[PATCH AUTOSEL 5.4 01/23] ARM: 9058/1: cache-v7: refactor v7_invalidate_l1 to avoid clobbering r5/r6

[PATCH AUTOSEL 5.4 01/23] ARM: 9058/1: cache-v7: refactor v7_invalidate_l1 to avoid clobbering r5/r6

[Sasha Levin]

From: Ard Biesheuvel <ardb@kernel.org>

[ Upstream commit f9e7a99fb6b86aa6a00e53b34ee6973840e005aa ]

The cache invalidation code in v7_invalidate_l1 can be tweaked to
re-read the associativity from CCSIDR, and keep the way identifier
component in a single register that is assigned in the outer loop. This
way, we need 2 registers less.

Given that the number of sets is typically much larger than the
associativity, rearrange the code so that the outer loop has the fewer
number of iterations, ensuring that the re-read of CCSIDR only occurs a
handful of times in practice.

Fix the whitespace while at it, and update the comment to indicate that
this code is no longer a clone of anything else.

Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/mm/cache-v7.S | 51 +++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 26 deletions(-)

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 0ee8fc4b4672..8e69bf36a3ec 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,41 +33,40 @@ icache_size:
  * processor.  We fix this by performing an invalidate, rather than a
  * clean + invalidate, before jumping into the kernel.
  *
- * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs
- * to be called for both secondary cores startup and primary core resume
- * procedures.
+ * This function needs to be called for both secondary cores startup and
+ * primary core resume procedures.
  */
 ENTRY(v7_invalidate_l1)
        mov     r0, #0
        mcr     p15, 2, r0, c0, c0, 0
        mrc     p15, 1, r0, c0, c0, 0
 
-       movw    r1, #0x7fff
-       and     r2, r1, r0, lsr #13
+	movw	r3, #0x3ff
+	and	r3, r3, r0, lsr #3	@ 'Associativity' in CCSIDR[12:3]
+	clz	r1, r3			@ WayShift
+	mov	r2, #1
+	mov	r3, r3, lsl r1		@ NumWays-1 shifted into bits [31:...]
+	movs	r1, r2, lsl r1		@ #1 shifted left by same amount
+	moveq	r1, #1			@ r1 needs value > 0 even if only 1 way
 
-       movw    r1, #0x3ff
+	and	r2, r0, #0x7
+	add	r2, r2, #4		@ SetShift
 
-       and     r3, r1, r0, lsr #3      @ NumWays - 1
-       add     r2, r2, #1              @ NumSets
+1:	movw	r4, #0x7fff
+	and	r0, r4, r0, lsr #13	@ 'NumSets' in CCSIDR[27:13]
 
-       and     r0, r0, #0x7
-       add     r0, r0, #4      @ SetShift
-
-       clz     r1, r3          @ WayShift
-       add     r4, r3, #1      @ NumWays
-1:     sub     r2, r2, #1      @ NumSets--
-       mov     r3, r4          @ Temp = NumWays
-2:     subs    r3, r3, #1      @ Temp--
-       mov     r5, r3, lsl r1
-       mov     r6, r2, lsl r0
-       orr     r5, r5, r6      @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
-       mcr     p15, 0, r5, c7, c6, 2
-       bgt     2b
-       cmp     r2, #0
-       bgt     1b
-       dsb     st
-       isb
-       ret     lr
+2:	mov	r4, r0, lsl r2		@ NumSet << SetShift
+	orr	r4, r4, r3		@ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+	mcr	p15, 0, r4, c7, c6, 2
+	subs	r0, r0, #1		@ Set--
+	bpl	2b
+	subs	r3, r3, r1		@ Way--
+	bcc	3f
+	mrc	p15, 1, r0, c0, c0, 0	@ re-read cache geometry from CCSIDR
+	b	1b
+3:	dsb	st
+	isb
+	ret	lr
 ENDPROC(v7_invalidate_l1)
 
 /*
-- 
2.30.2

[PATCH AUTOSEL 5.4 01/23] ARM: 9058/1: cache-v7: refactor v7_invalidate_l1 to avoid clobbering r5/r6

[Sasha Levin]

From: Ard Biesheuvel <ardb@kernel.org>

[ Upstream commit f9e7a99fb6b86aa6a00e53b34ee6973840e005aa ]

The cache invalidation code in v7_invalidate_l1 can be tweaked to
re-read the associativity from CCSIDR, and keep the way identifier
component in a single register that is assigned in the outer loop. This
way, we need 2 registers less.

Given that the number of sets is typically much larger than the
associativity, rearrange the code so that the outer loop has the fewer
number of iterations, ensuring that the re-read of CCSIDR only occurs a
handful of times in practice.

Fix the whitespace while at it, and update the comment to indicate that
this code is no longer a clone of anything else.

Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/mm/cache-v7.S | 51 +++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 26 deletions(-)

diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 0ee8fc4b4672..8e69bf36a3ec 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,41 +33,40 @@ icache_size:
  * processor.  We fix this by performing an invalidate, rather than a
  * clean + invalidate, before jumping into the kernel.
  *
- * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs
- * to be called for both secondary cores startup and primary core resume
- * procedures.
+ * This function needs to be called for both secondary cores startup and
+ * primary core resume procedures.
  */
 ENTRY(v7_invalidate_l1)
        mov     r0, #0
        mcr     p15, 2, r0, c0, c0, 0
        mrc     p15, 1, r0, c0, c0, 0
 
-       movw    r1, #0x7fff
-       and     r2, r1, r0, lsr #13
+	movw	r3, #0x3ff
+	and	r3, r3, r0, lsr #3	@ 'Associativity' in CCSIDR[12:3]
+	clz	r1, r3			@ WayShift
+	mov	r2, #1
+	mov	r3, r3, lsl r1		@ NumWays-1 shifted into bits [31:...]
+	movs	r1, r2, lsl r1		@ #1 shifted left by same amount
+	moveq	r1, #1			@ r1 needs value > 0 even if only 1 way
 
-       movw    r1, #0x3ff
+	and	r2, r0, #0x7
+	add	r2, r2, #4		@ SetShift
 
-       and     r3, r1, r0, lsr #3      @ NumWays - 1
-       add     r2, r2, #1              @ NumSets
+1:	movw	r4, #0x7fff
+	and	r0, r4, r0, lsr #13	@ 'NumSets' in CCSIDR[27:13]
 
-       and     r0, r0, #0x7
-       add     r0, r0, #4      @ SetShift
-
-       clz     r1, r3          @ WayShift
-       add     r4, r3, #1      @ NumWays
-1:     sub     r2, r2, #1      @ NumSets--
-       mov     r3, r4          @ Temp = NumWays
-2:     subs    r3, r3, #1      @ Temp--
-       mov     r5, r3, lsl r1
-       mov     r6, r2, lsl r0
-       orr     r5, r5, r6      @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
-       mcr     p15, 0, r5, c7, c6, 2
-       bgt     2b
-       cmp     r2, #0
-       bgt     1b
-       dsb     st
-       isb
-       ret     lr
+2:	mov	r4, r0, lsl r2		@ NumSet << SetShift
+	orr	r4, r4, r3		@ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+	mcr	p15, 0, r4, c7, c6, 2
+	subs	r0, r0, #1		@ Set--
+	bpl	2b
+	subs	r3, r3, r1		@ Way--
+	bcc	3f
+	mrc	p15, 1, r0, c0, c0, 0	@ re-read cache geometry from CCSIDR
+	b	1b
+3:	dsb	st
+	isb
+	ret	lr
 ENDPROC(v7_invalidate_l1)
 
 /*
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.4 02/23] PCI: thunder: Fix compile testing

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

[ Upstream commit 16f7ae5906dfbeff54f74ec75d0563bb3a87ab0b ]

Compile-testing these drivers is currently broken. Enabling it causes a
couple of build failures though:

  drivers/pci/controller/pci-thunder-ecam.c:119:30: error: shift count >= width of type [-Werror,-Wshift-count-overflow]
  drivers/pci/controller/pci-thunder-pem.c:54:2: error: implicit declaration of function 'writeq' [-Werror,-Wimplicit-function-declaration]
  drivers/pci/controller/pci-thunder-pem.c:392:8: error: implicit declaration of function 'acpi_get_rc_resources' [-Werror,-Wimplicit-function-declaration]

Fix them with the obvious one-line changes.

Link: https://lore.kernel.org/r/20210308152501.2135937-2-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Robert Richter <rric@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/controller/pci-thunder-ecam.c |  2 +-
 drivers/pci/controller/pci-thunder-pem.c  | 13 +++++++------
 drivers/pci/pci.h                         |  6 ++++++
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c
index 32d1d7b81ef4..18715d2ce022 100644
--- a/drivers/pci/controller/pci-thunder-ecam.c
+++ b/drivers/pci/controller/pci-thunder-ecam.c
@@ -116,7 +116,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
 	 * the config space access window.  Since we are working with
 	 * the high-order 32 bits, shift everything down by 32 bits.
 	 */
-	node_bits = (cfg->res.start >> 32) & (1 << 12);
+	node_bits = upper_32_bits(cfg->res.start) & (1 << 12);
 
 	v |= node_bits;
 	set_val(v, where, size, val);
diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
index f127ce8bd4ef..1650ec2c35f9 100644
--- a/drivers/pci/controller/pci-thunder-pem.c
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -11,6 +11,7 @@
 #include <linux/pci-acpi.h>
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include "../pci.h"
 
 #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
@@ -314,9 +315,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 	 * structure here for the BAR.
 	 */
 	bar4_start = res_pem->start + 0xf00000;
-	pem_pci->ea_entry[0] = (u32)bar4_start | 2;
-	pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
-	pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
+	pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2;
+	pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u;
+	pem_pci->ea_entry[2] = upper_32_bits(bar4_start);
 
 	cfg->priv = pem_pci;
 	return 0;
@@ -324,9 +325,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 
-#define PEM_RES_BASE		0x87e0c0000000UL
-#define PEM_NODE_MASK		GENMASK(45, 44)
-#define PEM_INDX_MASK		GENMASK(26, 24)
+#define PEM_RES_BASE		0x87e0c0000000ULL
+#define PEM_NODE_MASK		GENMASK_ULL(45, 44)
+#define PEM_INDX_MASK		GENMASK_ULL(26, 24)
 #define PEM_MIN_DOM_IN_NODE	4
 #define PEM_MAX_DOM_IN_NODE	10
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a5adc2e2c351..572c2f0a2f0c 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -588,6 +588,12 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 #if defined(CONFIG_PCI_QUIRKS) && defined(CONFIG_ARM64)
 int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment,
 			  struct resource *res);
+#else
+static inline int acpi_get_rc_resources(struct device *dev, const char *hid,
+					u16 segment, struct resource *res)
+{
+	return -ENODEV;
+}
 #endif
 
 u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar);
-- 
2.30.2

[PATCH AUTOSEL 5.4 02/23] PCI: thunder: Fix compile testing

[Sasha Levin]

From: Arnd Bergmann <arnd@arndb.de>

[ Upstream commit 16f7ae5906dfbeff54f74ec75d0563bb3a87ab0b ]

Compile-testing these drivers is currently broken. Enabling it causes a
couple of build failures though:

  drivers/pci/controller/pci-thunder-ecam.c:119:30: error: shift count >= width of type [-Werror,-Wshift-count-overflow]
  drivers/pci/controller/pci-thunder-pem.c:54:2: error: implicit declaration of function 'writeq' [-Werror,-Wimplicit-function-declaration]
  drivers/pci/controller/pci-thunder-pem.c:392:8: error: implicit declaration of function 'acpi_get_rc_resources' [-Werror,-Wimplicit-function-declaration]

Fix them with the obvious one-line changes.

