Skip to contentSkip to conversation

Fix kdump failures with crashkernel=high

PATCH In review Joerg Roedel 4 participants 10 messages Jun 5, 2015 – Jun 12, 2015

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

v3 cover Fix kdump failures with crashkernel=high

v2->v3

* Rebased to v4.1-rc6
* Updated changelogs as requested and added outcome of previous discussions
* Added more Acked-bys

v1->v2:

* Updated comments based on feedback from Konrad
* Added Acked-bys
* Rebased to v3.19-rc3

Hi,

here is a patch-set to fix failed kdump kernel boots when the systems was booted with crashkernel=X,high. On those systems the kernel allocates only 72MiB of low-memory for DMA buffers, which showed to be too low on some systems.

The problem is that 64MiB of the low-memory is allocated by swiotlb, leaving 8MB for the page-allocator. But swiotlb tries to allocate DMA memory from the page-allocator first, which fails pretty fast in the boot sequence, causing warnings. This patch-set removes these warnings.

But even the 64MiB for swiotlb are eaten up on some systems, so that the default of low-memory allocated for the crash-kernel is increase from 72MB to 256MB (only changing the defaults, can still be overwritten by crashkernel=X,low).

This number comes from experiments on the affected systems, 128MiB low-memory was still not enough there, thus I set the value to 256MiB to fix the issues.

Any feedback appreciated.

Thanks,

Joerg

Joerg Roedel (3):
swiotlb: Warn on allocation failure in swiotlb_alloc_coherent x86, swiotlb: Try coherent allocations with __GFP_NOWARN x86, crash: Allocate enough low-mem when crashkernel=high

 arch/x86/kernel/pci-swiotlb.c |  7 +++++++
 arch/x86/kernel/setup.c       |  5 ++++-
 lib/swiotlb.c                 | 11 +++++++++--
 3 files changed, 20 insertions(+), 3 deletions(-)
Signature · 1 line
1.9.1
#1 lore raw

PATCH v3 1/3 swiotlb: Warn on allocation failure in swiotlb_alloc_coherent

From: Joerg Roedel <[email protected]>

Print a warning when all allocation tries have been failed and the function is about to return NULL. This prepares for calling the function with __GFP_NOWARN to suppress allocation failure warnings before all fall-backs have failed.

---
 lib/swiotlb.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
lib/swiotlb.c +9 -2
index 4abda07..e0e9212 100644
@@ -655,7 +655,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 */
 		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (paddr == SWIOTLB_MAP_ERROR)
-			return NULL;
+			goto err_warn;
 
 		ret = phys_to_virt(paddr);
 		dev_addr = phys_to_dma(hwdev, paddr);
@@ -669,7 +669,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 			swiotlb_tbl_unmap_single(hwdev, paddr,
 						 size, DMA_TO_DEVICE);
-			return NULL;
+			goto err_warn;
 		}
 	}
 
@@ -677,6 +677,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	memset(ret, 0, size);
 
 	return ret;
+
+err_warn:
+	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+		dev_name(hwdev), size);
+	dump_stack();
+
+	return NULL;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
Signature · 1 line
1.9.1
#2 lore raw

[tip:x86/kdump] swiotlb: Warn on allocation failure in swiotlb_alloc_coherent()

swiotlb: Warn on allocation failure in swiotlb_alloc_coherent()
Commit-ID:  94cc81f9a8f995923e35e2db936741dd62d18350
Gitweb:     http://git.kernel.org/tip/94cc81f9a8f995923e35e2db936741dd62d18350
Author:     Joerg Roedel <[email protected]>
AuthorDate: Wed, 10 Jun 2015 17:49:40 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Thu, 11 Jun 2015 08:28:38 +0200

swiotlb: Warn on allocation failure in swiotlb_alloc_coherent()

Print a warning when all allocation tries have been failed and the function is about to return NULL.

This prepares for calling the function with __GFP_NOWARN to suppress allocation failure warnings before all fall-backs have failed - which we'll do to improve kdump behavior.

