From d10f60ae27d26d811e2a1bb39ded47df96d7499f Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Mon, 14 Oct 2019 16:51:28 +0000
Subject: [PATCH 1/4] powerpc/32s: fix allow/prevent_user_access() when
 crossing segment boundaries.

Make sure starting addr is aligned to segment boundary so that when
incrementing the segment, the starting address of the new segment is
below the end address. Otherwise the last segment might get  missed.

Fixes: a68c31fc01ef ("powerpc/32s: Implement Kernel Userspace Access Protection")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/067a1b09f15f421d40797c2d04c22d4049a1cee8.1571071875.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/book3s/32/kup.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 677e9babef80..f9dc597b0b86 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -91,6 +91,7 @@
 
 static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 {
+	addr &= 0xf0000000;	/* align addr to start of segment */
 	barrier();	/* make sure thread.kuap is updated before playing with SRs */
 	while (addr < end) {
 		mtsrin(sr, addr);

From a8a30219ba78b1abb92091102b632f8e9bbdbf03 Mon Sep 17 00:00:00 2001
From: Frederic Barrat <fbarrat@linux.ibm.com>
Date: Wed, 16 Oct 2019 18:28:33 +0200
Subject: [PATCH 2/4] powerpc/powernv/eeh: Fix oops when probing cxl devices

Recent cleanup in the way EEH support is added to a device causes a
kernel oops when the cxl driver probes a device and creates virtual
devices discovered on the FPGA:

  BUG: Kernel NULL pointer dereference at 0x000000a0
  Faulting instruction address: 0xc000000000048070
  Oops: Kernel access of bad area, sig: 7 [#1]
  ...
  NIP eeh_add_device_late.part.9+0x50/0x1e0
  LR  eeh_add_device_late.part.9+0x3c/0x1e0
  Call Trace:
    _dev_info+0x5c/0x6c (unreliable)
    pnv_pcibios_bus_add_device+0x60/0xb0
    pcibios_bus_add_device+0x40/0x60
    pci_bus_add_device+0x30/0x100
    pci_bus_add_devices+0x64/0xd0
    cxl_pci_vphb_add+0xe0/0x130 [cxl]
    cxl_probe+0x504/0x5b0 [cxl]
    local_pci_probe+0x6c/0x110
    work_for_cpu_fn+0x38/0x60

The root cause is that those cxl virtual devices don't have a
representation in the device tree and therefore no associated pci_dn
structure. In eeh_add_device_late(), pdn is NULL, so edev is NULL and
we oops.

We never had explicit support for EEH for those virtual devices.
Instead, EEH events are reported to the (real) pci device and handled
by the cxl driver. Which can then forward to the virtual devices and
handle dependencies. The fact that we try adding EEH support for the
virtual devices is new and a side-effect of the recent cleanup.

This patch fixes it by skipping adding EEH support on powernv for
devices which don't have a pci_dn structure.

The cxl driver doesn't create virtual devices on pseries so this patch
doesn't fix it there intentionally.

Fixes: b905f8cdca77 ("powerpc/eeh: EEH for pSeries hot plug")
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191016162833.22509-1-fbarrat@linux.ibm.com
---
 arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 6bc24a47e9ef..6f300ab7f0e9 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
+	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");

From 05d9a952832cb206a32e3705eff6edebdb2207e7 Mon Sep 17 00:00:00 2001
From: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Date: Wed, 11 Sep 2019 13:34:33 -0300
Subject: [PATCH 3/4] powerpc/prom_init: Undo relocation before entering secure
 mode

The ultravisor will do an integrity check of the kernel image but we
relocated it so the check will fail. Restore the original image by
relocating it back to the kernel virtual base address.

This works because during build vmlinux is linked with an expected
virtual runtime address of KERNELBASE.

Fixes: 6a9c930bd775 ("powerpc/prom_init: Add the ESM call to prom_init")
Signed-off-by: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Tested-by: Michael Anderson <andmike@linux.ibm.com>
[mpe: Add IS_ENABLED() to fix the CONFIG_RELOCATABLE=n build]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190911163433.12822-1-bauerman@linux.ibm.com
---
 arch/powerpc/include/asm/elf.h         |  3 +++
 arch/powerpc/kernel/prom_init.c        | 13 +++++++++++++
 arch/powerpc/kernel/prom_init_check.sh |  3 ++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 409c9bfb43d9..57c229a86f08 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -175,4 +175,7 @@ do {									\
 	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a4e7762dd286..100f1b57ec2f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
 	/* Switch to secure mode. */
 	prom_printf("Switching to secure mode.\n");
 