Link: https://lore.kernel.org/r/20210308152501.2135937-2-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Robert Richter <rric@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/controller/pci-thunder-ecam.c |  2 +-
 drivers/pci/controller/pci-thunder-pem.c  | 13 +++++++------
 drivers/pci/pci.h                         |  6 ++++++
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c
index 32d1d7b81ef4..18715d2ce022 100644
--- a/drivers/pci/controller/pci-thunder-ecam.c
+++ b/drivers/pci/controller/pci-thunder-ecam.c
@@ -116,7 +116,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
 	 * the config space access window.  Since we are working with
 	 * the high-order 32 bits, shift everything down by 32 bits.
 	 */
-	node_bits = (cfg->res.start >> 32) & (1 << 12);
+	node_bits = upper_32_bits(cfg->res.start) & (1 << 12);
 
 	v |= node_bits;
 	set_val(v, where, size, val);
diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
index f127ce8bd4ef..1650ec2c35f9 100644
--- a/drivers/pci/controller/pci-thunder-pem.c
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -11,6 +11,7 @@
 #include <linux/pci-acpi.h>
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include "../pci.h"
 
 #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
@@ -314,9 +315,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 	 * structure here for the BAR.
 	 */
 	bar4_start = res_pem->start + 0xf00000;
-	pem_pci->ea_entry[0] = (u32)bar4_start | 2;
-	pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
-	pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
+	pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2;
+	pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u;
+	pem_pci->ea_entry[2] = upper_32_bits(bar4_start);
 
 	cfg->priv = pem_pci;
 	return 0;
@@ -324,9 +325,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 
-#define PEM_RES_BASE		0x87e0c0000000UL
-#define PEM_NODE_MASK		GENMASK(45, 44)
-#define PEM_INDX_MASK		GENMASK(26, 24)
+#define PEM_RES_BASE		0x87e0c0000000ULL
+#define PEM_NODE_MASK		GENMASK_ULL(45, 44)
+#define PEM_INDX_MASK		GENMASK_ULL(26, 24)
 #define PEM_MIN_DOM_IN_NODE	4
 #define PEM_MAX_DOM_IN_NODE	10
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a5adc2e2c351..572c2f0a2f0c 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -588,6 +588,12 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 #if defined(CONFIG_PCI_QUIRKS) && defined(CONFIG_ARM64)
 int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment,
 			  struct resource *res);
+#else
+static inline int acpi_get_rc_resources(struct device *dev, const char *hid,
+					u16 segment, struct resource *res)
+{
+	return -ENODEV;
+}
 #endif
 
 u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar);
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.4 03/23] dmaengine: dw-edma: Fix crash on loading/unloading driver

[Sasha Levin]

From: Gustavo Pimentel <Gustavo.Pimentel@synopsys.com>

[ Upstream commit e970dcc4bd8e0a1376e794fc81d41d0fc98262dd ]

When the driver is compiled as a module and loaded if we try to unload
it, the Kernel shows a crash log. This Kernel crash is due to the
dma_async_device_unregister() call done after deleting the channels,
this patch fixes this issue.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Link: https://lore.kernel.org/r/4aa850c035cf7ee488f1d3fb6dee0e37be0dce0a.1613674948.git.gustavo.pimentel@synopsys.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/dma/dw-edma/dw-edma-core.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 31577316f80b..afbd1a459019 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -910,22 +910,21 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 	/* Power management */
 	pm_runtime_disable(dev);
 
+	/* Deregister eDMA device */
+	dma_async_device_unregister(&dw->wr_edma);
 	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
 				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
 		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
 	}
 
+	dma_async_device_unregister(&dw->rd_edma);
 	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
 				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
 		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
 	}
 
-	/* Deregister eDMA device */
-	dma_async_device_unregister(&dw->wr_edma);
-	dma_async_device_unregister(&dw->rd_edma);
-
 	/* Turn debugfs off */
 	dw_edma_v0_core_debugfs_off();
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 04/23] ARM: 9066/1: ftrace: pause/unpause function graph tracer in cpu_suspend()

[Sasha Levin]

From: "louis.wang" <liang26812@gmail.com>

[ Upstream commit 8252ca87c7a2111502ee13994956f8c309faad7f ]

Enabling function_graph tracer on ARM causes kernel panic, because the
function graph tracer updates the "return address" of a function in order
to insert a trace callback on function exit, it saves the function's
original return address in a return trace stack, but cpu_suspend() may not
return through the normal return path.

cpu_suspend() will resume directly via the cpu_resume path, but the return
trace stack has been set-up by the subfunctions of cpu_suspend(), which
makes the "return address" inconsistent with cpu_suspend().

This patch refers to Commit de818bd4522c40ea02a81b387d2fa86f989c9623
("arm64: kernel: pause/unpause function graph tracer in cpu_suspend()"),

fixes the issue by pausing/resuming the function graph tracer on the thread
executing cpu_suspend(), so that the function graph tracer state is kept
consistent across functions that enter power down states and never return
by effectively disabling graph tracer while they are executing.

Signed-off-by: louis.wang <liang26812@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/kernel/suspend.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index d08099269e35..e126386fb78a 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
@@ -26,6 +27,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	if (!idmap_pgd)
 		return -EINVAL;
 
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
 	/*
 	 * Provide a temporary page table with an identity mapping for
 	 * the MMU-enable code, required for resuming.  On successful
@@ -33,6 +41,9 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * back to the correct page tables.
 	 */
 	ret = __cpu_suspend(arg, fn, __mpidr);
+
+	unpause_graph_tracing();
+
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_bp_all();
@@ -46,7 +57,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	u32 __mpidr = cpu_logical_map(smp_processor_id());
-	return __cpu_suspend(arg, fn, __mpidr);
+	int ret;
+
+	pause_graph_tracing();
+	ret = __cpu_suspend(arg, fn, __mpidr);
+	unpause_graph_tracing();
+
+	return ret;
 }
 #define	idmap_pgd	NULL
 #endif
-- 
2.30.2

[PATCH AUTOSEL 5.4 04/23] ARM: 9066/1: ftrace: pause/unpause function graph tracer in cpu_suspend()

[Sasha Levin]

From: "louis.wang" <liang26812@gmail.com>

[ Upstream commit 8252ca87c7a2111502ee13994956f8c309faad7f ]

Enabling function_graph tracer on ARM causes kernel panic, because the
function graph tracer updates the "return address" of a function in order
to insert a trace callback on function exit, it saves the function's
original return address in a return trace stack, but cpu_suspend() may not
return through the normal return path.

cpu_suspend() will resume directly via the cpu_resume path, but the return
trace stack has been set-up by the subfunctions of cpu_suspend(), which
makes the "return address" inconsistent with cpu_suspend().

This patch refers to Commit de818bd4522c40ea02a81b387d2fa86f989c9623
("arm64: kernel: pause/unpause function graph tracer in cpu_suspend()"),

fixes the issue by pausing/resuming the function graph tracer on the thread
executing cpu_suspend(), so that the function graph tracer state is kept
consistent across functions that enter power down states and never return
by effectively disabling graph tracer while they are executing.

Signed-off-by: louis.wang <liang26812@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/kernel/suspend.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index d08099269e35..e126386fb78a 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
@@ -26,6 +27,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	if (!idmap_pgd)
 		return -EINVAL;
 
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
 	/*
 	 * Provide a temporary page table with an identity mapping for
 	 * the MMU-enable code, required for resuming.  On successful
@@ -33,6 +41,9 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * back to the correct page tables.
 	 */
 	ret = __cpu_suspend(arg, fn, __mpidr);
+
+	unpause_graph_tracing();
+
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_bp_all();
@@ -46,7 +57,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	u32 __mpidr = cpu_logical_map(smp_processor_id());
-	return __cpu_suspend(arg, fn, __mpidr);
+	int ret;
+
+	pause_graph_tracing();
+	ret = __cpu_suspend(arg, fn, __mpidr);
+	unpause_graph_tracing();
+
+	return ret;
 }
 #define	idmap_pgd	NULL
 #endif
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.4 05/23] f2fs: fix to avoid out-of-bounds memory access

[Sasha Levin]

From: Chao Yu <yuchao0@huawei.com>

[ Upstream commit b862676e371715456c9dade7990c8004996d0d9e ]

butt3rflyh4ck <butterflyhuangxx@gmail.com> reported a bug found by
syzkaller fuzzer with custom modifications in 5.12.0-rc3+ [1]:

 dump_stack+0xfa/0x151 lib/dump_stack.c:120
 print_address_description.constprop.0.cold+0x82/0x32c mm/kasan/report.c:232
 __kasan_report mm/kasan/report.c:399 [inline]
 kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416
 f2fs_test_bit fs/f2fs/f2fs.h:2572 [inline]
 current_nat_addr fs/f2fs/node.h:213 [inline]
 get_next_nat_page fs/f2fs/node.c:123 [inline]
 __flush_nat_entry_set fs/f2fs/node.c:2888 [inline]
 f2fs_flush_nat_entries+0x258e/0x2960 fs/f2fs/node.c:2991
 f2fs_write_checkpoint+0x1372/0x6a70 fs/f2fs/checkpoint.c:1640
 f2fs_issue_checkpoint+0x149/0x410 fs/f2fs/checkpoint.c:1807
 f2fs_sync_fs+0x20f/0x420 fs/f2fs/super.c:1454
 __sync_filesystem fs/sync.c:39 [inline]
 sync_filesystem fs/sync.c:67 [inline]
 sync_filesystem+0x1b5/0x260 fs/sync.c:48
 generic_shutdown_super+0x70/0x370 fs/super.c:448
 kill_block_super+0x97/0xf0 fs/super.c:1394

The root cause is, if nat entry in checkpoint journal area is corrupted,
e.g. nid of journalled nat entry exceeds max nid value, during checkpoint,
once it tries to flush nat journal to NAT area, get_next_nat_page() may
access out-of-bounds memory on nat_bitmap due to it uses wrong nid value
as bitmap offset.

[1] https://lore.kernel.org/lkml/CAFcO6XOMWdr8pObek6eN6-fs58KG9doRFadgJj-FnF-1x43s2g@mail.gmail.com/T/#u

Reported-and-tested-by: butt3rflyh4ck <butterflyhuangxx@gmail.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/node.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7ce33698ae38..48bb5d3c709d 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2718,6 +2718,9 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 		struct f2fs_nat_entry raw_ne;
 		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
+		if (f2fs_check_nid_range(sbi, nid))
+			continue;
+
 		raw_ne = nat_in_journal(journal, i);
 
 		ne = __lookup_nat_cache(nm_i, nid);
-- 
2.30.2

[f2fs-dev] [PATCH AUTOSEL 5.4 05/23] f2fs: fix to avoid out-of-bounds memory access

[Sasha Levin]

From: Chao Yu <yuchao0@huawei.com>

[ Upstream commit b862676e371715456c9dade7990c8004996d0d9e ]

butt3rflyh4ck <butterflyhuangxx@gmail.com> reported a bug found by
syzkaller fuzzer with custom modifications in 5.12.0-rc3+ [1]:

 dump_stack+0xfa/0x151 lib/dump_stack.c:120
 print_address_description.constprop.0.cold+0x82/0x32c mm/kasan/report.c:232
 __kasan_report mm/kasan/report.c:399 [inline]
 kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416
 f2fs_test_bit fs/f2fs/f2fs.h:2572 [inline]
 current_nat_addr fs/f2fs/node.h:213 [inline]
 get_next_nat_page fs/f2fs/node.c:123 [inline]
 __flush_nat_entry_set fs/f2fs/node.c:2888 [inline]
 f2fs_flush_nat_entries+0x258e/0x2960 fs/f2fs/node.c:2991
 f2fs_write_checkpoint+0x1372/0x6a70 fs/f2fs/checkpoint.c:1640
 f2fs_issue_checkpoint+0x149/0x410 fs/f2fs/checkpoint.c:1807
 f2fs_sync_fs+0x20f/0x420 fs/f2fs/super.c:1454
 __sync_filesystem fs/sync.c:39 [inline]
 sync_filesystem fs/sync.c:67 [inline]
 sync_filesystem+0x1b5/0x260 fs/sync.c:48
 generic_shutdown_super+0x70/0x370 fs/super.c:448
 kill_block_super+0x97/0xf0 fs/super.c:1394

The root cause is, if nat entry in checkpoint journal area is corrupted,
e.g. nid of journalled nat entry exceeds max nid value, during checkpoint,
once it tries to flush nat journal to NAT area, get_next_nat_page() may
access out-of-bounds memory on nat_bitmap due to it uses wrong nid value
as bitmap offset.

[1] https://lore.kernel.org/lkml/CAFcO6XOMWdr8pObek6eN6-fs58KG9doRFadgJj-FnF-1x43s2g@mail.gmail.com/T/#u

Reported-and-tested-by: butt3rflyh4ck <butterflyhuangxx@gmail.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/f2fs/node.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7ce33698ae38..48bb5d3c709d 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2718,6 +2718,9 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 		struct f2fs_nat_entry raw_ne;
 		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
+		if (f2fs_check_nid_range(sbi, nid))
+			continue;
+
 		raw_ne = nat_in_journal(journal, i);
 
 		ne = __lookup_nat_cache(nm_i, nid);
-- 
2.30.2



_______________________________________________
Linux-f2fs-devel mailing list
Linux-f2fs-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel

[PATCH AUTOSEL 5.4 06/23] ACPI / hotplug / PCI: Fix reference count leak in enable_slot()

[Sasha Levin]

From: Feilong Lin <linfeilong@huawei.com>

[ Upstream commit 3bbfd319034ddce59e023837a4aa11439460509b ]

In enable_slot(), if pci_get_slot() returns NULL, we clear the SLOT_ENABLED
flag. When pci_get_slot() finds a device, it increments the device's
reference count.  In this case, we did not call pci_dev_put() to decrement
the reference count, so the memory of the device (struct pci_dev type) will
eventually leak.

Call pci_dev_put() to decrement its reference count when pci_get_slot()
returns a PCI device.