---
 lib/swiotlb.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
lib/swiotlb.c +9 -2
index 3c365ab..42e192d 100644
@@ -656,7 +656,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 */
 		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (paddr == SWIOTLB_MAP_ERROR)
-			return NULL;
+			goto err_warn;
 
 		ret = phys_to_virt(paddr);
 		dev_addr = phys_to_dma(hwdev, paddr);
@@ -670,7 +670,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 			swiotlb_tbl_unmap_single(hwdev, paddr,
 						 size, DMA_TO_DEVICE);
-			return NULL;
+			goto err_warn;
 		}
 	}
 
@@ -678,6 +678,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	memset(ret, 0, size);
 
 	return ret;
+
+err_warn:
+	pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n",
+		dev_name(hwdev), size);
+	dump_stack();
+
+	return NULL;
 }
 EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
#3 lore raw

PATCH v3 2/3 x86, swiotlb: Try coherent allocations with __GFP_NOWARN

In reply to Joerg Roedel

From: Joerg Roedel <[email protected]>

When we boot a kdump kernel in high memory, there is by default only 72MB of low memory available. The swiotlb code takes 64MB of it (by default) so that there are only 8MB left to allocate from. On systems with many devices this causes page allocator warnings from dma_generic_alloc_coherent():

systemd-udevd: page allocation failure: order:0, mode:0x280d4

CPU: 0 PID: 197 Comm: systemd-udevd Tainted: G        W       3.12.28-4-default #1
Hardware name: HP ProLiant DL980 G7, BIOS P66 07/30/2012
 ffff8800781335e0 ffffffff8150b1db 00000000000280d4 ffffffff8113af90
 0000000000000000 0000000000000000 ffff88007efdbb00 0000000100000000
 0000000000000000 0000000000000000 0000000000000000 0000000000000001
Call Trace:
  dump_trace+0x7d/0x2d0
  show_stack_log_lvl+0x94/0x170
  show_stack+0x21/0x50
  dump_stack+0x41/0x51
  warn_alloc_failed+0xf0/0x160
  __alloc_pages_slowpath+0x72f/0x796
  __alloc_pages_nodemask+0x1ea/0x210
  dma_generic_alloc_coherent+0x96/0x140
  x86_swiotlb_alloc_coherent+0x1c/0x50
  ttm_dma_pool_alloc_new_pages+0xab/0x320 [ttm]
  ttm_dma_populate+0x3ce/0x640 [ttm]
  ttm_tt_bind+0x36/0x60 [ttm]
  ttm_bo_handle_move_mem+0x55f/0x5c0 [ttm]
  ttm_bo_move_buffer+0x105/0x130 [ttm]
  ttm_bo_validate+0xc1/0x130 [ttm]
  ttm_bo_init+0x24b/0x400 [ttm]
  radeon_bo_create+0x16c/0x200 [radeon]
  radeon_ring_init+0x11e/0x2b0 [radeon]
  r100_cp_init+0x123/0x5b0 [radeon]
  r100_startup+0x194/0x230 [radeon]
  r100_init+0x223/0x410 [radeon]
  radeon_device_init+0x6af/0x830 [radeon]
  radeon_driver_load_kms+0x89/0x180 [radeon]
  drm_get_pci_dev+0x121/0x2f0 [drm]
  local_pci_probe+0x39/0x60
  pci_device_probe+0xa9/0x120
  driver_probe_device+0x9d/0x3d0
  __driver_attach+0x8b/0x90
  bus_for_each_dev+0x5b/0x90
  bus_add_driver+0x1f8/0x2c0
  driver_register+0x5b/0xe0
  do_one_initcall+0xf2/0x1a0
  load_module+0x1207/0x1c70
  SYSC_finit_module+0x75/0xa0
  system_call_fastpath+0x16/0x1b
  0x7fac533d2788

After these warnings the code enters a fall-back path and allocated directly from the swiotlb aperture in the end. So remove these warnings as this is not a fatal error.