+	/*
+	 * The ultravisor will do an integrity check of the kernel image but we
+	 * relocated it so the check will fail. Restore the original image by
+	 * relocating it back to the kernel virtual base address.
+	 */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(KERNELBASE);
+
 	ret = enter_secure_mode(kbase, fdt);
+
+	/* Relocate the kernel again. */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(kbase);
+
 	if (ret != U_SUCCESS) {
 		prom_printf("Returned %d from switching to secure mode.\n", ret);
 		prom_rtas_os_term("Switch to secure mode failed.\n");
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 78bab17b1396..b183ab9c5107 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 logo_linux_clut224 btext_prepare_BAT
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
+relocate"
 
 NM="$1"
 OBJ="$2"

From 7d6475051fb3d9339c5c760ed9883bc0a9048b21 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Tue, 22 Oct 2019 21:58:14 +1000
Subject: [PATCH 4/4] powerpc/powernv: Fix CPU idle to be called with IRQs
 disabled

Commit e78a7614f3876 ("idle: Prevent late-arriving interrupts from
disrupting offline") changes arch_cpu_idle_dead to be called with
interrupts disabled, which triggers the WARN in pnv_smp_cpu_kill_self.

Fix this by fixing up irq_happened after hard disabling, rather than
requiring there are no pending interrupts, similarly to what was done
done until commit 2525db04d1cc5 ("powerpc/powernv: Simplify lazy IRQ
handling in CPU offline").

Fixes: e78a7614f3876 ("idle: Prevent late-arriving interrupts from disrupting offline")
Reported-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Add unexpected_mask rather than checking for known bad values,
      change the WARN_ON() to a WARN_ON_ONCE()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191022115814.22456-1-npiggin@gmail.com
---
 arch/powerpc/platforms/powernv/smp.c | 53 +++++++++++++++++++---------
 1 file changed, 37 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fbd6e6b7bbf2..13e251699346 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void)
 	return 0;
 }
 
+static void pnv_flush_interrupts(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (xive_enabled())
+			xive_flush_interrupt();
+		else
+			icp_opal_flush_interrupt();
+	} else {
+		icp_native_flush_interrupt();
+	}
+}
+
 static void pnv_smp_cpu_kill_self(void)
 {
+	unsigned long srr1, unexpected_mask, wmask;
 	unsigned int cpu;
-	unsigned long srr1, wmask;
 	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
-	/*
-	 * This hard disables local interurpts, ensuring we have no lazy
-	 * irqs pending.
-	 */
-	WARN_ON(irqs_disabled());
-	hard_irq_disable();
-	WARN_ON(lazy_irq_pending());
 
 	idle_task_exit();
 	current->active_mm = NULL; /* for sanity */
@@ -172,6 +177,27 @@ static void pnv_smp_cpu_kill_self(void)
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		wmask = SRR1_WAKEMASK_P8;
 
+	/*
+	 * This turns the irq soft-disabled state we're called with, into a
+	 * hard-disabled state with pending irq_happened interrupts cleared.
+	 *
+	 * PACA_IRQ_DEC   - Decrementer should be ignored.
+	 * PACA_IRQ_HMI   - Can be ignored, processing is done in real mode.
+	 * PACA_IRQ_DBELL, EE, PMI - Unexpected.
+	 */
+	hard_irq_disable();
+	if (generic_check_cpu_restart(cpu))
+		goto out;
+
+	unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS);
+	if (local_paca->irq_happened & unexpected_mask) {
+		if (local_paca->irq_happened & PACA_IRQ_EE)
+			pnv_flush_interrupts();
+		DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n",
+				cpu, local_paca->irq_happened);
+	}
+	local_paca->irq_happened = PACA_IRQ_HARD_DIS;
+
 	/*
 	 * We don't want to take decrementer interrupts while we are
 	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
@@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void)
 
 		srr1 = pnv_cpu_offline(cpu);
 
+		WARN_ON_ONCE(!irqs_disabled());
 		WARN_ON(lazy_irq_pending());
 
 		/*
@@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void)
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
 		    ((srr1 & wmask) == SRR1_WAKEHVI)) {
-			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-				if (xive_enabled())
-					xive_flush_interrupt();
-				else
-					icp_opal_flush_interrupt();
-			} else
-				icp_native_flush_interrupt();
+			pnv_flush_interrupts();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
 	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
+out:
 	DBG("CPU%d coming online...\n", cpu);
 }