Link: https://lore.kernel.org/r/b411af88-5049-a1c6-83ac-d104a1f429be@huawei.com
Signed-off-by: Feilong Lin <linfeilong@huawei.com>
Signed-off-by: Zhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/pci/hotplug/acpiphp_glue.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 6e60b4b1bf53..98be06ac2af2 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -540,6 +540,7 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
 			slot->flags &= ~SLOT_ENABLED;
 			continue;
 		}
+		pci_dev_put(dev);
 	}
 }
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 07/23] Input: elants_i2c - do not bind to i2c-hid compatible ACPI instantiated devices

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit 65299e8bfb24774e6340e93ae49f6626598917c8 ]

Several users have been reporting that elants_i2c gives several errors
during probe and that their touchscreen does not work on their Lenovo AMD
based laptops with a touchscreen with a ELAN0001 ACPI hardware-id:

[    0.550596] elants_i2c i2c-ELAN0001:00: i2c-ELAN0001:00 supply vcc33 not found, using dummy regulator
[    0.551836] elants_i2c i2c-ELAN0001:00: i2c-ELAN0001:00 supply vccio not found, using dummy regulator
[    0.560932] elants_i2c i2c-ELAN0001:00: elants_i2c_send failed (77 77 77 77): -121
[    0.562427] elants_i2c i2c-ELAN0001:00: software reset failed: -121
[    0.595925] elants_i2c i2c-ELAN0001:00: elants_i2c_send failed (77 77 77 77): -121
[    0.597974] elants_i2c i2c-ELAN0001:00: software reset failed: -121
[    0.621893] elants_i2c i2c-ELAN0001:00: elants_i2c_send failed (77 77 77 77): -121
[    0.622504] elants_i2c i2c-ELAN0001:00: software reset failed: -121
[    0.632650] elants_i2c i2c-ELAN0001:00: elants_i2c_send failed (4d 61 69 6e): -121
[    0.634256] elants_i2c i2c-ELAN0001:00: boot failed: -121
[    0.699212] elants_i2c i2c-ELAN0001:00: invalid 'hello' packet: 00 00 ff ff
[    1.630506] elants_i2c i2c-ELAN0001:00: Failed to read fw id: -121
[    1.645508] elants_i2c i2c-ELAN0001:00: unknown packet 00 00 ff ff

Despite these errors, the elants_i2c driver stays bound to the device
(it returns 0 from its probe method despite the errors), blocking the
i2c-hid driver from binding.

Manually unbinding the elants_i2c driver and binding the i2c-hid driver
makes the touchscreen work.

Check if the ACPI-fwnode for the touchscreen contains one of the i2c-hid
compatiblity-id strings and if it has the I2C-HID spec's DSM to get the
HID descriptor address, If it has both then make elants_i2c not bind,
so that the i2c-hid driver can bind.

This assumes that non of the (older) elan touchscreens which actually
need the elants_i2c driver falsely advertise an i2c-hid compatiblity-id
+ DSM in their ACPI-fwnodes. If some of them actually do have this
false advertising, then this change may lead to regressions.

While at it also drop the unnecessary DEVICE_NAME prefixing of the
"I2C check functionality error", dev_err already outputs the driver-name.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=207759
Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210405202756.16830-1-hdegoede@redhat.com

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/input/touchscreen/elants_i2c.c | 44 ++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index d4ad24ea54c8..a51e7c85f581 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -36,6 +36,7 @@
 #include <linux/of.h>
 #include <linux/gpio/consumer.h>
 #include <linux/regulator/consumer.h>
+#include <linux/uuid.h>
 #include <asm/unaligned.h>
 
 /* Device, Driver information */
@@ -1127,6 +1128,40 @@ static void elants_i2c_power_off(void *_data)
 	}
 }
 
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id i2c_hid_ids[] = {
+	{"ACPI0C50", 0 },
+	{"PNP0C50", 0 },
+	{ },
+};
+
+static const guid_t i2c_hid_guid =
+	GUID_INIT(0x3CDFF6F7, 0x4267, 0x4555,
+		  0xAD, 0x05, 0xB3, 0x0A, 0x3D, 0x89, 0x38, 0xDE);
+
+static bool elants_acpi_is_hid_device(struct device *dev)
+{
+	acpi_handle handle = ACPI_HANDLE(dev);
+	union acpi_object *obj;
+
+	if (acpi_match_device_ids(ACPI_COMPANION(dev), i2c_hid_ids))
+		return false;
+
+	obj = acpi_evaluate_dsm_typed(handle, &i2c_hid_guid, 1, 1, NULL, ACPI_TYPE_INTEGER);
+	if (obj) {
+		ACPI_FREE(obj);
+		return true;
+	}
+
+	return false;
+}
+#else
+static bool elants_acpi_is_hid_device(struct device *dev)
+{
+	return false;
+}
+#endif
+
 static int elants_i2c_probe(struct i2c_client *client,
 			    const struct i2c_device_id *id)
 {
@@ -1135,9 +1170,14 @@ static int elants_i2c_probe(struct i2c_client *client,
 	unsigned long irqflags;
 	int error;
 
+	/* Don't bind to i2c-hid compatible devices, these are handled by the i2c-hid drv. */
+	if (elants_acpi_is_hid_device(&client->dev)) {
+		dev_warn(&client->dev, "This device appears to be an I2C-HID device, not binding\n");
+		return -ENODEV;
+	}
+
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
-		dev_err(&client->dev,
-			"%s: i2c check functionality error\n", DEVICE_NAME);
+		dev_err(&client->dev, "I2C check functionality error\n");
 		return -ENXIO;
 	}
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 08/23] Input: silead - add workaround for x86 BIOS-es which bring the chip up in a stuck state

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit e479187748a8f151a85116a7091c599b121fdea5 ]

Some buggy BIOS-es bring up the touchscreen-controller in a stuck
state where it blocks the I2C bus. Specifically this happens on
the Jumper EZpad 7 tablet model.

After much poking at this problem I have found that the following steps
are necessary to unstuck the chip / bus:

1. Turn off the Silead chip.
2. Try to do an I2C transfer with the chip, this will fail in response to
   which the I2C-bus-driver will call: i2c_recover_bus() which will unstuck
   the I2C-bus. Note the unstuck-ing of the I2C bus only works if we first
   drop the chip of the bus by turning it off.
3. Turn the chip back on.

On the x86/ACPI systems were this problem is seen, step 1. and 3. require
making ACPI calls and dealing with ACPI Power Resources. This commit adds
a workaround which runtime-suspends the chip to turn it off, leaving it up
to the ACPI subsystem to deal with all the ACPI specific details.

There is no good way to detect this bug, so the workaround gets activated
by a new "silead,stuck-controller-bug" boolean device-property. Since this
is only used on x86/ACPI, this will be set by model specific device-props
set by drivers/platform/x86/touchscreen_dmi.c. Therefor this new
device-property is not documented in the DT-bindings.

Dmesg will contain the following messages on systems where the workaround
is activated:

[   54.309029] silead_ts i2c-MSSL1680:00: [Firmware Bug]: Stuck I2C bus: please ignore the next 'controller timed out' error
[   55.373593] i2c_designware 808622C1:04: controller timed out
[   55.582186] silead_ts i2c-MSSL1680:00: Silead chip ID: 0x80360000

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20210405202745.16777-1-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/input/touchscreen/silead.c | 44 +++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 4 deletions(-)

diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c
index ad8b6a2bfd36..c8776146f1d1 100644
--- a/drivers/input/touchscreen/silead.c
+++ b/drivers/input/touchscreen/silead.c
@@ -20,6 +20,7 @@
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
 #include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/regulator/consumer.h>
 
@@ -335,10 +336,8 @@ static int silead_ts_get_id(struct i2c_client *client)
 
 	error = i2c_smbus_read_i2c_block_data(client, SILEAD_REG_ID,
 					      sizeof(chip_id), (u8 *)&chip_id);
-	if (error < 0) {
-		dev_err(&client->dev, "Chip ID read error %d\n", error);
+	if (error < 0)
 		return error;
-	}
 
 	data->chip_id = le32_to_cpu(chip_id);
 	dev_info(&client->dev, "Silead chip ID: 0x%8X", data->chip_id);
@@ -351,12 +350,49 @@ static int silead_ts_setup(struct i2c_client *client)
 	int error;
 	u32 status;
 
+	/*
+	 * Some buggy BIOS-es bring up the chip in a stuck state where it
+	 * blocks the I2C bus. The following steps are necessary to
+	 * unstuck the chip / bus:
+	 * 1. Turn off the Silead chip.
+	 * 2. Try to do an I2C transfer with the chip, this will fail in
+	 *    response to which the I2C-bus-driver will call:
+	 *    i2c_recover_bus() which will unstuck the I2C-bus. Note the
+	 *    unstuck-ing of the I2C bus only works if we first drop the
+	 *    chip off the bus by turning it off.
+	 * 3. Turn the chip back on.
+	 *
+	 * On the x86/ACPI systems were this problem is seen, step 1. and
+	 * 3. require making ACPI calls and dealing with ACPI Power
+	 * Resources. The workaround below runtime-suspends the chip to
+	 * turn it off, leaving it up to the ACPI subsystem to deal with
+	 * this.
+	 */
+
+	if (device_property_read_bool(&client->dev,
+				      "silead,stuck-controller-bug")) {
+		pm_runtime_set_active(&client->dev);
+		pm_runtime_enable(&client->dev);
+		pm_runtime_allow(&client->dev);
+
+		pm_runtime_suspend(&client->dev);
+
+		dev_warn(&client->dev, FW_BUG "Stuck I2C bus: please ignore the next 'controller timed out' error\n");
+		silead_ts_get_id(client);
+
+		/* The forbid will also resume the device */
+		pm_runtime_forbid(&client->dev);
+		pm_runtime_disable(&client->dev);
+	}
+
 	silead_ts_set_power(client, SILEAD_POWER_OFF);
 	silead_ts_set_power(client, SILEAD_POWER_ON);
 
 	error = silead_ts_get_id(client);
-	if (error)
+	if (error) {
+		dev_err(&client->dev, "Chip ID read error %d\n", error);
 		return error;
+	}
 
 	error = silead_ts_init(client);
 	if (error)
-- 
2.30.2

[PATCH AUTOSEL 5.4 09/23] um: Mark all kernel symbols as local

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit d5027ca63e0e778b641cf23e3f5c6d6212cf412b ]

Ritesh reported a bug [1] against UML, noting that it crashed on
startup. The backtrace shows the following (heavily redacted):

(gdb) bt
...
 #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268
 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2
 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72
...
 #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359
...
 #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486
 #45 0x00007f8990968b85 in __getgrnam_r [...]
 #46 0x00007f89909d6b77 in grantpt [...]
 #47 0x00007f8990a9394e in __GI_openpty [...]
 #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407
 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598
 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45
 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334
 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144

indicating that the UML function openpty_cb() calls openpty(),
which internally calls __getgrnam_r(), which causes the nsswitch
machinery to get started.

This loads, through lots of indirection that I snipped, the
libcom_err.so.2 library, which (in an unknown function, "??")
calls sem_init().

Now, of course it wants to get libpthread's sem_init(), since
it's linked against libpthread. However, the dynamic linker
looks up that symbol against the binary first, and gets the
kernel's sem_init().

Hajime Tazaki noted that "objcopy -L" can localize a symbol,
so the dynamic linker wouldn't do the lookup this way. I tried,
but for some reason that didn't seem to work.

Doing the same thing in the linker script instead does seem to
work, though I cannot entirely explain - it *also* works if I
just add "VERSION { { global: *; }; }" instead, indicating that
something else is happening that I don't really understand. It
may be that explicitly doing that marks them with some kind of
empty version, and that's different from the default.

Explicitly marking them with a version breaks kallsyms, so that
doesn't seem to be possible.

Marking all the symbols as local seems correct, and does seem
to address the issue, so do that. Also do it for static link,
nsswitch libraries could still be loaded there.

[1] https://bugs.debian.org/983379

Reported-by: Ritesh Raj Sarraf <rrs@debian.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Acked-By: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Tested-By: Ritesh Raj Sarraf <rrs@debian.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/um/kernel/dyn.lds.S | 6 ++++++
 arch/um/kernel/uml.lds.S | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index f5001481010c..a82ec0113321 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -6,6 +6,12 @@ OUTPUT_ARCH(ELF_ARCH)
 ENTRY(_start)
 jiffies = jiffies_64;
 
+VERSION {
+  {
+    local: *;
+  };
+}
+
 SECTIONS
 {
   PROVIDE (__executable_start = START);
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 9f21443be2c9..85b404d068f4 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -7,6 +7,12 @@ OUTPUT_ARCH(ELF_ARCH)
 ENTRY(_start)
 jiffies = jiffies_64;
 
+VERSION {
+  {
+    local: *;
+  };
+}
+
 SECTIONS
 {
   /* This must contain the right address - not quite the default ELF one.*/
-- 
2.30.2

[PATCH AUTOSEL 5.4 09/23] um: Mark all kernel symbols as local

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit d5027ca63e0e778b641cf23e3f5c6d6212cf412b ]

Ritesh reported a bug [1] against UML, noting that it crashed on
startup. The backtrace shows the following (heavily redacted):

(gdb) bt
...
 #26 0x0000000060015b5d in sem_init () at ipc/sem.c:268
 #27 0x00007f89906d92f7 in ?? () from /lib/x86_64-linux-gnu/libcom_err.so.2
 #28 0x00007f8990ab8fb2 in call_init (...) at dl-init.c:72
...
 #40 0x00007f89909bf3a6 in nss_load_library (...) at nsswitch.c:359
...
 #44 0x00007f8990895e35 in _nss_compat_getgrnam_r (...) at nss_compat/compat-grp.c:486
 #45 0x00007f8990968b85 in __getgrnam_r [...]
 #46 0x00007f89909d6b77 in grantpt [...]
 #47 0x00007f8990a9394e in __GI_openpty [...]
 #48 0x00000000604a1f65 in openpty_cb (...) at arch/um/os-Linux/sigio.c:407
 #49 0x00000000604a58d0 in start_idle_thread (...) at arch/um/os-Linux/skas/process.c:598
 #50 0x0000000060004a3d in start_uml () at arch/um/kernel/skas/process.c:45
 #51 0x00000000600047b2 in linux_main (...) at arch/um/kernel/um_arch.c:334
 #52 0x000000006000574f in main (...) at arch/um/os-Linux/main.c:144

indicating that the UML function openpty_cb() calls openpty(),
which internally calls __getgrnam_r(), which causes the nsswitch
machinery to get started.