---
 arch/x86/kernel/pci-swiotlb.c | 7 +++++++
 1 file changed, 7 insertions(+)
arch/x86/kernel/pci-swiotlb.c +7 -0
index 77dd0ad..6d6894c 100644
@@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 {
 	void *vaddr;
 
+	/*
+         * Don't print a warning when the first allocation attempt
+         * fails. The swiotlb_alloc_coherent() function will print a
+         * warning when the allocation of DMA memory ultimatly failed.
+	 */
+	flags |= __GFP_NOWARN;
+
 	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
 					   attrs);
 	if (vaddr)
Signature · 1 line
1.9.1
#4 lore raw

[tip:x86/kdump] x86/swiotlb: Try coherent allocations with __GFP_NOWARN

x86/swiotlb: Try coherent allocations with __GFP_NOWARN
Commit-ID:  186dfc9d69b96a38ec6ec654127dba4432184494
Gitweb:     http://git.kernel.org/tip/186dfc9d69b96a38ec6ec654127dba4432184494
Author:     Joerg Roedel <[email protected]>
AuthorDate: Wed, 10 Jun 2015 17:49:41 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Thu, 11 Jun 2015 08:28:38 +0200

x86/swiotlb: Try coherent allocations with __GFP_NOWARN

When we boot a kdump kernel in high memory, there is by default only 72MB of low memory available. The swiotlb code takes 64MB of it (by default) so that there are only 8MB left to allocate from. On systems with many devices this causes page allocator warnings from dma_generic_alloc_coherent():

systemd-udevd: page allocation failure: order:0, mode:0x280d4

  CPU: 0 PID: 197 Comm: systemd-udevd Tainted: G        W
  3.12.28-4-default #1 Hardware name: HP ProLiant DL980 G7, BIOS
  P66 07/30/2012  ffff8800781335e0 ffffffff8150b1db 00000000000280d4 ffffffff8113af90
   0000000000000000 0000000000000000 ffff88007efdbb00 0000000100000000
   0000000000000000 0000000000000000 0000000000000000 0000000000000001
  Call Trace:
    dump_trace+0x7d/0x2d0
    show_stack_log_lvl+0x94/0x170
    show_stack+0x21/0x50
    dump_stack+0x41/0x51
    warn_alloc_failed+0xf0/0x160
    __alloc_pages_slowpath+0x72f/0x796
    __alloc_pages_nodemask+0x1ea/0x210
    dma_generic_alloc_coherent+0x96/0x140
    x86_swiotlb_alloc_coherent+0x1c/0x50
    ttm_dma_pool_alloc_new_pages+0xab/0x320 [ttm]
    ttm_dma_populate+0x3ce/0x640 [ttm]
    ttm_tt_bind+0x36/0x60 [ttm]
    ttm_bo_handle_move_mem+0x55f/0x5c0 [ttm]
    ttm_bo_move_buffer+0x105/0x130 [ttm]
    ttm_bo_validate+0xc1/0x130 [ttm]
    ttm_bo_init+0x24b/0x400 [ttm]
    radeon_bo_create+0x16c/0x200 [radeon]
    radeon_ring_init+0x11e/0x2b0 [radeon]
    r100_cp_init+0x123/0x5b0 [radeon]
    r100_startup+0x194/0x230 [radeon]
    r100_init+0x223/0x410 [radeon]
    radeon_device_init+0x6af/0x830 [radeon]
    radeon_driver_load_kms+0x89/0x180 [radeon]
    drm_get_pci_dev+0x121/0x2f0 [drm]
    local_pci_probe+0x39/0x60
    pci_device_probe+0xa9/0x120
    driver_probe_device+0x9d/0x3d0
    __driver_attach+0x8b/0x90
    bus_for_each_dev+0x5b/0x90
    bus_add_driver+0x1f8/0x2c0
    driver_register+0x5b/0xe0
    do_one_initcall+0xf2/0x1a0
    load_module+0x1207/0x1c70
    SYSC_finit_module+0x75/0xa0
    system_call_fastpath+0x16/0x1b
    0x7fac533d2788

After these warnings the code enters a fall-back path and allocated directly from the swiotlb aperture in the end. So remove these warnings as this is not a fatal error.

