All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: linuxppc-dev@lists.ozlabs.org
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
	kvm-ppc@vger.kernel.org,
	David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH kernel 2/2] powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
Date: Tue, 16 Feb 2021 14:33:07 +1100	[thread overview]
Message-ID: <20210216033307.69863-3-aik@ozlabs.ru> (raw)
In-Reply-To: <20210216033307.69863-1-aik@ozlabs.ru>

Most platforms allocate IOMMU table structures (specifically it_map)
at the boot time and when this fails - it is a valid reason for panic().

However the powernv platform allocates it_map after a device is returned
to the host OS after being passed through and this happens long after
the host OS booted. It is quite possible to trigger the it_map allocation
panic() and kill the host even though it is not necessary - the host OS
can still use the DMA bypass mode (requires a tiny fraction of it_map's
memory) and even if that fails, the host OS is runnnable as it was without
the device for which allocating it_map causes the panic.

Instead of immediately crashing in a powernv/ioda2 system, this prints
an error and continues. All other platforms still call panic().

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/kernel/iommu.c               |  6 ++++--
 arch/powerpc/platforms/cell/iommu.c       |  3 ++-
 arch/powerpc/platforms/pasemi/iommu.c     |  4 +++-
 arch/powerpc/platforms/powernv/pci-ioda.c | 15 ++++++++-------
 arch/powerpc/platforms/pseries/iommu.c    | 10 +++++++---
 arch/powerpc/sysdev/dart_iommu.c          |  3 ++-
 6 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 8eb6eb0afa97..c1a5c366a664 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -728,8 +728,10 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
 	tbl->it_map = vzalloc_node(sz, nid);
-	if (!tbl->it_map)
-		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
+	if (!tbl->it_map) {
+		pr_err("%s: Can't allocate %ld bytes\n", __func__, sz);
+		return NULL;
+	}
 
 	iommu_table_reserve_pages(tbl, res_start, res_end);
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 2124831cf57c..fa08699aedeb 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -486,7 +486,8 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->table.it_size = size >> window->table.it_page_shift;
 	window->table.it_ops = &cell_iommu_ops;
 
-	iommu_init_table(&window->table, iommu->nid, 0, 0);
+	if (!iommu_init_table(&window->table, iommu->nid, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	pr_debug("\tioid      %d\n", window->ioid);
 	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index b500a6e47e6b..5be7242fbd86 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -146,7 +146,9 @@ static void iommu_table_iobmap_setup(void)
 	 */
 	iommu_table_iobmap.it_blocksize = 4;
 	iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops;
-	iommu_init_table(&iommu_table_iobmap, 0, 0, 0);
+	if (!iommu_init_table(&iommu_table_iobmap, 0, 0, 0))
+		panic("Failed to initialize iommu table");
+
 	pr_debug(" <- %s\n", __func__);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f0f901683a2f..66c3c3337334 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1762,7 +1762,8 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 	tbl->it_ops = &pnv_ioda1_iommu_ops;
 	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
 	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
-	iommu_init_table(tbl, phb->hose->node, 0, 0);
+	if (!iommu_init_table(tbl, phb->hose->node, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	pe->dma_setup_done = true;
 	return;
@@ -1930,16 +1931,16 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 		res_start = pe->phb->ioda.m32_pci_base >> tbl->it_page_shift;
 		res_end = min(window_size, SZ_4G) >> tbl->it_page_shift;
 	}
-	iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end);
 
-	rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+	if (iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end))
+		rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+	else
+		rc = -ENOMEM;
 	if (rc) {
-		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
-				rc);
+		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n", rc);
 		iommu_tce_table_put(tbl);
-		return rc;
+		tbl = NULL; /* This clears iommu_table_base below */
 	}
-
 	if (!pnv_iommu_bypass_disabled)
 		pnv_pci_ioda2_set_bypass(pe, true);
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 9fc5217f0c8e..4d9ac1f181c2 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -638,7 +638,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	tbl->it_ops = &iommu_table_pseries_ops;
-	iommu_init_table(tbl, pci->phb->node, 0, 0);
+	if (!iommu_init_table(tbl, pci->phb->node, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -720,7 +721,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, ppci->phb->node, 0, 0);
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -749,7 +751,9 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
-		iommu_init_table(tbl, phb->node, 0, 0);
+		if (!iommu_init_table(tbl, phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		set_iommu_table_base(&dev->dev, tbl);
 		return;
 	}
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 6b4a34b36d98..1d33b7a5ea83 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -344,7 +344,8 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
-	iommu_init_table(&iommu_table_dart, -1, 0, 0);
+	if (!iommu_init_table(&iommu_table_dart, -1, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	/* Reserve the last page of the DART to avoid possible prefetch
 	 * past the DART mapped area
-- 
2.17.1