This loads, through lots of indirection that I snipped, the
libcom_err.so.2 library, which (in an unknown function, "??")
calls sem_init().

Now, of course it wants to get libpthread's sem_init(), since
it's linked against libpthread. However, the dynamic linker
looks up that symbol against the binary first, and gets the
kernel's sem_init().

Hajime Tazaki noted that "objcopy -L" can localize a symbol,
so the dynamic linker wouldn't do the lookup this way. I tried,
but for some reason that didn't seem to work.

Doing the same thing in the linker script instead does seem to
work, though I cannot entirely explain - it *also* works if I
just add "VERSION { { global: *; }; }" instead, indicating that
something else is happening that I don't really understand. It
may be that explicitly doing that marks them with some kind of
empty version, and that's different from the default.

Explicitly marking them with a version breaks kallsyms, so that
doesn't seem to be possible.

Marking all the symbols as local seems correct, and does seem
to address the issue, so do that. Also do it for static link,
nsswitch libraries could still be loaded there.

[1] https://bugs.debian.org/983379

Reported-by: Ritesh Raj Sarraf <rrs@debian.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Acked-By: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Tested-By: Ritesh Raj Sarraf <rrs@debian.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/um/kernel/dyn.lds.S | 6 ++++++
 arch/um/kernel/uml.lds.S | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/arch/um/kernel/dyn.lds.S b/arch/um/kernel/dyn.lds.S
index f5001481010c..a82ec0113321 100644
--- a/arch/um/kernel/dyn.lds.S
+++ b/arch/um/kernel/dyn.lds.S
@@ -6,6 +6,12 @@ OUTPUT_ARCH(ELF_ARCH)
 ENTRY(_start)
 jiffies = jiffies_64;
 
+VERSION {
+  {
+    local: *;
+  };
+}
+
 SECTIONS
 {
   PROVIDE (__executable_start = START);
diff --git a/arch/um/kernel/uml.lds.S b/arch/um/kernel/uml.lds.S
index 9f21443be2c9..85b404d068f4 100644
--- a/arch/um/kernel/uml.lds.S
+++ b/arch/um/kernel/uml.lds.S
@@ -7,6 +7,12 @@ OUTPUT_ARCH(ELF_ARCH)
 ENTRY(_start)
 jiffies = jiffies_64;
 
+VERSION {
+  {
+    local: *;
+  };
+}
+
 SECTIONS
 {
   /* This must contain the right address - not quite the default ELF one.*/
-- 
2.30.2


_______________________________________________
linux-um mailing list
linux-um@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-um

[PATCH AUTOSEL 5.4 10/23] um: Disable CONFIG_GCOV with MODULES

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit ad3d19911632debc886ef4a992d41d6de7927006 ]

CONFIG_GCOV doesn't work with modules, and for various reasons
it cannot work, see also
https://lore.kernel.org/r/d36ea54d8c0a8dd706826ba844a6f27691f45d55.camel@sipsolutions.net

Make CONFIG_GCOV depend on !MODULES to avoid anyone
running into issues there. This also means we need
not export the gcov symbols.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/um/Kconfig.debug      |  1 +
 arch/um/kernel/Makefile    |  1 -
 arch/um/kernel/gmon_syms.c | 16 ----------------
 3 files changed, 1 insertion(+), 17 deletions(-)
 delete mode 100644 arch/um/kernel/gmon_syms.c

diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug
index 85726eeec345..e4a0f12f20d9 100644
--- a/arch/um/Kconfig.debug
+++ b/arch/um/Kconfig.debug
@@ -17,6 +17,7 @@ config GCOV
 	bool "Enable gcov support"
 	depends on DEBUG_INFO
 	depends on !KCOV
+	depends on !MODULES
 	help
 	  This option allows developers to retrieve coverage data from a UML
 	  session.
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 5aa882011e04..e698e0c7dbdc 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -21,7 +21,6 @@ obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
-obj-$(CONFIG_GCOV)	+= gmon_syms.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 
diff --git a/arch/um/kernel/gmon_syms.c b/arch/um/kernel/gmon_syms.c
deleted file mode 100644
index 9361a8eb9bf1..000000000000
--- a/arch/um/kernel/gmon_syms.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/module.h>
-
-extern void __bb_init_func(void *)  __attribute__((weak));
-EXPORT_SYMBOL(__bb_init_func);
-
-extern void __gcov_init(void *)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_init);
-extern void __gcov_merge_add(void *, unsigned int)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_merge_add);
-extern void __gcov_exit(void)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_exit);
-- 
2.30.2

[PATCH AUTOSEL 5.4 10/23] um: Disable CONFIG_GCOV with MODULES

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit ad3d19911632debc886ef4a992d41d6de7927006 ]

CONFIG_GCOV doesn't work with modules, and for various reasons
it cannot work, see also
https://lore.kernel.org/r/d36ea54d8c0a8dd706826ba844a6f27691f45d55.camel@sipsolutions.net

Make CONFIG_GCOV depend on !MODULES to avoid anyone
running into issues there. This also means we need
not export the gcov symbols.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/um/Kconfig.debug      |  1 +
 arch/um/kernel/Makefile    |  1 -
 arch/um/kernel/gmon_syms.c | 16 ----------------
 3 files changed, 1 insertion(+), 17 deletions(-)
 delete mode 100644 arch/um/kernel/gmon_syms.c

diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug
index 85726eeec345..e4a0f12f20d9 100644
--- a/arch/um/Kconfig.debug
+++ b/arch/um/Kconfig.debug
@@ -17,6 +17,7 @@ config GCOV
 	bool "Enable gcov support"
 	depends on DEBUG_INFO
 	depends on !KCOV
+	depends on !MODULES
 	help
 	  This option allows developers to retrieve coverage data from a UML
 	  session.
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 5aa882011e04..e698e0c7dbdc 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -21,7 +21,6 @@ obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
 
 obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
 obj-$(CONFIG_GPROF)	+= gprof_syms.o
-obj-$(CONFIG_GCOV)	+= gmon_syms.o
 obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 
diff --git a/arch/um/kernel/gmon_syms.c b/arch/um/kernel/gmon_syms.c
deleted file mode 100644
index 9361a8eb9bf1..000000000000
--- a/arch/um/kernel/gmon_syms.c
+++ /dev/null
@@ -1,16 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- */
-
-#include <linux/module.h>
-
-extern void __bb_init_func(void *)  __attribute__((weak));
-EXPORT_SYMBOL(__bb_init_func);
-
-extern void __gcov_init(void *)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_init);
-extern void __gcov_merge_add(void *, unsigned int)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_merge_add);
-extern void __gcov_exit(void)  __attribute__((weak));
-EXPORT_SYMBOL(__gcov_exit);
-- 
2.30.2


_______________________________________________
linux-um mailing list
linux-um@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-um

[PATCH AUTOSEL 5.4 11/23] ARM: 9075/1: kernel: Fix interrupted SMC calls

[Sasha Levin]

From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>

[ Upstream commit 57ac51667d8cd62731223d687e5fe7b41c502f89 ]

On Qualcomm ARM32 platforms, the SMC call can return before it has
completed. If this occurs, the call can be restarted, but it requires
using the returned session ID value from the interrupted SMC call.

The ARM32 SMCC code already has the provision to add platform specific
quirks for things like this. So let's make use of it and add the
Qualcomm specific quirk (ARM_SMCCC_QUIRK_QCOM_A6) used by the QCOM_SCM
driver.

This change is similar to the below one added for ARM64 a while ago:
commit 82bcd087029f ("firmware: qcom: scm: Fix interrupted SCM calls")

Without this change, the Qualcomm ARM32 platforms like SDX55 will return
-EINVAL for SMC calls used for modem firmware loading and validation.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/kernel/asm-offsets.c |  3 +++
 arch/arm/kernel/smccc-call.S  | 11 ++++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index bfb05c93494d..4ce2e29da14d 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -27,6 +27,7 @@
 #include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 #include "signal.h"
 
 /*
@@ -160,6 +161,8 @@ int main(void)
   DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
   DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
 #endif
+  DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
+  DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
   BLANK();
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
index 00664c78faca..931df62a7831 100644
--- a/arch/arm/kernel/smccc-call.S
+++ b/arch/arm/kernel/smccc-call.S
@@ -3,7 +3,9 @@
  * Copyright (c) 2015, Linaro Limited
  */
 #include <linux/linkage.h>
+#include <linux/arm-smccc.h>
 
+#include <asm/asm-offsets.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/unwind.h>
@@ -27,7 +29,14 @@ UNWIND(	.fnstart)
 UNWIND(	.save	{r4-r7})
 	ldm	r12, {r4-r7}
 	\instr
-	pop	{r4-r7}
+	ldr	r4, [sp, #36]
+	cmp	r4, #0
+	beq	1f			// No quirk structure
+	ldr     r5, [r4, #ARM_SMCCC_QUIRK_ID_OFFS]
+	cmp     r5, #ARM_SMCCC_QUIRK_QCOM_A6
+	bne	1f			// No quirk present
+	str	r6, [r4, #ARM_SMCCC_QUIRK_STATE_OFFS]
+1:	pop	{r4-r7}
 	ldr	r12, [sp, #(4 * 4)]
 	stm	r12, {r0-r3}
 	bx	lr
-- 
2.30.2

[PATCH AUTOSEL 5.4 11/23] ARM: 9075/1: kernel: Fix interrupted SMC calls

[Sasha Levin]

From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>

[ Upstream commit 57ac51667d8cd62731223d687e5fe7b41c502f89 ]

On Qualcomm ARM32 platforms, the SMC call can return before it has
completed. If this occurs, the call can be restarted, but it requires
using the returned session ID value from the interrupted SMC call.

The ARM32 SMCC code already has the provision to add platform specific
quirks for things like this. So let's make use of it and add the
Qualcomm specific quirk (ARM_SMCCC_QUIRK_QCOM_A6) used by the QCOM_SCM
driver.

This change is similar to the below one added for ARM64 a while ago:
commit 82bcd087029f ("firmware: qcom: scm: Fix interrupted SCM calls")

Without this change, the Qualcomm ARM32 platforms like SDX55 will return
-EINVAL for SMC calls used for modem firmware loading and validation.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/kernel/asm-offsets.c |  3 +++
 arch/arm/kernel/smccc-call.S  | 11 ++++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index bfb05c93494d..4ce2e29da14d 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -27,6 +27,7 @@
 #include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 #include "signal.h"
 
 /*
@@ -160,6 +161,8 @@ int main(void)
   DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
   DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
 #endif
+  DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
+  DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
   BLANK();
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
index 00664c78faca..931df62a7831 100644
--- a/arch/arm/kernel/smccc-call.S
+++ b/arch/arm/kernel/smccc-call.S
@@ -3,7 +3,9 @@
  * Copyright (c) 2015, Linaro Limited
  */
 #include <linux/linkage.h>
+#include <linux/arm-smccc.h>
 
+#include <asm/asm-offsets.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/unwind.h>
@@ -27,7 +29,14 @@ UNWIND(	.fnstart)
 UNWIND(	.save	{r4-r7})
 	ldm	r12, {r4-r7}
 	\instr
-	pop	{r4-r7}
+	ldr	r4, [sp, #36]
+	cmp	r4, #0
+	beq	1f			// No quirk structure
+	ldr     r5, [r4, #ARM_SMCCC_QUIRK_ID_OFFS]
+	cmp     r5, #ARM_SMCCC_QUIRK_QCOM_A6
+	bne	1f			// No quirk present
+	str	r6, [r4, #ARM_SMCCC_QUIRK_STATE_OFFS]
+1:	pop	{r4-r7}
 	ldr	r12, [sp, #(4 * 4)]
 	stm	r12, {r0-r3}
 	bx	lr
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH AUTOSEL 5.4 12/23] scripts/recordmcount.pl: Fix RISC-V regex for clang

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 2f095504f4b9cf75856d6a9cf90299cf75aa46c5 ]

Clang can generate R_RISCV_CALL_PLT relocations to _mcount:

$ llvm-objdump -dr build/riscv/init/main.o | rg mcount
                000000000000000e:  R_RISCV_CALL_PLT     _mcount
                000000000000004e:  R_RISCV_CALL_PLT     _mcount

After this, the __start_mcount_loc section is properly generated and
function tracing still works.

Link: https://github.com/ClangBuiltLinux/linux/issues/1331
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 scripts/recordmcount.pl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 0bafed857e17..857d5b70b1a9 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -395,7 +395,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
 } elsif ($arch eq "riscv") {
     $function_regex = "^([0-9a-fA-F]+)\\s+<([^.0-9][0-9a-zA-Z_\\.]+)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL\\s_mcount\$";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_mcount\$";
     $type = ".quad";
     $alignment = 2;
 } elsif ($arch eq "nds32") {
-- 
2.30.2

[PATCH AUTOSEL 5.4 12/23] scripts/recordmcount.pl: Fix RISC-V regex for clang

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 2f095504f4b9cf75856d6a9cf90299cf75aa46c5 ]

Clang can generate R_RISCV_CALL_PLT relocations to _mcount:

$ llvm-objdump -dr build/riscv/init/main.o | rg mcount
                000000000000000e:  R_RISCV_CALL_PLT     _mcount
                000000000000004e:  R_RISCV_CALL_PLT     _mcount

After this, the __start_mcount_loc section is properly generated and
function tracing still works.