[ Simplify, reflow comment. ]
Cc Andrew Morton <[email protected]>
Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Brian Gerst <[email protected]>
Cc Dave Young <[email protected]>
Cc Denys Vlasenko <[email protected]>
Cc H. Peter Anvin <[email protected]>
Cc Jörg Rödel <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Vivek Goyal <[email protected]>
---
 arch/x86/kernel/pci-swiotlb.c | 7 +++++++
 1 file changed, 7 insertions(+)
arch/x86/kernel/pci-swiotlb.c +7 -0
index 77dd0ad..adf0392 100644
@@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 {
 	void *vaddr;
 
+	/*
+	 * Don't print a warning when the first allocation attempt fails.
+	 * swiotlb_alloc_coherent() will print a warning when the DMA
+	 * memory allocation ultimately failed.
+	 */
+	flags |= __GFP_NOWARN;
+
 	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
 					   attrs);
 	if (vaddr)
#5 lore raw

PATCH v3 3/3 x86, crash: Allocate enough low-mem when crashkernel=high

In reply to Joerg Roedel

From: Joerg Roedel <[email protected]>

When the crashkernel is loaded above 4GiB in memory the first kernel only allocates 72MiB of low-memory for the DMA requirements of the second kernel. On systems with many devices this is not enough and causes device driver initialization errors and failed crash dumps. Testing by SUSE and Redhat have shown that 256MiB is a good default value for now and the discussion has agreed on this value as well. So set this default value to 256MiB to make sure there is enough memory available for DMA.

---
 arch/x86/kernel/setup.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
arch/x86/kernel/setup.c +4 -1
index d74ac33..a09f368 100644
@@ -535,8 +535,11 @@ static void __init reserve_crashkernel_low(void)
 		 *	swiotlb overflow buffer: now is hardcoded to 32k.
 		 *		We round it to 8M for other buffers that
 		 *		may need to stay low too.
+		 *		Also make sure we allocate enough extra memory
+		 *		low memory so that we don't run out of DMA
+		 *		buffers for 32bit devices.
 		 */
-		low_size = swiotlb_size_or_default() + (8UL<<20);
+		low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
 		auto_set = true;
 	} else {
 		/* passed with crashkernel=0,low ? */
Signature · 1 line
1.9.1
#6 lore raw

[tip:x86/kdump] x86/crash: Allocate enough low memory when crashkernel=high

x86/crash: Allocate enough low memory when crashkernel=high
Commit-ID:  94fb9334182284e8e7e4bcb9125c25dc33af19d4
Gitweb:     http://git.kernel.org/tip/94fb9334182284e8e7e4bcb9125c25dc33af19d4
Author:     Joerg Roedel <[email protected]>
AuthorDate: Wed, 10 Jun 2015 17:49:42 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Thu, 11 Jun 2015 08:28:39 +0200

x86/crash: Allocate enough low memory when crashkernel=high

When the crash kernel is loaded above 4GiB in memory, the first kernel allocates only 72MiB of low-memory for the DMA requirements of the second kernel. On systems with many devices this is not enough and causes device driver initialization errors and failed crash dumps. Testing by SUSE and Redhat has shown that 256MiB is a good default value for now and the discussion has lead to this value as well. So set this default value to 256MiB to make sure there is enough memory available for DMA.