WARNING: multiple messages have this Message-ID (diff)
From: Alexey Kardashevskiy <aik@ozlabs.ru>
To: linuxppc-dev@lists.ozlabs.org
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
	kvm-ppc@vger.kernel.org,
	David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH kernel 2/2] powerpc/iommu: Do not immediately panic when failed IOMMU table allocation
Date: Tue, 16 Feb 2021 03:33:07 +0000	[thread overview]
Message-ID: <20210216033307.69863-3-aik@ozlabs.ru> (raw)
In-Reply-To: <20210216033307.69863-1-aik@ozlabs.ru>

Most platforms allocate IOMMU table structures (specifically it_map)
at the boot time and when this fails - it is a valid reason for panic().

However the powernv platform allocates it_map after a device is returned
to the host OS after being passed through and this happens long after
the host OS booted. It is quite possible to trigger the it_map allocation
panic() and kill the host even though it is not necessary - the host OS
can still use the DMA bypass mode (requires a tiny fraction of it_map's
memory) and even if that fails, the host OS is runnnable as it was without
the device for which allocating it_map causes the panic.

Instead of immediately crashing in a powernv/ioda2 system, this prints
an error and continues. All other platforms still call panic().

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/kernel/iommu.c               |  6 ++++--
 arch/powerpc/platforms/cell/iommu.c       |  3 ++-
 arch/powerpc/platforms/pasemi/iommu.c     |  4 +++-
 arch/powerpc/platforms/powernv/pci-ioda.c | 15 ++++++++-------
 arch/powerpc/platforms/pseries/iommu.c    | 10 +++++++---
 arch/powerpc/sysdev/dart_iommu.c          |  3 ++-
 6 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 8eb6eb0afa97..c1a5c366a664 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -728,8 +728,10 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid,
 	sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
 
 	tbl->it_map = vzalloc_node(sz, nid);
-	if (!tbl->it_map)
-		panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
+	if (!tbl->it_map) {
+		pr_err("%s: Can't allocate %ld bytes\n", __func__, sz);
+		return NULL;
+	}
 
 	iommu_table_reserve_pages(tbl, res_start, res_end);
 
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 2124831cf57c..fa08699aedeb 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -486,7 +486,8 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->table.it_size = size >> window->table.it_page_shift;
 	window->table.it_ops = &cell_iommu_ops;
 
-	iommu_init_table(&window->table, iommu->nid, 0, 0);
+	if (!iommu_init_table(&window->table, iommu->nid, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	pr_debug("\tioid      %d\n", window->ioid);
 	pr_debug("\tblocksize %ld\n", window->table.it_blocksize);
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index b500a6e47e6b..5be7242fbd86 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -146,7 +146,9 @@ static void iommu_table_iobmap_setup(void)
 	 */
 	iommu_table_iobmap.it_blocksize = 4;
 	iommu_table_iobmap.it_ops = &iommu_table_iobmap_ops;
-	iommu_init_table(&iommu_table_iobmap, 0, 0, 0);
+	if (!iommu_init_table(&iommu_table_iobmap, 0, 0, 0))
+		panic("Failed to initialize iommu table");
+
 	pr_debug(" <- %s\n", __func__);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f0f901683a2f..66c3c3337334 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1762,7 +1762,8 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 	tbl->it_ops = &pnv_ioda1_iommu_ops;
 	pe->table_group.tce32_start = tbl->it_offset << tbl->it_page_shift;
 	pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift;
-	iommu_init_table(tbl, phb->hose->node, 0, 0);
+	if (!iommu_init_table(tbl, phb->hose->node, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	pe->dma_setup_done = true;
 	return;
@@ -1930,16 +1931,16 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 		res_start = pe->phb->ioda.m32_pci_base >> tbl->it_page_shift;
 		res_end = min(window_size, SZ_4G) >> tbl->it_page_shift;
 	}
-	iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end);
 