Link: https://github.com/ClangBuiltLinux/linux/issues/1331
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Fangrui Song <maskray@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 scripts/recordmcount.pl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 0bafed857e17..857d5b70b1a9 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -395,7 +395,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
 } elsif ($arch eq "riscv") {
     $function_regex = "^([0-9a-fA-F]+)\\s+<([^.0-9][0-9a-zA-Z_\\.]+)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL\\s_mcount\$";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_mcount\$";
     $type = ".quad";
     $alignment = 2;
 } elsif ($arch eq "nds32") {
-- 
2.30.2


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

[PATCH AUTOSEL 5.4 13/23] riscv: Workaround mcount name prior to clang-13

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 7ce04771503074a7de7f539cc43f5e1b385cb99b ]

Prior to clang 13.0.0, the RISC-V name for the mcount symbol was
"mcount", which differs from the GCC version of "_mcount", which results
in the following errors:

riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_level':
main.c:(.text+0xe): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_start':
main.c:(.text+0x4e): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_finish':
main.c:(.text+0x92): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `.LBB32_28':
main.c:(.text+0x30c): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `free_initmem':
main.c:(.text+0x54c): undefined reference to `mcount'

This has been corrected in https://reviews.llvm.org/D98881 but the
minimum supported clang version is 10.0.1. To avoid build errors and to
gain a working function tracer, adjust the name of the mcount symbol for
older versions of clang in mount.S and recordmcount.pl.

Link: https://github.com/ClangBuiltLinux/linux/issues/1331
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/riscv/include/asm/ftrace.h | 14 ++++++++++++--
 arch/riscv/kernel/mcount.S      | 10 +++++-----
 scripts/recordmcount.pl         |  2 +-
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 02fbc175142e..693c3839a7df 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -10,9 +10,19 @@
 #endif
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
+/*
+ * Clang prior to 13 had "mcount" instead of "_mcount":
+ * https://reviews.llvm.org/D98881
+ */
+#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000
+#define MCOUNT_NAME _mcount
+#else
+#define MCOUNT_NAME mcount
+#endif
+
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #ifndef __ASSEMBLY__
-void _mcount(void);
+void MCOUNT_NAME(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
@@ -33,7 +43,7 @@ struct dyn_arch_ftrace {
  * both auipc and jalr at the same time.
  */
 
-#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define MCOUNT_ADDR		((unsigned long)MCOUNT_NAME)
 #define JALR_SIGN_MASK		(0x00000800)
 #define JALR_OFFSET_MASK	(0x00000fff)
 #define AUIPC_OFFSET_MASK	(0xfffff000)
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 8a5593ff9ff3..6d462681c9c0 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -47,8 +47,8 @@
 
 ENTRY(ftrace_stub)
 #ifdef CONFIG_DYNAMIC_FTRACE
-       .global _mcount
-       .set    _mcount, ftrace_stub
+       .global MCOUNT_NAME
+       .set    MCOUNT_NAME, ftrace_stub
 #endif
 	ret
 ENDPROC(ftrace_stub)
@@ -78,7 +78,7 @@ ENDPROC(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-ENTRY(_mcount)
+ENTRY(MCOUNT_NAME)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
@@ -124,6 +124,6 @@ do_trace:
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-ENDPROC(_mcount)
+ENDPROC(MCOUNT_NAME)
 #endif
-EXPORT_SYMBOL(_mcount)
+EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 857d5b70b1a9..4f84657f55c2 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -395,7 +395,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
 } elsif ($arch eq "riscv") {
     $function_regex = "^([0-9a-fA-F]+)\\s+<([^.0-9][0-9a-zA-Z_\\.]+)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_mcount\$";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_?mcount\$";
     $type = ".quad";
     $alignment = 2;
 } elsif ($arch eq "nds32") {
-- 
2.30.2

[PATCH AUTOSEL 5.4 13/23] riscv: Workaround mcount name prior to clang-13

[Sasha Levin]

From: Nathan Chancellor <nathan@kernel.org>

[ Upstream commit 7ce04771503074a7de7f539cc43f5e1b385cb99b ]

Prior to clang 13.0.0, the RISC-V name for the mcount symbol was
"mcount", which differs from the GCC version of "_mcount", which results
in the following errors:

riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_level':
main.c:(.text+0xe): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_start':
main.c:(.text+0x4e): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `__traceiter_initcall_finish':
main.c:(.text+0x92): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `.LBB32_28':
main.c:(.text+0x30c): undefined reference to `mcount'
riscv64-linux-gnu-ld: init/main.o: in function `free_initmem':
main.c:(.text+0x54c): undefined reference to `mcount'

This has been corrected in https://reviews.llvm.org/D98881 but the
minimum supported clang version is 10.0.1. To avoid build errors and to
gain a working function tracer, adjust the name of the mcount symbol for
older versions of clang in mount.S and recordmcount.pl.

Link: https://github.com/ClangBuiltLinux/linux/issues/1331
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/riscv/include/asm/ftrace.h | 14 ++++++++++++--
 arch/riscv/kernel/mcount.S      | 10 +++++-----
 scripts/recordmcount.pl         |  2 +-
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 02fbc175142e..693c3839a7df 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -10,9 +10,19 @@
 #endif
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
+/*
+ * Clang prior to 13 had "mcount" instead of "_mcount":
+ * https://reviews.llvm.org/D98881
+ */
+#if defined(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 130000
+#define MCOUNT_NAME _mcount
+#else
+#define MCOUNT_NAME mcount
+#endif
+
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #ifndef __ASSEMBLY__
-void _mcount(void);
+void MCOUNT_NAME(void);
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
@@ -33,7 +43,7 @@ struct dyn_arch_ftrace {
  * both auipc and jalr at the same time.
  */
 
-#define MCOUNT_ADDR		((unsigned long)_mcount)
+#define MCOUNT_ADDR		((unsigned long)MCOUNT_NAME)
 #define JALR_SIGN_MASK		(0x00000800)
 #define JALR_OFFSET_MASK	(0x00000fff)
 #define AUIPC_OFFSET_MASK	(0xfffff000)
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 8a5593ff9ff3..6d462681c9c0 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -47,8 +47,8 @@
 
 ENTRY(ftrace_stub)
 #ifdef CONFIG_DYNAMIC_FTRACE
-       .global _mcount
-       .set    _mcount, ftrace_stub
+       .global MCOUNT_NAME
+       .set    MCOUNT_NAME, ftrace_stub
 #endif
 	ret
 ENDPROC(ftrace_stub)
@@ -78,7 +78,7 @@ ENDPROC(return_to_handler)
 #endif
 
 #ifndef CONFIG_DYNAMIC_FTRACE
-ENTRY(_mcount)
+ENTRY(MCOUNT_NAME)
 	la	t4, ftrace_stub
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	la	t0, ftrace_graph_return
@@ -124,6 +124,6 @@ do_trace:
 	jalr	t5
 	RESTORE_ABI_STATE
 	ret
-ENDPROC(_mcount)
+ENDPROC(MCOUNT_NAME)
 #endif
-EXPORT_SYMBOL(_mcount)
+EXPORT_SYMBOL(MCOUNT_NAME)
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 857d5b70b1a9..4f84657f55c2 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -395,7 +395,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
 } elsif ($arch eq "riscv") {
     $function_regex = "^([0-9a-fA-F]+)\\s+<([^.0-9][0-9a-zA-Z_\\.]+)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_mcount\$";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL(_PLT)?\\s_?mcount\$";
     $type = ".quad";
     $alignment = 2;
 } elsif ($arch eq "nds32") {
-- 
2.30.2


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

[PATCH AUTOSEL 5.4 14/23] scsi: lpfc: Fix illegal memory access on Abort IOCBs

[Sasha Levin]

From: James Smart <jsmart2021@gmail.com>

[ Upstream commit e1364711359f3ced054bda9920477c8bf93b74c5 ]

In devloss timer handler and in backend calls to terminate remote port I/O,
there is logic to walk through all active IOCBs and validate them to
potentially trigger an abort request. This logic is causing illegal memory
accesses which leads to a crash. Abort IOCBs, which may be on the list, do
not have an associated lpfc_io_buf struct. The driver is trying to map an
lpfc_io_buf struct on the IOCB and which results in a bogus address thus
the issue.

Fix by skipping over ABORT IOCBs (CLOSE IOCBs are ABORTS that don't send
ABTS) in the IOCB scan logic.

Link: https://lore.kernel.org/r/20210421234433.102079-1-jsmart2021@gmail.com
Co-developed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/scsi/lpfc/lpfc_sli.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index b9857d7b224f..d3a54178bfe1 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -11341,13 +11341,20 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 			   lpfc_ctx_cmd ctx_cmd)
 {
 	struct lpfc_io_buf *lpfc_cmd;
+	IOCB_t *icmd = NULL;
 	int rc = 1;
 
 	if (iocbq->vport != vport)
 		return rc;
 
-	if (!(iocbq->iocb_flag &  LPFC_IO_FCP) ||
-	    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ))
+	if (!(iocbq->iocb_flag & LPFC_IO_FCP) ||
+	    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ) ||
+	      iocbq->iocb_flag & LPFC_DRIVER_ABORTED)
+		return rc;
+
+	icmd = &iocbq->iocb;
+	if (icmd->ulpCommand == CMD_ABORT_XRI_CN ||
+	    icmd->ulpCommand == CMD_CLOSE_XRI_CN)
 		return rc;
 
 	lpfc_cmd = container_of(iocbq, struct lpfc_io_buf, cur_iocbq);
-- 
2.30.2

[PATCH AUTOSEL 5.4 15/23] ceph: fix fscache invalidation

[Sasha Levin]

From: Jeff Layton <jlayton@kernel.org>

[ Upstream commit 10a7052c7868bc7bc72d947f5aac6f768928db87 ]

Ensure that we invalidate the fscache whenever we invalidate the
pagecache.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/caps.c  | 1 +
 fs/ceph/inode.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 22833fa5bb58..a6047caf77ec 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1780,6 +1780,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	u32 invalidating_gen = ci->i_rdcache_gen;
 
 	spin_unlock(&ci->i_ceph_lock);
+	ceph_fscache_invalidate(inode);
 	invalidate_mapping_pages(&inode->i_data, 0, -1);
 	spin_lock(&ci->i_ceph_lock);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 660a878e20ef..5beebbbb42f0 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1875,6 +1875,7 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 	orig_gen = ci->i_rdcache_gen;
 	spin_unlock(&ci->i_ceph_lock);
 
+	ceph_fscache_invalidate(inode);
 	if (invalidate_inode_pages2(inode->i_mapping) < 0) {
 		pr_err("invalidate_pages %p fails\n", inode);
 	}
-- 
2.30.2

[PATCH AUTOSEL 5.4 16/23] scsi: target: tcmu: Return from tcmu_handle_completions() if cmd_id not found

[Sasha Levin]

From: Bodo Stroesser <bostroesser@gmail.com>

[ Upstream commit 9814b55cde0588b6d9bc496cee43f87316cbc6f1 ]

If tcmu_handle_completions() finds an invalid cmd_id while looping over cmd
responses from userspace it sets TCMU_DEV_BIT_BROKEN and breaks the
loop. This means that it does further handling for the tcmu device.

Skip that handling by replacing 'break' with 'return'.

Additionally change tcmu_handle_completions() from unsigned int to bool,
since the value used in return already is bool.

Link: https://lore.kernel.org/r/20210423150123.24468-1-bostroesser@gmail.com
Signed-off-by: Bodo Stroesser <bostroesser@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/target/target_core_user.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index d6634baebb47..71144e33272a 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1205,7 +1205,7 @@ static void tcmu_set_next_deadline(struct list_head *queue,
 		del_timer(timer);
 }
 
-static unsigned int tcmu_handle_completions(struct tcmu_dev *udev)
+static bool tcmu_handle_completions(struct tcmu_dev *udev)
 {
 	struct tcmu_mailbox *mb;
 	struct tcmu_cmd *cmd;
@@ -1245,7 +1245,7 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev)
 			pr_err("cmd_id %u not found, ring is broken\n",
 			       entry->hdr.cmd_id);
 			set_bit(TCMU_DEV_BIT_BROKEN, &udev->flags);
-			break;
+			return false;
 		}
 
 		tcmu_handle_completion(cmd, entry);
-- 
2.30.2

[PATCH AUTOSEL 5.4 17/23] bridge: Fix possible races between assigning rx_handler_data and setting IFF_BRIDGE_PORT bit

[Sasha Levin]

From: Zhang Zhengming <zhangzhengming@huawei.com>

[ Upstream commit 59259ff7a81b9eb6213891c6451221e567f8f22f ]

There is a crash in the function br_get_link_af_size_filtered,
as the port_exists(dev) is true and the rx_handler_data of dev is NULL.
But the rx_handler_data of dev is correct saved in vmcore.

