[PATCH AUTOSEL 6.0 21/27] powerpc/rtas: avoid device tree lookups in rtas_os_term()

[PATCH AUTOSEL 6.0 21/27] powerpc/rtas: avoid device tree lookups in rtas_os_term()

[Sasha Levin]

From: Nathan Lynch <nathanl@linux.ibm.com>

[ Upstream commit ed2213bfb192ab51f09f12e9b49b5d482c6493f3 ]

rtas_os_term() is called during panic. Its behavior depends on a couple
of conditions in the /rtas node of the device tree, the traversal of
which entails locking and local IRQ state changes. If the kernel panics
while devtree_lock is held, rtas_os_term() as currently written could
hang.

Instead of discovering the relevant characteristics at panic time,
cache them in file-static variables at boot. Note the lookup for
"ibm,extended-os-term" is converted to of_property_read_bool() since it
is a boolean property, not an RTAS function token.

Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com>
[mpe: Incorporate suggested change from Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221118150751.469393-4-nathanl@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/rtas.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 0b8a858aa847..082b0c9e0c8a 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -875,6 +875,7 @@ void __noreturn rtas_halt(void)
 
 /* Must be in the RMO region, so we place it here */
 static char rtas_os_term_buf[2048];
+static s32 ibm_os_term_token = RTAS_UNKNOWN_SERVICE;
 
 void rtas_os_term(char *str)
 {
@@ -886,14 +887,13 @@ void rtas_os_term(char *str)
 	 * this property may terminate the partition which we want to avoid
 	 * since it interferes with panic_timeout.
 	 */
-	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") ||
-	    RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term"))
+	if (ibm_os_term_token == RTAS_UNKNOWN_SERVICE)
 		return;
 
 	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
 
 	do {
-		status = rtas_call(rtas_token("ibm,os-term"), 1, 1, NULL,
+		status = rtas_call(ibm_os_term_token, 1, 1, NULL,
 				   __pa(rtas_os_term_buf));
 	} while (rtas_busy_delay(status));
 
@@ -1255,6 +1255,13 @@ void __init rtas_initialize(void)
 	no_entry = of_property_read_u32(rtas.dev, "linux,rtas-entry", &entry);
 	rtas.entry = no_entry ? rtas.base : entry;
 
+	/*
+	 * Discover these now to avoid device tree lookups in the
+	 * panic path.
+	 */
+	if (of_property_read_bool(rtas.dev, "ibm,extended-os-term"))
+		ibm_os_term_token = rtas_token("ibm,os-term");
+
 	/* If RTAS was found, allocate the RMO buffer for it and look for
 	 * the stop-self token if any
 	 */
-- 
2.35.1

[PATCH AUTOSEL 6.0 22/27] powerpc/rtas: avoid scheduling in rtas_os_term()

[Sasha Levin]

From: Nathan Lynch <nathanl@linux.ibm.com>

[ Upstream commit 6c606e57eecc37d6b36d732b1ff7e55b7dc32dd4 ]

It's unsafe to use rtas_busy_delay() to handle a busy status from
the ibm,os-term RTAS function in rtas_os_term():

Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
BUG: sleeping function called from invalid context at arch/powerpc/kernel/rtas.c:618
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 1, name: swapper/0
preempt_count: 2, expected: 0
CPU: 7 PID: 1 Comm: swapper/0 Tainted: G      D            6.0.0-rc5-02182-gf8553a572277-dirty #9
Call Trace:
[c000000007b8f000] [c000000001337110] dump_stack_lvl+0xb4/0x110 (unreliable)
[c000000007b8f040] [c0000000002440e4] __might_resched+0x394/0x3c0
[c000000007b8f0e0] [c00000000004f680] rtas_busy_delay+0x120/0x1b0
[c000000007b8f100] [c000000000052d04] rtas_os_term+0xb8/0xf4
[c000000007b8f180] [c0000000001150fc] pseries_panic+0x50/0x68
[c000000007b8f1f0] [c000000000036354] ppc_panic_platform_handler+0x34/0x50
[c000000007b8f210] [c0000000002303c4] notifier_call_chain+0xd4/0x1c0
[c000000007b8f2b0] [c0000000002306cc] atomic_notifier_call_chain+0xac/0x1c0
[c000000007b8f2f0] [c0000000001d62b8] panic+0x228/0x4d0
[c000000007b8f390] [c0000000001e573c] do_exit+0x140c/0x1420
[c000000007b8f480] [c0000000001e586c] make_task_dead+0xdc/0x200

Use rtas_busy_delay_time() instead, which signals without side effects
whether to attempt the ibm,os-term RTAS call again.

Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221118150751.469393-5-nathanl@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/kernel/rtas.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 082b0c9e0c8a..5a873d4fbd7b 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -892,10 +892,15 @@ void rtas_os_term(char *str)
 
 	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
 
+	/*
+	 * Keep calling as long as RTAS returns a "try again" status,
+	 * but don't use rtas_busy_delay(), which potentially
+	 * schedules.
+	 */
 	do {
 		status = rtas_call(ibm_os_term_token, 1, 1, NULL,
 				   __pa(rtas_os_term_buf));
-	} while (rtas_busy_delay(status));
+	} while (rtas_busy_delay_time(status));
 
 	if (status != 0)
 		printk(KERN_EMERG "ibm,os-term call failed %d\n", status);
-- 
2.35.1

[PATCH AUTOSEL 6.0 25/27] powerpc/msi: Fix deassociation of MSI descriptors

[Sasha Levin]

From: Marc Zyngier <maz@kernel.org>

[ Upstream commit 4545c6a3d6ba71747eaa984c338ddd745e56e23f ]

Since 2f2940d16823 ("genirq/msi: Remove filter from
msi_free_descs_free_range()"), the core MSI code relies on the
msi_desc->irq field to have been cleared before the descriptor
can be freed, as it indicates that there is no association with
a device anymore.

The irq domain code provides this guarantee, and so does s390,
which is one of the two architectures not using irq domains for
MSIs.

Powerpc, however, is missing this particular requirements,
leading in a splat and leaked MSI descriptors.

Adding the now required irq reset to the handful of powerpc backends
that implement MSIs fixes that particular problem.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/70dab88e-6119-0c12-7c6a-61bcbe239f66@roeck-us.net
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/4xx/hsta_msi.c  | 1 +
 arch/powerpc/platforms/cell/axon_msi.c | 1 +
 arch/powerpc/platforms/pasemi/msi.c    | 1 +
 arch/powerpc/sysdev/fsl_msi.c          | 1 +
 arch/powerpc/sysdev/mpic_u3msi.c       | 1 +
 5 files changed, 5 insertions(+)

diff --git a/arch/powerpc/platforms/4xx/hsta_msi.c b/arch/powerpc/platforms/4xx/hsta_msi.c
index d4f7fff1fc87..e11b57a62b05 100644
--- a/arch/powerpc/platforms/4xx/hsta_msi.c
+++ b/arch/powerpc/platforms/4xx/hsta_msi.c
@@ -115,6 +115,7 @@ static void hsta_teardown_msi_irqs(struct pci_dev *dev)
 		msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1);
 		pr_debug("%s: Teardown IRQ %u (index %u)\n", __func__,
 			 entry->irq, irq);
+		entry->irq = 0;
 	}
 }
 
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 5b012abca773..0c11aad896c7 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -289,6 +289,7 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
 	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ASSOCIATED) {
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
+		entry->irq = 0;
 	}
 }
 
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index dc1846660005..166c97fff16d 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -66,6 +66,7 @@ static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
+		entry->irq = 0;
 		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, ALLOC_CHUNK);
 	}
 }
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 73c2d70706c0..57978a44d55b 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -132,6 +132,7 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev)
 		msi_data = irq_get_chip_data(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
+		entry->irq = 0;
 		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
 }
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 1d8cfdfdf115..492cb03c0b62 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -108,6 +108,7 @@ static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
+		entry->irq = 0;
 		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1);
 	}
 }
-- 
2.35.1