-	rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+	if (iommu_init_table(tbl, pe->phb->hose->node, res_start, res_end))
+		rc = pnv_pci_ioda2_set_window(&pe->table_group, 0, tbl);
+	else
+		rc = -ENOMEM;
 	if (rc) {
-		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n",
-				rc);
+		pe_err(pe, "Failed to configure 32-bit TCE table, err %ld\n", rc);
 		iommu_tce_table_put(tbl);
-		return rc;
+		tbl = NULL; /* This clears iommu_table_base below */
 	}
-
 	if (!pnv_iommu_bypass_disabled)
 		pnv_pci_ioda2_set_bypass(pe, true);
 
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 9fc5217f0c8e..4d9ac1f181c2 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -638,7 +638,8 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
 
 	iommu_table_setparms(pci->phb, dn, tbl);
 	tbl->it_ops = &iommu_table_pseries_ops;
-	iommu_init_table(tbl, pci->phb->node, 0, 0);
+	if (!iommu_init_table(tbl, pci->phb->node, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	/* Divide the rest (1.75GB) among the children */
 	pci->phb->dma_window_size = 0x80000000ul;
@@ -720,7 +721,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 		iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
 				ppci->table_group, dma_window);
 		tbl->it_ops = &iommu_table_lpar_multi_ops;
-		iommu_init_table(tbl, ppci->phb->node, 0, 0);
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -749,7 +751,9 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		tbl = PCI_DN(dn)->table_group->tables[0];
 		iommu_table_setparms(phb, dn, tbl);
 		tbl->it_ops = &iommu_table_pseries_ops;
-		iommu_init_table(tbl, phb->node, 0, 0);
+		if (!iommu_init_table(tbl, phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		set_iommu_table_base(&dev->dev, tbl);
 		return;
 	}
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 6b4a34b36d98..1d33b7a5ea83 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -344,7 +344,8 @@ static void iommu_table_dart_setup(void)
 	iommu_table_dart.it_index = 0;
 	iommu_table_dart.it_blocksize = 1;
 	iommu_table_dart.it_ops = &iommu_dart_ops;
-	iommu_init_table(&iommu_table_dart, -1, 0, 0);
+	if (!iommu_init_table(&iommu_table_dart, -1, 0, 0))
+		panic("Failed to initialize iommu table");
 
 	/* Reserve the last page of the DART to avoid possible prefetch
 	 * past the DART mapped area
-- 
2.17.1

  parent reply	other threads:[~2021-02-16  3:34 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-16  3:33 [PATCH kernel 0/2] powerpc/iommu: Stop crashing the host when VM is terminated Alexey Kardashevskiy
2021-02-16  3:33 ` Alexey Kardashevskiy
2021-02-16  3:33 ` [PATCH kernel 1/2] powerpc/iommu: Allocate it_map by vmalloc Alexey Kardashevskiy
2021-02-16  3:33   ` Alexey Kardashevskiy
2021-02-17  0:16   ` David Gibson
2021-02-17  0:16     ` David Gibson
2021-02-17 19:11   ` Leonardo Bras
2021-02-17 19:11     ` Leonardo Bras
2021-02-16  3:33 ` Alexey Kardashevskiy [this message]
2021-02-16  3:33   ` [PATCH kernel 2/2] powerpc/iommu: Do not immediately panic when failed IOMMU table allocation Alexey Kardashevskiy
2021-02-17  0:16   ` David Gibson
2021-02-17  0:16     ` David Gibson
2021-02-17 19:32   ` Leonardo Bras
2021-02-17 19:32     ` Leonardo Bras
2021-02-22  5:24     ` Alexey Kardashevskiy
2021-02-22  5:24       ` Alexey Kardashevskiy
2021-02-22 18:39       ` Leonardo Bras
2021-02-22 18:39         ` Leonardo Bras
2021-04-29 14:01 ` [PATCH kernel 0/2] powerpc/iommu: Stop crashing the host when VM is terminated Michael Ellerman
2021-04-29 14:01   ` Michael Ellerman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210216033307.69863-3-aik@ozlabs.ru \
    --to=aik@ozlabs.ru \
    --cc=david@gibson.dropbear.id.au \
    --cc=kvm-ppc@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.