The oops looks something like:
 ...
 pc : br_get_link_af_size_filtered+0x28/0x1c8 [bridge]
 ...
 Call trace:
  br_get_link_af_size_filtered+0x28/0x1c8 [bridge]
  if_nlmsg_size+0x180/0x1b0
  rtnl_calcit.isra.12+0xf8/0x148
  rtnetlink_rcv_msg+0x334/0x370
  netlink_rcv_skb+0x64/0x130
  rtnetlink_rcv+0x28/0x38
  netlink_unicast+0x1f0/0x250
  netlink_sendmsg+0x310/0x378
  sock_sendmsg+0x4c/0x70
  __sys_sendto+0x120/0x150
  __arm64_sys_sendto+0x30/0x40
  el0_svc_common+0x78/0x130
  el0_svc_handler+0x38/0x78
  el0_svc+0x8/0xc

In br_add_if(), we found there is no guarantee that
assigning rx_handler_data to dev->rx_handler_data
will before setting the IFF_BRIDGE_PORT bit of priv_flags.
So there is a possible data competition:

CPU 0:                                                        CPU 1:
(RCU read lock)                                               (RTNL lock)
rtnl_calcit()                                                 br_add_slave()
  if_nlmsg_size()                                               br_add_if()
    br_get_link_af_size_filtered()                              -> netdev_rx_handler_register
                                                                    ...
                                                                    // The order is not guaranteed
      ...                                                           -> dev->priv_flags |= IFF_BRIDGE_PORT;
      // The IFF_BRIDGE_PORT bit of priv_flags has been set
      -> if (br_port_exists(dev)) {
        // The dev->rx_handler_data has NOT been assigned
        -> p = br_port_get_rcu(dev);
        ....
                                                                    -> rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
                                                                     ...

Fix it in br_get_link_af_size_filtered, using br_port_get_check_rcu() and checking the return value.

Signed-off-by: Zhang Zhengming <zhangzhengming@huawei.com>
Reviewed-by: Zhao Lei <zhaolei69@huawei.com>
Reviewed-by: Wang Xiaogang <wangxiaogang3@huawei.com>
Suggested-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bridge/br_netlink.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a0a54482aabc..8a664148f57a 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -99,8 +99,9 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
 
 	rcu_read_lock();
 	if (netif_is_bridge_port(dev)) {
-		p = br_port_get_rcu(dev);
-		vg = nbp_vlan_group_rcu(p);
+		p = br_port_get_check_rcu(dev);
+		if (p)
+			vg = nbp_vlan_group_rcu(p);
 	} else if (dev->priv_flags & IFF_EBRIDGE) {
 		br = netdev_priv(dev);
 		vg = br_vlan_group_rcu(br);
-- 
2.30.2

[Bridge] [PATCH AUTOSEL 5.4 17/23] bridge: Fix possible races between assigning rx_handler_data and setting IFF_BRIDGE_PORT bit

[Sasha Levin]

From: Zhang Zhengming <zhangzhengming@huawei.com>

[ Upstream commit 59259ff7a81b9eb6213891c6451221e567f8f22f ]

There is a crash in the function br_get_link_af_size_filtered,
as the port_exists(dev) is true and the rx_handler_data of dev is NULL.
But the rx_handler_data of dev is correct saved in vmcore.

The oops looks something like:
 ...
 pc : br_get_link_af_size_filtered+0x28/0x1c8 [bridge]
 ...
 Call trace:
  br_get_link_af_size_filtered+0x28/0x1c8 [bridge]
  if_nlmsg_size+0x180/0x1b0
  rtnl_calcit.isra.12+0xf8/0x148
  rtnetlink_rcv_msg+0x334/0x370
  netlink_rcv_skb+0x64/0x130
  rtnetlink_rcv+0x28/0x38
  netlink_unicast+0x1f0/0x250
  netlink_sendmsg+0x310/0x378
  sock_sendmsg+0x4c/0x70
  __sys_sendto+0x120/0x150
  __arm64_sys_sendto+0x30/0x40
  el0_svc_common+0x78/0x130
  el0_svc_handler+0x38/0x78
  el0_svc+0x8/0xc

In br_add_if(), we found there is no guarantee that
assigning rx_handler_data to dev->rx_handler_data
will before setting the IFF_BRIDGE_PORT bit of priv_flags.
So there is a possible data competition:

CPU 0:                                                        CPU 1:
(RCU read lock)                                               (RTNL lock)
rtnl_calcit()                                                 br_add_slave()
  if_nlmsg_size()                                               br_add_if()
    br_get_link_af_size_filtered()                              -> netdev_rx_handler_register
                                                                    ...
                                                                    // The order is not guaranteed
      ...                                                           -> dev->priv_flags |= IFF_BRIDGE_PORT;
      // The IFF_BRIDGE_PORT bit of priv_flags has been set
      -> if (br_port_exists(dev)) {
        // The dev->rx_handler_data has NOT been assigned
        -> p = br_port_get_rcu(dev);
        ....
                                                                    -> rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
                                                                     ...

Fix it in br_get_link_af_size_filtered, using br_port_get_check_rcu() and checking the return value.

Signed-off-by: Zhang Zhengming <zhangzhengming@huawei.com>
Reviewed-by: Zhao Lei <zhaolei69@huawei.com>
Reviewed-by: Wang Xiaogang <wangxiaogang3@huawei.com>
Suggested-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bridge/br_netlink.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index a0a54482aabc..8a664148f57a 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -99,8 +99,9 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
 
 	rcu_read_lock();
 	if (netif_is_bridge_port(dev)) {
-		p = br_port_get_rcu(dev);
-		vg = nbp_vlan_group_rcu(p);
+		p = br_port_get_check_rcu(dev);
+		if (p)
+			vg = nbp_vlan_group_rcu(p);
 	} else if (dev->priv_flags & IFF_EBRIDGE) {
 		br = netdev_priv(dev);
 		vg = br_vlan_group_rcu(br);
-- 
2.30.2

[PATCH AUTOSEL 5.4 18/23] drm/amd/display: Fix two cursor duplication when using overlay

[Sasha Levin]

From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>

[ Upstream commit 16e9b3e58bc3fce7391539e0eb3fd167cbf9951f ]

Our driver supports overlay planes, and as expected, some userspace
compositor takes advantage of these features. If the userspace is not
enabling the cursor, they can use multiple planes as they please.
Nevertheless, we start to have constraints when userspace tries to
enable hardware cursor with various planes. Basically, we cannot draw
the cursor at the same size and position on two separated pipes since it
uses extra bandwidth and DML only run with one cursor.

For those reasons, when we enable hardware cursor and multiple planes,
our driver should accept variations like the ones described below:

  +-------------+   +--------------+
  | +---------+ |   |              |
  | |Primary  | |   | Primary      |
  | |         | |   | Overlay      |
  | +---------+ |   |              |
  |Overlay      |   |              |
  +-------------+   +--------------+

In this scenario, we can have the desktop UI in the overlay and some
other framebuffer attached to the primary plane (e.g., video). However,
userspace needs to obey some rules and avoid scenarios like the ones
described below (when enabling hw cursor):

                                      +--------+
                                      |Overlay |
 +-------------+    +-----+-------+ +-|        |--+
 | +--------+  | +--------+       | | +--------+  |
 | |Overlay |  | |Overlay |       | |             |
 | |        |  | |        |       | |             |
 | +--------+  | +--------+       | |             |
 | Primary     |    | Primary     | | Primary     |
 +-------------+    +-------------+ +-------------+

 +-------------+   +-------------+
 |     +--------+  |  Primary    |
 |     |Overlay |  |             |
 |     |        |  |             |
 |     +--------+  | +--------+  |
 | Primary     |   | |Overlay |  |
 +-------------+   +-|        |--+
                     +--------+

If the userspace violates some of the above scenarios, our driver needs
to reject the commit; otherwise, we can have unexpected behavior. Since
we don't have a proper driver validation for the above case, we can see
some problems like a duplicate cursor in applications that use multiple
planes. This commit fixes the cursor issue and others by adding adequate
verification for multiple planes.

Change since V1 (Harry and Sean):
- Remove cursor verification from the equation.

Cc: Louis Li <Ching-shih.Li@amd.com>
Cc: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Cc: Harry Wentland <Harry.Wentland@amd.com>
Cc: Hersen Wu <hersenxs.wu@amd.com>
Cc: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 51 +++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index fbbe611d4873..800dc67c98f1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7254,6 +7254,53 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm
 }
 #endif
 
+static int validate_overlay(struct drm_atomic_state *state)
+{
+	int i;
+	struct drm_plane *plane;
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *primary_state, *overlay_state = NULL;
+
+	/* Check if primary plane is contained inside overlay */
+	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
+		if (plane->type == DRM_PLANE_TYPE_OVERLAY) {
+			if (drm_atomic_plane_disabling(plane->state, new_plane_state))
+				return 0;
+
+			overlay_state = new_plane_state;
+			continue;
+		}
+	}
+
+	/* check if we're making changes to the overlay plane */
+	if (!overlay_state)
+		return 0;
+
+	/* check if overlay plane is enabled */
+	if (!overlay_state->crtc)
+		return 0;
+
+	/* find the primary plane for the CRTC that the overlay is enabled on */
+	primary_state = drm_atomic_get_plane_state(state, overlay_state->crtc->primary);
+	if (IS_ERR(primary_state))
+		return PTR_ERR(primary_state);
+
+	/* check if primary plane is enabled */
+	if (!primary_state->crtc)
+		return 0;
+
+	/* Perform the bounds check to ensure the overlay plane covers the primary */
+	if (primary_state->crtc_x < overlay_state->crtc_x ||
+	    primary_state->crtc_y < overlay_state->crtc_y ||
+	    primary_state->crtc_x + primary_state->crtc_w > overlay_state->crtc_x + overlay_state->crtc_w ||
+	    primary_state->crtc_y + primary_state->crtc_h > overlay_state->crtc_y + overlay_state->crtc_h) {
+		DRM_DEBUG_ATOMIC("Overlay plane is enabled with hardware cursor but does not fully cover primary plane\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
  * @dev: The DRM device
@@ -7427,6 +7474,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 	}
 
+	ret = validate_overlay(state);
+	if (ret)
+		goto fail;
+
 	/* Add new/modified planes */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
-- 
2.30.2

[PATCH AUTOSEL 5.4 18/23] drm/amd/display: Fix two cursor duplication when using overlay

[Sasha Levin]

From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>

[ Upstream commit 16e9b3e58bc3fce7391539e0eb3fd167cbf9951f ]

Our driver supports overlay planes, and as expected, some userspace
compositor takes advantage of these features. If the userspace is not
enabling the cursor, they can use multiple planes as they please.
Nevertheless, we start to have constraints when userspace tries to
enable hardware cursor with various planes. Basically, we cannot draw
the cursor at the same size and position on two separated pipes since it
uses extra bandwidth and DML only run with one cursor.

For those reasons, when we enable hardware cursor and multiple planes,
our driver should accept variations like the ones described below:

  +-------------+   +--------------+
  | +---------+ |   |              |
  | |Primary  | |   | Primary      |
  | |         | |   | Overlay      |
  | +---------+ |   |              |
  |Overlay      |   |              |
  +-------------+   +--------------+

In this scenario, we can have the desktop UI in the overlay and some
other framebuffer attached to the primary plane (e.g., video). However,
userspace needs to obey some rules and avoid scenarios like the ones
described below (when enabling hw cursor):

                                      +--------+
                                      |Overlay |
 +-------------+    +-----+-------+ +-|        |--+
 | +--------+  | +--------+       | | +--------+  |
 | |Overlay |  | |Overlay |       | |             |
 | |        |  | |        |       | |             |
 | +--------+  | +--------+       | |             |
 | Primary     |    | Primary     | | Primary     |
 +-------------+    +-------------+ +-------------+

 +-------------+   +-------------+
 |     +--------+  |  Primary    |
 |     |Overlay |  |             |
 |     |        |  |             |
 |     +--------+  | +--------+  |
 | Primary     |   | |Overlay |  |
 +-------------+   +-|        |--+
                     +--------+

If the userspace violates some of the above scenarios, our driver needs
to reject the commit; otherwise, we can have unexpected behavior. Since
we don't have a proper driver validation for the above case, we can see
some problems like a duplicate cursor in applications that use multiple
planes. This commit fixes the cursor issue and others by adding adequate
verification for multiple planes.

Change since V1 (Harry and Sean):
- Remove cursor verification from the equation.

Cc: Louis Li <Ching-shih.Li@amd.com>
Cc: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Cc: Harry Wentland <Harry.Wentland@amd.com>
Cc: Hersen Wu <hersenxs.wu@amd.com>
Cc: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 51 +++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index fbbe611d4873..800dc67c98f1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7254,6 +7254,53 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm
 }
 #endif
 
+static int validate_overlay(struct drm_atomic_state *state)
+{
+	int i;
+	struct drm_plane *plane;
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *primary_state, *overlay_state = NULL;
+
+	/* Check if primary plane is contained inside overlay */
+	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
+		if (plane->type == DRM_PLANE_TYPE_OVERLAY) {
+			if (drm_atomic_plane_disabling(plane->state, new_plane_state))
+				return 0;
+
+			overlay_state = new_plane_state;
+			continue;
+		}
+	}
+
+	/* check if we're making changes to the overlay plane */
+	if (!overlay_state)
+		return 0;
+
+	/* check if overlay plane is enabled */
+	if (!overlay_state->crtc)
+		return 0;
+
+	/* find the primary plane for the CRTC that the overlay is enabled on */
+	primary_state = drm_atomic_get_plane_state(state, overlay_state->crtc->primary);
+	if (IS_ERR(primary_state))
+		return PTR_ERR(primary_state);
+
+	/* check if primary plane is enabled */
+	if (!primary_state->crtc)
+		return 0;
+
+	/* Perform the bounds check to ensure the overlay plane covers the primary */
+	if (primary_state->crtc_x < overlay_state->crtc_x ||
+	    primary_state->crtc_y < overlay_state->crtc_y ||
+	    primary_state->crtc_x + primary_state->crtc_w > overlay_state->crtc_x + overlay_state->crtc_w ||
+	    primary_state->crtc_y + primary_state->crtc_h > overlay_state->crtc_y + overlay_state->crtc_h) {
+		DRM_DEBUG_ATOMIC("Overlay plane is enabled with hardware cursor but does not fully cover primary plane\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
  * @dev: The DRM device
@@ -7427,6 +7474,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 	}
 
+	ret = validate_overlay(state);
+	if (ret)
+		goto fail;
+
 	/* Add new/modified planes */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
-- 
2.30.2

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH AUTOSEL 5.4 18/23] drm/amd/display: Fix two cursor duplication when using overlay

[Sasha Levin]

From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>

[ Upstream commit 16e9b3e58bc3fce7391539e0eb3fd167cbf9951f ]

Our driver supports overlay planes, and as expected, some userspace
compositor takes advantage of these features. If the userspace is not
enabling the cursor, they can use multiple planes as they please.
Nevertheless, we start to have constraints when userspace tries to
enable hardware cursor with various planes. Basically, we cannot draw
the cursor at the same size and position on two separated pipes since it
uses extra bandwidth and DML only run with one cursor.

