notifier(&router->netevent_nb);
 	unregister_inet6addr_validator_notifier(&router->inet6addr_valid_nb);
 	unregister_inetaddr_validator_notifier(&router->inetaddr_valid_nb);
Signature · 1 line
2.43.0
author maintainer
#585 lore raw

PATCH 579/583 selftests: mlxsw: qos_pfc: Adjust the test to support 8 lanes

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Amit Cohen <[email protected]>

[ Upstream commit b34f4de6d30cbaa8fed905a5080b6eace8c84dc7 ]

'qos_pfc' test checks PFC behavior. The idea is to limit the traffic using a shaper somewhere in the flow of the packets. In this area, the buffer is smaller than the buffer at the beginning of the flow, so it fills up until there is no more space left. The test configures there PFC which is supposed to notice that the headroom is filling up and send PFC Xoff to indicate the transmitter to stop sending traffic for the priorities sharing this PG.

The Xon/Xoff threshold is auto-configured and always equal to 2*(MTU rounded up to cell size). Even after sending the PFC Xoff packet, traffic will keep arriving until the transmitter receives and processes the PFC packet. This amount of traffic is known as the PFC delay allowance.

Currently the buffer for the delay traffic is configured as 100KB. The MTU in the test is 10KB, therefore the threshold for Xoff is about 20KB. This allows 80KB extra to be stored in this buffer.

8-lane ports use two buffers among which the configured buffer is split, the Xoff threshold then applies to each buffer in parallel.

The test does not take into account the behavior of 8-lane ports, when the ports are configured to 400Gbps with 8 lanes or 800Gbps with 8 lanes, packets are dropped and the test fails.

Check if the relevant ports use 8 lanes, in such case double the size of the buffer, as the headroom is split half-half.

---
 .../selftests/drivers/net/mlxsw/qos_pfc.sh     | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)
tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +17 -1
index 42ce602d8d49..e71d811656bb 100755
@@ -120,6 +120,9 @@ h2_destroy()
 
 switch_create()
 {
+	local lanes_swp4
+	local pg1_size
+
 	# pools
 	# -----
 
@@ -229,7 +232,20 @@ switch_create()
 	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
+	pg1_size=$_100KB
+
+	setup_wait_dev_with_timeout $swp4
+
+	lanes_swp4=$(ethtool $swp4 | grep 'Lanes:')
+	lanes_swp4=${lanes_swp4#*"Lanes: "}
+
+	# 8-lane ports use two buffers among which the configured buffer
+	# is split, so double the size to get twice (20K + 80K).
+	if [[ $lanes_swp4 -eq 8 ]]; then
+		pg1_size=$((pg1_size * 2))
+	fi
+
+	dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size
 
 	# bridges
 	# -------
Signature · 1 line
2.43.0
author maintainer
#586 lore raw

PATCH 580/583 ipv6: mcast: fix data-race in ipv6_mc_down / mld_ifc_work

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nikita Zhandarovich <[email protected]>

[ Upstream commit 2e7ef287f07c74985f1bf2858bedc62bd9ebf155 ]

idev->mc_ifc_count can be written over without proper locking.

Originally found by syzbot [1], fix this issue by encapsulating calls to mld_ifc_stop_work() (and mld_gq_stop_work() for good measure) with mutex_lock() and mutex_unlock() accordingly as these functions should only be called with mc_lock per their declarations.

[1]

BUG: KCSAN: data-race in ipv6_mc_down / mld_ifc_work

write to 0xffff88813a80c832 of 1 bytes by task 3771 on cpu 0:

 mld_ifc_stop_work net/ipv6/mcast.c:1080 [inline]
 ipv6_mc_down+0x10a/0x280 net/ipv6/mcast.c:2725
 addrconf_ifdown+0xe32/0xf10 net/ipv6/addrconf.c:3949
 addrconf_notify+0x310/0x980
 notifier_call_chain kernel/notifier.c:93 [inline]
 raw_notifier_call_chain+0x6b/0x1c0 kernel/notifier.c:461
 __dev_notify_flags+0x205/0x3d0
 dev_change_flags+0xab/0xd0 net/core/dev.c:8685
 do_setlink+0x9f6/0x2430 net/core/rtnetlink.c:2916
 rtnl_group_changelink net/core/rtnetlink.c:3458 [inline]
 __rtnl_newlink net/core/rtnetlink.c:3717 [inline]
 rtnl_newlink+0xbb3/0x1670 net/core/rtnetlink.c:3754
 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6558
 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2545
 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6576
 netlink_unicast_kernel net/netlink/af_netlink.c:1342 [inline]
 netlink_unicast+0x589/0x650 net/netlink/af_netlink.c:1368
 netlink_sendmsg+0x66e/0x770 net/netlink/af_netlink.c:1910
 ...

write to 0xffff88813a80c832 of 1 bytes by task 22 on cpu 1:

 mld_ifc_work+0x54c/0x7b0 net/ipv6/mcast.c:2653
 process_one_work kernel/workqueue.c:2627 [inline]
 process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2700
 worker_thread+0x525/0x730 kernel/workqueue.c:2781
 ...
---
 net/ipv6/mcast.c | 4 ++++
 1 file changed, 4 insertions(+)
net/ipv6/mcast.c +4 -0
index 5ce25bcb9974..f948cf7bfc44 100644
@@ -2723,8 +2723,12 @@ void ipv6_mc_down(struct inet6_dev *idev)
 	synchronize_net();
 	mld_query_stop_work(idev);
 	mld_report_stop_work(idev);
+
+	mutex_lock(&idev->mc_lock);
 	mld_ifc_stop_work(idev);
 	mld_gq_stop_work(idev);
+	mutex_unlock(&idev->mc_lock);
+
 	mld_dad_stop_work(idev);
 }
 
Signature · 1 line
2.43.0
author maintainer
#587 lore raw

PATCH 581/583 i2c: s3c24xx: fix read transfers in polling mode

In reply to Greg Kroah-Hartman

6.6-stable review patch. If anyone has any objections, please let me know.

------------------

From: Marek Szyprowski <[email protected]>

[ Upstream commit 0d9cf23ed55d7ba3ab26d617a3ae507863674c8f ]

To properly handle read transfers in polling mode, no waiting for the ACK state is needed as it will never come. Just wait a bit to ensure start state is on the bus and continue processing next bytes.

Fixes 117053f77a5a ("i2c: s3c2410: Add polling mode support")
---
 drivers/i2c/busses/i2c-s3c2410.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
drivers/i2c/busses/i2c-s3c2410.c +11 -2
index 127eb3805fac..fdd7a4259d2c 100644
@@ -216,8 +216,17 @@ static bool is_ack(struct s3c24xx_i2c *i2c)
 	int tries;
 
 	for (tries = 50; tries; --tries) {
-		if (readl(i2c->regs + S3C2410_IICCON)
-			& S3C2410_IICCON_IRQPEND) {
+		unsigned long tmp = readl(i2c->regs + S3C2410_IICCON);
+
+		if (!(tmp & S3C2410_IICCON_ACKEN)) {
+			/*
+			 * Wait a bit for the bus to stabilize,
+			 * delay estimated experimentally.
+			 */
+			usleep_range(100, 200);
+			return true;
+		}
+		if (tmp & S3C2410_IICCON_IRQPEND) {
 			if (!(readl(i2c->regs + S3C2410_IICSTAT)
 				& S3C2410_IICSTAT_LASTBIT))
 				return true;
Signature · 1 line
2.43.0