[ Reflow comment. ]
Cc Andrew Morton <[email protected]>
Cc Andy Lutomirski <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Brian Gerst <[email protected]>
Cc Dave Young <[email protected]>
Cc Denys Vlasenko <[email protected]>
Cc H. Peter Anvin <[email protected]>
Cc Jörg Rödel <[email protected]>
Cc Linus Torvalds <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Vivek Goyal <[email protected]>
---
 arch/x86/kernel/setup.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)
arch/x86/kernel/setup.c +7 -5
index d74ac33..cba8288 100644
@@ -531,12 +531,14 @@ static void __init reserve_crashkernel_low(void)
 	if (ret != 0) {
 		/*
 		 * two parts from lib/swiotlb.c:
-		 *	swiotlb size: user specified with swiotlb= or default.
-		 *	swiotlb overflow buffer: now is hardcoded to 32k.
-		 *		We round it to 8M for other buffers that
-		 *		may need to stay low too.
+		 * -swiotlb size: user-specified with swiotlb= or default.
+		 *
+		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+		 * to 8M for other buffers that may need to stay low too. Also
+		 * make sure we allocate enough extra low memory so that we
+		 * don't run out of DMA buffers for 32-bit devices.
 		 */
-		low_size = swiotlb_size_or_default() + (8UL<<20);
+		low_size = max(swiotlb_size_or_default() + (8UL<<20), 256UL<<20);
 		auto_set = true;
 	} else {
 		/* passed with crashkernel=0,low ? */
maintainer
#7 lore raw
In reply to Joerg Roedel
Quoted 46 lines · Joerg Roedel

v2->v3

* Rebased to v4.1-rc6
* Updated changelogs as requested and added outcome of previous discussions
* Added more Acked-bys

v1->v2:

* Updated comments based on feedback from Konrad
* Added Acked-bys
* Rebased to v3.19-rc3

Hi,

here is a patch-set to fix failed kdump kernel boots when the systems was booted with crashkernel=X,high. On those systems the kernel allocates only 72MiB of low-memory for DMA buffers, which showed to be too low on some systems.

The problem is that 64MiB of the low-memory is allocated by swiotlb, leaving 8MB for the page-allocator. But swiotlb tries to allocate DMA memory from the page-allocator first, which fails pretty fast in the boot sequence, causing warnings. This patch-set removes these warnings.

But even the 64MiB for swiotlb are eaten up on some systems, so that the default of low-memory allocated for the crash-kernel is increase from 72MB to 256MB (only changing the defaults, can still be overwritten by crashkernel=X,low).

This number comes from experiments on the affected systems, 128MiB low-memory was still not enough there, thus I set the value to 256MiB to fix the issues.

Any feedback appreciated.

Thanks,

Joerg

Joerg Roedel (3):
swiotlb: Warn on allocation failure in swiotlb_alloc_coherent x86, swiotlb: Try coherent allocations with __GFP_NOWARN x86, crash: Allocate enough low-mem when crashkernel=high

Quoted 4 lines
 arch/x86/kernel/pci-swiotlb.c |  7 +++++++
 arch/x86/kernel/setup.c       |  5 ++++-
 lib/swiotlb.c                 | 11 +++++++++--
 3 files changed, 20 insertions(+), 3 deletions(-)

Looks simple enough, all applied, thanks.

hpa, Ingo, any concerns?

Signature · 5 lines
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--
#8 lore raw
Quoted 5 lines · Borislav Petkov
Quoted 5 lines

Joerg Roedel (3):
swiotlb: Warn on allocation failure in swiotlb_alloc_coherent x86, swiotlb: Try coherent allocations with __GFP_NOWARN x86, crash: Allocate enough low-mem when crashkernel=high

Quoted 8 lines
Quoted 4 lines
 arch/x86/kernel/pci-swiotlb.c |  7 +++++++
 arch/x86/kernel/setup.c       |  5 ++++-
 lib/swiotlb.c                 | 11 +++++++++--
 3 files changed, 20 insertions(+), 3 deletions(-)

Looks simple enough, all applied, thanks.

hpa, Ingo, any concerns?

Modulo a couple of typos it all looks sane.

Thanks,

Ingo

maintainer
#9 lore raw
Quoted 1 line · Ingo Molnar

Modulo a couple of typos it all looks sane.

Ah yes, I caught a few while applying. I'll send you the final result tomorrow.

Signature · 5 lines
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.
--