For those reasons, when we enable hardware cursor and multiple planes,
our driver should accept variations like the ones described below:

  +-------------+   +--------------+
  | +---------+ |   |              |
  | |Primary  | |   | Primary      |
  | |         | |   | Overlay      |
  | +---------+ |   |              |
  |Overlay      |   |              |
  +-------------+   +--------------+

In this scenario, we can have the desktop UI in the overlay and some
other framebuffer attached to the primary plane (e.g., video). However,
userspace needs to obey some rules and avoid scenarios like the ones
described below (when enabling hw cursor):

                                      +--------+
                                      |Overlay |
 +-------------+    +-----+-------+ +-|        |--+
 | +--------+  | +--------+       | | +--------+  |
 | |Overlay |  | |Overlay |       | |             |
 | |        |  | |        |       | |             |
 | +--------+  | +--------+       | |             |
 | Primary     |    | Primary     | | Primary     |
 +-------------+    +-------------+ +-------------+

 +-------------+   +-------------+
 |     +--------+  |  Primary    |
 |     |Overlay |  |             |
 |     |        |  |             |
 |     +--------+  | +--------+  |
 | Primary     |   | |Overlay |  |
 +-------------+   +-|        |--+
                     +--------+

If the userspace violates some of the above scenarios, our driver needs
to reject the commit; otherwise, we can have unexpected behavior. Since
we don't have a proper driver validation for the above case, we can see
some problems like a duplicate cursor in applications that use multiple
planes. This commit fixes the cursor issue and others by adding adequate
verification for multiple planes.

Change since V1 (Harry and Sean):
- Remove cursor verification from the equation.

Cc: Louis Li <Ching-shih.Li@amd.com>
Cc: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Cc: Harry Wentland <Harry.Wentland@amd.com>
Cc: Hersen Wu <hersenxs.wu@amd.com>
Cc: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 51 +++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index fbbe611d4873..800dc67c98f1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7254,6 +7254,53 @@ static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm
 }
 #endif
 
+static int validate_overlay(struct drm_atomic_state *state)
+{
+	int i;
+	struct drm_plane *plane;
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct drm_plane_state *primary_state, *overlay_state = NULL;
+
+	/* Check if primary plane is contained inside overlay */
+	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
+		if (plane->type == DRM_PLANE_TYPE_OVERLAY) {
+			if (drm_atomic_plane_disabling(plane->state, new_plane_state))
+				return 0;
+
+			overlay_state = new_plane_state;
+			continue;
+		}
+	}
+
+	/* check if we're making changes to the overlay plane */
+	if (!overlay_state)
+		return 0;
+
+	/* check if overlay plane is enabled */
+	if (!overlay_state->crtc)
+		return 0;
+
+	/* find the primary plane for the CRTC that the overlay is enabled on */
+	primary_state = drm_atomic_get_plane_state(state, overlay_state->crtc->primary);
+	if (IS_ERR(primary_state))
+		return PTR_ERR(primary_state);
+
+	/* check if primary plane is enabled */
+	if (!primary_state->crtc)
+		return 0;
+
+	/* Perform the bounds check to ensure the overlay plane covers the primary */
+	if (primary_state->crtc_x < overlay_state->crtc_x ||
+	    primary_state->crtc_y < overlay_state->crtc_y ||
+	    primary_state->crtc_x + primary_state->crtc_w > overlay_state->crtc_x + overlay_state->crtc_w ||
+	    primary_state->crtc_y + primary_state->crtc_h > overlay_state->crtc_y + overlay_state->crtc_h) {
+		DRM_DEBUG_ATOMIC("Overlay plane is enabled with hardware cursor but does not fully cover primary plane\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
  * @dev: The DRM device
@@ -7427,6 +7474,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 			goto fail;
 	}
 
+	ret = validate_overlay(state);
+	if (ret)
+		goto fail;
+
 	/* Add new/modified planes */
 	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		ret = dm_update_plane_state(dc, state, plane,
-- 
2.30.2

[PATCH AUTOSEL 5.4 19/23] gpiolib: acpi: Add quirk to ignore EC wakeups on Dell Venue 10 Pro 5055

[Sasha Levin]

From: Hans de Goede <hdegoede@redhat.com>

[ Upstream commit da91ece226729c76f60708efc275ebd4716ad089 ]

Like some other Bay and Cherry Trail SoC based devices the Dell Venue
10 Pro 5055 has an embedded-controller which uses ACPI GPIO events to
report events instead of using the standard ACPI EC interface for this.

The EC interrupt is only used to report battery-level changes and
it keeps doing this while the system is suspended, causing the system
to not stay suspended.

Add an ignore-wake quirk for the GPIO pin used by the EC to fix the
spurious wakeups from suspend.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpio/gpiolib-acpi.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 66dcab6ab26d..e3ddc99c105d 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1394,6 +1394,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] = {
 			.no_edge_events_on_boot = true,
 		},
 	},
+	{
+		/*
+		 * The Dell Venue 10 Pro 5055, with Bay Trail SoC + TI PMIC uses an
+		 * external embedded-controller connected via I2C + an ACPI GPIO
+		 * event handler on INT33FFC:02 pin 12, causing spurious wakeups.
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Venue 10 Pro 5055"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_wake = "INT33FC:02@12",
+		},
+	},
 	{
 		/*
 		 * HP X2 10 models with Cherry Trail SoC + TI PMIC use an
-- 
2.30.2

[PATCH AUTOSEL 5.4 20/23] ALSA: hda: generic: change the DAC ctl name for LO+SPK or LO+HP

[Sasha Levin]

From: Hui Wang <hui.wang@canonical.com>

[ Upstream commit f48652bbe3ae62ba2835a396b7e01f063e51c4cd ]

Without this change, the DAC ctl's name could be changed only when
the machine has both Speaker and Headphone, but we met some machines
which only has Lineout and Headhpone, and the Lineout and Headphone
share the Audio Mixer0 and DAC0, the ctl's name is set to "Front".

On most of machines, the "Front" is used for Speaker only or Lineout
only, but on this machine it is shared by Lineout and Headphone,
This introduces an issue in the pipewire and pulseaudio, suppose users
want the Headphone to be on and the Speaker/Lineout to be off, they
could turn off the "Front", this works on most of the machines, but on
this machine, the "Front" couldn't be turned off otherwise the
headphone will be off too. Here we do some change to let the ctl's
name change to "Headphone+LO" on this machine, and pipewire and
pulseaudio already could handle "Headphone+LO" and "Speaker+LO".
(https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/747)

BugLink: http://bugs.launchpad.net/bugs/804178
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Link: https://lore.kernel.org/r/20210504073917.22406-1-hui.wang@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 sound/pci/hda/hda_generic.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index efceeae09045..7ac3f04ca8c0 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -1202,11 +1202,17 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch,
 		*index = ch;
 		return "Headphone";
 	case AUTO_PIN_LINE_OUT:
-		/* This deals with the case where we have two DACs and
-		 * one LO, one HP and one Speaker */
-		if (!ch && cfg->speaker_outs && cfg->hp_outs) {
-			bool hp_lo_shared = !path_has_mixer(codec, spec->hp_paths[0], ctl_type);
-			bool spk_lo_shared = !path_has_mixer(codec, spec->speaker_paths[0], ctl_type);
+		/* This deals with the case where one HP or one Speaker or
+		 * one HP + one Speaker need to share the DAC with LO
+		 */
+		if (!ch) {
+			bool hp_lo_shared = false, spk_lo_shared = false;
+
+			if (cfg->speaker_outs)
+				spk_lo_shared = !path_has_mixer(codec,
+								spec->speaker_paths[0],	ctl_type);
+			if (cfg->hp_outs)
+				hp_lo_shared = !path_has_mixer(codec, spec->hp_paths[0], ctl_type);
 			if (hp_lo_shared && spk_lo_shared)
 				return spec->vmaster_mute.hook ? "PCM" : "Master";
 			if (hp_lo_shared)
-- 
2.30.2

[PATCH AUTOSEL 5.4 20/23] ALSA: hda: generic: change the DAC ctl name for LO+SPK or LO+HP

[Sasha Levin]

From: Hui Wang <hui.wang@canonical.com>

[ Upstream commit f48652bbe3ae62ba2835a396b7e01f063e51c4cd ]

Without this change, the DAC ctl's name could be changed only when
the machine has both Speaker and Headphone, but we met some machines
which only has Lineout and Headhpone, and the Lineout and Headphone
share the Audio Mixer0 and DAC0, the ctl's name is set to "Front".

On most of machines, the "Front" is used for Speaker only or Lineout
only, but on this machine it is shared by Lineout and Headphone,
This introduces an issue in the pipewire and pulseaudio, suppose users
want the Headphone to be on and the Speaker/Lineout to be off, they
could turn off the "Front", this works on most of the machines, but on
this machine, the "Front" couldn't be turned off otherwise the
headphone will be off too. Here we do some change to let the ctl's
name change to "Headphone+LO" on this machine, and pipewire and
pulseaudio already could handle "Headphone+LO" and "Speaker+LO".
(https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/747)

BugLink: http://bugs.launchpad.net/bugs/804178
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Link: https://lore.kernel.org/r/20210504073917.22406-1-hui.wang@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 sound/pci/hda/hda_generic.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index efceeae09045..7ac3f04ca8c0 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -1202,11 +1202,17 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch,
 		*index = ch;
 		return "Headphone";
 	case AUTO_PIN_LINE_OUT:
-		/* This deals with the case where we have two DACs and
-		 * one LO, one HP and one Speaker */
-		if (!ch && cfg->speaker_outs && cfg->hp_outs) {
-			bool hp_lo_shared = !path_has_mixer(codec, spec->hp_paths[0], ctl_type);
-			bool spk_lo_shared = !path_has_mixer(codec, spec->speaker_paths[0], ctl_type);
+		/* This deals with the case where one HP or one Speaker or
+		 * one HP + one Speaker need to share the DAC with LO
+		 */
+		if (!ch) {
+			bool hp_lo_shared = false, spk_lo_shared = false;
+
+			if (cfg->speaker_outs)
+				spk_lo_shared = !path_has_mixer(codec,
+								spec->speaker_paths[0],	ctl_type);
+			if (cfg->hp_outs)
+				hp_lo_shared = !path_has_mixer(codec, spec->hp_paths[0], ctl_type);
 			if (hp_lo_shared && spk_lo_shared)
 				return spec->vmaster_mute.hook ? "PCM" : "Master";
 			if (hp_lo_shared)
-- 
2.30.2

[PATCH AUTOSEL 5.4 21/23] block: reexpand iov_iter after read/write

[Sasha Levin]

From: yangerkun <yangerkun@huawei.com>

[ Upstream commit cf7b39a0cbf6bf57aa07a008d46cf695add05b4c ]

We get a bug:

BUG: KASAN: slab-out-of-bounds in iov_iter_revert+0x11c/0x404
lib/iov_iter.c:1139
Read of size 8 at addr ffff0000d3fb11f8 by task

CPU: 0 PID: 12582 Comm: syz-executor.2 Not tainted
5.10.0-00843-g352c8610ccd2 #2
Hardware name: linux,dummy-virt (DT)
Call trace:
 dump_backtrace+0x0/0x2d0 arch/arm64/kernel/stacktrace.c:132
 show_stack+0x28/0x34 arch/arm64/kernel/stacktrace.c:196
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x110/0x164 lib/dump_stack.c:118
 print_address_description+0x78/0x5c8 mm/kasan/report.c:385
 __kasan_report mm/kasan/report.c:545 [inline]
 kasan_report+0x148/0x1e4 mm/kasan/report.c:562
 check_memory_region_inline mm/kasan/generic.c:183 [inline]
 __asan_load8+0xb4/0xbc mm/kasan/generic.c:252
 iov_iter_revert+0x11c/0x404 lib/iov_iter.c:1139
 io_read fs/io_uring.c:3421 [inline]
 io_issue_sqe+0x2344/0x2d64 fs/io_uring.c:5943
 __io_queue_sqe+0x19c/0x520 fs/io_uring.c:6260
 io_queue_sqe+0x2a4/0x590 fs/io_uring.c:6326
 io_submit_sqe fs/io_uring.c:6395 [inline]
 io_submit_sqes+0x4c0/0xa04 fs/io_uring.c:6624
 __do_sys_io_uring_enter fs/io_uring.c:9013 [inline]
 __se_sys_io_uring_enter fs/io_uring.c:8960 [inline]
 __arm64_sys_io_uring_enter+0x190/0x708 fs/io_uring.c:8960
 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:48 [inline]
 el0_svc_common arch/arm64/kernel/syscall.c:158 [inline]
 do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:227
 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367
 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383
 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670

Allocated by task 12570:
 stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track mm/kasan/common.c:56 [inline]
 __kasan_kmalloc+0xdc/0x120 mm/kasan/common.c:461
 kasan_kmalloc+0xc/0x14 mm/kasan/common.c:475
 __kmalloc+0x23c/0x334 mm/slub.c:3970
 kmalloc include/linux/slab.h:557 [inline]
 __io_alloc_async_data+0x68/0x9c fs/io_uring.c:3210
 io_setup_async_rw fs/io_uring.c:3229 [inline]
 io_read fs/io_uring.c:3436 [inline]
 io_issue_sqe+0x2954/0x2d64 fs/io_uring.c:5943
 __io_queue_sqe+0x19c/0x520 fs/io_uring.c:6260
 io_queue_sqe+0x2a4/0x590 fs/io_uring.c:6326
 io_submit_sqe fs/io_uring.c:6395 [inline]
 io_submit_sqes+0x4c0/0xa04 fs/io_uring.c:6624
 __do_sys_io_uring_enter fs/io_uring.c:9013 [inline]
 __se_sys_io_uring_enter fs/io_uring.c:8960 [inline]
 __arm64_sys_io_uring_enter+0x190/0x708 fs/io_uring.c:8960
 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline]
 invoke_syscall arch/arm64/kernel/syscall.c:48 [inline]
 el0_svc_common arch/arm64/kernel/syscall.c:158 [inline]
 do_el0_svc+0x120/0x290 arch/arm64/kernel/syscall.c:227
 el0_svc+0x1c/0x28 arch/arm64/kernel/entry-common.c:367
 el0_sync_handler+0x98/0x170 arch/arm64/kernel/entry-common.c:383
 el0_sync+0x140/0x180 arch/arm64/kernel/entry.S:670

Freed by task 12570:
 stack_trace_save+0x80/0xb8 kernel/stacktrace.c:121
 kasan_save_stack mm/kasan/common.c:48 [inline]
 kasan_set_track+0x38/0x6c mm/kasan/common.c:56
 kasan_set_free_info+0x20/0x40 mm/kasan/generic.c:355
 __kasan_slab_free+0x124/0x150 mm/kasan/common.c:422
 kasan_slab_free+0x10/0x1c mm/kasan/common.c:431
 slab_free_hook mm/slub.c:1544 [inline]
 slab_free_freelist_hook mm/slub.c:1577 [inline]
 slab_free mm/slub.c:3142 [inline]
 kfree+0x104/0x38c mm/slub.c:4124
 io_dismantle_req fs/io_uring.c:1855 [inline]
 __io_free_req+0x70/0x254 fs/io_uring.c:1867
 io_put_req_find_next fs/io_uring.c:2173 [inline]
 __io_queue_sqe+0x1fc/0x520 fs/io_uring.c:6279
 __io_req_task_submit+0x154/0x21c fs/io_uring.c:2051
 io_req_task_submit+0x2c/0x44 fs/io_uring.c:2063
 task_work_run+0xdc/0x128 kernel/task_work.c:151
 get_signal+0x6f8/0x980 kernel/signal.c:2562
 do_signal+0x108/0x3a4 arch/arm64/kernel/signal.c:658
 do_notify_resume+0xbc/0x25c arch/arm64/kernel/signal.c:722
 work_pending+0xc/0x180

blkdev_read_iter can truncate iov_iter's count since the count + pos may
exceed the size of the blkdev. This will confuse io_read that we have
consume the iovec. And once we do the iov_iter_revert in io_read, we
will trigger the slab-out-of-bounds. Fix it by reexpand the count with
size has been truncated.

blkdev_write_iter can trigger the problem too.

Signed-off-by: yangerkun <yangerkun@huawei.com>
Acked-by: Pavel Begunkov <asml.silencec@gmail.com>
Link: https://lore.kernel.org/r/20210401071807.3328235-1-yangerkun@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/block_dev.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index bd93563477a4..fa329c7eddf0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1987,6 +1987,7 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	struct blk_plug plug;
+	size_t shorted = 0;
 	ssize_t ret;
 
 	if (bdev_read_only(I_BDEV(bd_inode)))
@@ -2005,12 +2006,17 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
 		return -EOPNOTSUPP;
 
-	iov_iter_truncate(from, size - iocb->ki_pos);
+	size -= iocb->ki_pos;
+	if (iov_iter_count(from) > size) {
+		shorted = iov_iter_count(from) - size;
+		iov_iter_truncate(from, size);
+	}
 
 	blk_start_plug(&plug);
 	ret = __generic_file_write_iter(iocb, from);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
+	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
 	blk_finish_plug(&plug);
 	return ret;
 }
@@ -2022,13 +2028,21 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	loff_t pos = iocb->ki_pos;
+	size_t shorted = 0;
+	ssize_t ret;
 
 	if (pos >= size)
 		return 0;
 
 	size -= pos;
-	iov_iter_truncate(to, size);
-	return generic_file_read_iter(iocb, to);
+	if (iov_iter_count(to) > size) {
+		shorted = iov_iter_count(to) - size;
+		iov_iter_truncate(to, size);
+	}
+
+	ret = generic_file_read_iter(iocb, to);
+	iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_read_iter);
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 22/23] lib: stackdepot: turn depot_lock spinlock to raw_spinlock

[Sasha Levin]

From: Zqiang <qiang.zhang@windriver.com>

[ Upstream commit 78564b9434878d686c5f88c4488b20cccbcc42bc ]

In RT system, the spin_lock will be replaced by sleepable rt_mutex lock,
in __call_rcu(), disable interrupts before calling
kasan_record_aux_stack(), will trigger this calltrace:

  BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:951
  in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 19, name: pgdatinit0
  Call Trace:
    ___might_sleep.cold+0x1b2/0x1f1
    rt_spin_lock+0x3b/0xb0
    stack_depot_save+0x1b9/0x440
    kasan_save_stack+0x32/0x40
    kasan_record_aux_stack+0xa5/0xb0
    __call_rcu+0x117/0x880
    __exit_signal+0xafb/0x1180
    release_task+0x1d6/0x480
    exit_notify+0x303/0x750
    do_exit+0x678/0xcf0
    kthread+0x364/0x4f0
    ret_from_fork+0x22/0x30

Replace spinlock with raw_spinlock.

Link: https://lkml.kernel.org/r/20210329084009.27013-1-qiang.zhang@windriver.com
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Reported-by: Andrew Halaney <ahalaney@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: Vijayanand Jitta <vjitta@codeaurora.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Cc: Yogesh Lal <ylal@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 lib/stackdepot.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 81c69c08d1d1..468626b8eb1b 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -69,7 +69,7 @@ static void *stack_slabs[STACK_ALLOC_MAX_SLABS];
 static int depot_index;
 static int next_slab_inited;
 static size_t depot_offset;
-static DEFINE_SPINLOCK(depot_lock);
+static DEFINE_RAW_SPINLOCK(depot_lock);
 
 static bool init_stack_slab(void **prealloc)
 {
@@ -269,7 +269,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries,
 			prealloc = page_address(page);
 	}
 
-	spin_lock_irqsave(&depot_lock, flags);
+	raw_spin_lock_irqsave(&depot_lock, flags);
 
 	found = find_stack(*bucket, entries, nr_entries, hash);
 	if (!found) {
@@ -293,7 +293,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries,
 		WARN_ON(!init_stack_slab(&prealloc));
 	}
 
-	spin_unlock_irqrestore(&depot_lock, flags);
+	raw_spin_unlock_irqrestore(&depot_lock, flags);
 exit:
 	if (prealloc) {
 		/* Nobody used this memory, ok to free it. */
-- 
2.30.2

[PATCH AUTOSEL 5.4 23/23] net: stmmac: Do not enable RX FIFO overflow interrupts

[Sasha Levin]

From: Yannick Vignon <yannick.vignon@nxp.com>

[ Upstream commit 8a7cb245cf28cb3e541e0d6c8624b95d079e155b ]

The RX FIFO overflows when the system is not able to process all received
packets and they start accumulating (first in the DMA queue in memory,
then in the FIFO). An interrupt is then raised for each overflowing packet
and handled in stmmac_interrupt(). This is counter-productive, since it
brings the system (or more likely, one CPU core) to its knees to process
the FIFO overflow interrupts.

stmmac_interrupt() handles overflow interrupts by writing the rx tail ptr
into the corresponding hardware register (according to the MAC spec, this
has the effect of restarting the MAC DMA). However, without freeing any rx
descriptors, the DMA stops right away, and another overflow interrupt is
raised as the FIFO overflows again. Since the DMA is already restarted at
the end of stmmac_rx_refill() after freeing descriptors, disabling FIFO
overflow interrupts and the corresponding handling code has no side effect,
and eliminates the interrupt storm when the RX FIFO overflows.

Signed-off-by: Yannick Vignon <yannick.vignon@nxp.com>
Link: https://lore.kernel.org/r/20210506143312.20784-1-yannick.vignon@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c  |  7 +------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++------------
 2 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index a41ac13cc4e5..0d993f4b701c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -211,7 +211,7 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 				       u32 channel, int fifosz, u8 qmode)
 {
 	unsigned int rqs = fifosz / 256 - 1;
-	u32 mtl_rx_op, mtl_rx_int;
+	u32 mtl_rx_op;
 
 	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
 
@@ -282,11 +282,6 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 	}
 
 	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	/* Enable MTL RX overflow */
-	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
-	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
-	       ioaddr + MTL_CHAN_INT_CTRL(channel));
 }
 
 static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8e7c60e02fa0..10d28be73f45 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3855,7 +3855,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	/* To handle GMAC own interrupts */
 	if ((priv->plat->has_gmac) || xmac) {
 		int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
-		int mtl_status;
 
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
@@ -3866,17 +3865,8 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 		}
 
 		for (queue = 0; queue < queues_count; queue++) {
-			struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-
-			mtl_status = stmmac_host_mtl_irq_status(priv, priv->hw,
-								queue);
-			if (mtl_status != -EINVAL)
-				status |= mtl_status;
-
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
-				stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
-						       rx_q->rx_tail_addr,
-						       queue);
+			status = stmmac_host_mtl_irq_status(priv, priv->hw,
+							    queue);
 		}
 
 		/* PCS link status */
-- 
2.30.2

[PATCH AUTOSEL 5.4 23/23] net: stmmac: Do not enable RX FIFO overflow interrupts

[Sasha Levin]

From: Yannick Vignon <yannick.vignon@nxp.com>

[ Upstream commit 8a7cb245cf28cb3e541e0d6c8624b95d079e155b ]

The RX FIFO overflows when the system is not able to process all received
packets and they start accumulating (first in the DMA queue in memory,
then in the FIFO). An interrupt is then raised for each overflowing packet
and handled in stmmac_interrupt(). This is counter-productive, since it
brings the system (or more likely, one CPU core) to its knees to process
the FIFO overflow interrupts.

stmmac_interrupt() handles overflow interrupts by writing the rx tail ptr
into the corresponding hardware register (according to the MAC spec, this
has the effect of restarting the MAC DMA). However, without freeing any rx
descriptors, the DMA stops right away, and another overflow interrupt is
raised as the FIFO overflows again. Since the DMA is already restarted at
the end of stmmac_rx_refill() after freeing descriptors, disabling FIFO
overflow interrupts and the corresponding handling code has no side effect,
and eliminates the interrupt storm when the RX FIFO overflows.

Signed-off-by: Yannick Vignon <yannick.vignon@nxp.com>
Link: https://lore.kernel.org/r/20210506143312.20784-1-yannick.vignon@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c  |  7 +------
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++------------
 2 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index a41ac13cc4e5..0d993f4b701c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -211,7 +211,7 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 				       u32 channel, int fifosz, u8 qmode)
 {
 	unsigned int rqs = fifosz / 256 - 1;
-	u32 mtl_rx_op, mtl_rx_int;
+	u32 mtl_rx_op;
 
 	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
 
@@ -282,11 +282,6 @@ static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
 	}
 
 	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	/* Enable MTL RX overflow */
-	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
-	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
-	       ioaddr + MTL_CHAN_INT_CTRL(channel));
 }
 
 static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8e7c60e02fa0..10d28be73f45 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3855,7 +3855,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	/* To handle GMAC own interrupts */
 	if ((priv->plat->has_gmac) || xmac) {
 		int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
-		int mtl_status;
 
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
@@ -3866,17 +3865,8 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 		}
 
 		for (queue = 0; queue < queues_count; queue++) {
-			struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-
-			mtl_status = stmmac_host_mtl_irq_status(priv, priv->hw,
-								queue);
-			if (mtl_status != -EINVAL)
-				status |= mtl_status;
-
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
-				stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
-						       rx_q->rx_tail_addr,
-						       queue);
+			status = stmmac_host_mtl_irq_status(priv, priv->hw,
+							    queue);
 		}
 
 		/* PCS link status */
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel