Skip to contentSkip to conversation

5.4.69-rc1 review

PATCH In review Greg Kroah-Hartman 5 participants 393 messages Sep 29, 2020 – Sep 30, 2020 Page 1 of 3

Subsystems (10)
lore
Share & tools
lore
author maintainer
#187 lore raw

PATCH 187/388 perf cpumap: Fix snprintf overflow check

In reply to Greg Kroah-Hartman

From: Christophe JAILLET <[email protected]>

[ Upstream commit d74b181a028bb5a468f0c609553eff6a8fdf4887 ]

'snprintf' returns the number of characters which would be generated for the given input.

If the returned value is *greater than* or equal to the buffer size, it means that the output has been truncated.

Fix the overflow test accordingly.

Fixes 7780c25bae59f ("perf tools: Allow ability to map cpus to nodes easily")
Fixes 92a7e1278005b ("perf cpumap: Add cpu__max_present_cpu()")
Cc Alexander Shishkin <[email protected]>
Cc Don Zickus <[email protected]>
Cc He Zhe <[email protected]>
Cc Jan Stancek <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Kan Liang <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/cpumap.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
tools/perf/util/cpumap.c +5 -5
index a22c1114e880d..324ec0456c83f 100644
@@ -299,7 +299,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
-	if (ret = PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -310,7 +310,7 @@ static void set_max_cpu_num(void)
 
 	/* get the highest present cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt);
-	if (ret = PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -338,7 +338,7 @@ static void set_max_node_num(void)
 
 	/* get the highest possible cpu number for a sparse allocation */
 	ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
-	if (ret = PATH_MAX) {
+	if (ret >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		goto out;
 	}
@@ -423,7 +423,7 @@ int cpu__setup_cpunode_map(void)
 		return 0;
 
 	n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
-	if (n = PATH_MAX) {
+	if (n >= PATH_MAX) {
 		pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 		return -1;
 	}
@@ -438,7 +438,7 @@ int cpu__setup_cpunode_map(void)
 			continue;
 
 		n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
-		if (n = PATH_MAX) {
+		if (n >= PATH_MAX) {
 			pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
 			continue;
 		}
Signature · 1 line
2.25.1
author maintainer
#44 lore raw

PATCH 44/388 x86/kdump: Always reserve the low 1M when the crashkernel option is specified

In reply to Greg Kroah-Hartman

From: Lianbo Jiang <[email protected]>

[ Upstream commit 6f599d84231fd27e42f4ca2a786a6641e8cddf00 ]

On x86, purgatory() copies the first 640K of memory to a backup region because the kernel needs those first 640K for the real mode trampoline during boot, among others.

However, when SME is enabled, the kernel cannot properly copy the old memory to the backup area but reads only its encrypted contents. The result is that the crash tool gets invalid pointers when parsing vmcore:

crash> kmem -s|grep -i invalid
kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid freepointer:a6086ac099f0c5a4
kmem: dma-kmalloc-512: slab:ffffd77680001c00 invalid freepointer:a6086ac099f0c5a4 crash>

So reserve the remaining low 1M memory when the crashkernel option is specified (after reserving real mode memory) so that allocated memory does not fall into the low 1M area and thus the copying of the contents of the first 640k to a backup region in purgatory() can be avoided altogether.

This way, it does not need to be included in crash dumps or used for anything except the trampolines that must live in the low 1M.

[ bp: Heavily rewrite commit message, flip check logic in
crash_reserve_low_1M().]

---
 arch/x86/include/asm/crash.h |  6 ++++++
 arch/x86/kernel/crash.c      | 15 +++++++++++++++
 arch/x86/realmode/init.c     |  2 ++
 3 files changed, 23 insertions(+)
arch/x86/include/asm/crash.h +6 -0
index ef5638f641f2b..88eadd08ad708 100644
@@ -10,4 +10,10 @@ int crash_setup_memmap_entries(struct kimage *image,
 		struct boot_params *params);
 void crash_smp_send_stop(void);
 
+#ifdef CONFIG_KEXEC_CORE
+void __init crash_reserve_low_1M(void);
+#else
+static inline void __init crash_reserve_low_1M(void) { }
+#endif
+
 #endif /* _ASM_X86_CRASH_H */
arch/x86/kernel/crash.c +15 -0
index eb651fbde92ac..ff25a2ea271cf 100644
@@ -24,6 +24,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -39,6 +40,7 @@
 #include <asm/virtext.h>
 #include <asm/intel_pt.h>
 #include <asm/crash.h>
+#include <asm/cmdline.h>
 
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
@@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void)
 	rcu_read_unlock();
 }
 
+/*
+ * When the crashkernel option is specified, only use the low
+ * 1M for the real mode trampoline.
+ */
+void __init crash_reserve_low_1M(void)
+{
+	if (cmdline_find_option(boot_command_line, "crashkernel", NULL, 0) < 0)
+		return;
+
+	memblock_reserve(0, 1<<20);
+	pr_info("Reserving the low 1M of memory for crashkernel\n");
+}
+
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
 static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
arch/x86/realmode/init.c +2 -0
index 7dce39c8c034a..262f83cad3551 100644
@@ -8,6 +8,7 @@
 #include <asm/pgtable.h>
 #include <asm/realmode.h>
 #include <asm/tlbflush.h>
+#include <asm/crash.h>
 
 struct real_mode_header *real_mode_header;
 u32 *trampoline_cr4_features;
@@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
 
 	memblock_reserve(mem, size);
 	set_real_mode_mem(mem);
+	crash_reserve_low_1M();
 }
 
 static void __init setup_real_mode(void)
Signature · 9 lines
2.25.1




_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec
author maintainer
#6 lore raw

PATCH 6/388 drm/amd/display: Do not double-buffer DTO adjustments

In reply to Greg Kroah-Hartman

From: Wesley Chalmers <[email protected]>

[ Upstream commit 6bd0a112ec129615d23aa5d8d3dd0be0243989aa ]

[WHY]
When changing DPP global ref clock, DTO adjustments must take effect immediately, or else underflow may occur.
It appears the original decision to double-buffer DTO adjustments was made to prevent underflows that occur when raising DPP ref clock (which is not double-buffered), but that same decision causes similar issues when lowering DPP global ref clock. The better solution is to order the adjustments according to whether clocks are being raised or lowered.

---
 .../gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c | 26 -------------------
 1 file changed, 26 deletions(-)
drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c +0 -26
index 16476ed255363..2064366322755 100644
@@ -119,32 +119,6 @@ void dccg2_get_dccg_ref_freq(struct dccg *dccg,
 
 void dccg2_init(struct dccg *dccg)
 {
-	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
-
-	// Fallthrough intentional to program all available dpp_dto's
-	switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) {
-	case 6:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1);
-		/* Fall through */
-	case 5:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1);
-		/* Fall through */
-	case 4:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1);
-		/* Fall through */
-	case 3:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1);
-		/* Fall through */
-	case 2:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1);
-		/* Fall through */
-	case 1:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1);
-		break;
-	default:
-		ASSERT(false);
-		break;
-	}
 }
 
 static const struct dccg_funcs dccg2_funcs = {
Signature · 1 line
2.25.1
author maintainer
#119 lore raw

PATCH 119/388 drm/omap: fix possible object reference leak

In reply to Greg Kroah-Hartman

From: Wen Yang <[email protected]>

[ Upstream commit 47340e46f34a3b1d80e40b43ae3d7a8da34a3541 ]

The call to of_find_matching_node returns a node pointer with refcount incremented thus it must be explicitly decremented after the last usage.

Detected by coccinelle with the following warnings:
drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c:212:2-8: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function. drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c:237:1-7: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function.

---
 drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c +3 -1
index 31502857f013d..ce67891eedd46 100644
@@ -192,7 +192,7 @@ static int __init omapdss_boot_init(void)
 	dss = of_find_matching_node(NULL, omapdss_of_match);
 
 	if (dss == NULL || !of_device_is_available(dss))
-		return 0;
+		goto put_node;
 
 	omapdss_walk_device(dss, true);
 
@@ -217,6 +217,8 @@ static int __init omapdss_boot_init(void)
 		kfree(n);
 	}
 
+put_node:
+	of_node_put(dss);
 	return 0;
 }
 
Signature · 8 lines
2.25.1



_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
author maintainer
#7 lore raw

PATCH 7/388 drm/amdkfd: Fix race in gfx10 context restore handler

In reply to Greg Kroah-Hartman

From: Jay Cornwall <[email protected]>

[ Upstream commit c18cc2bb9e064d3a613d8276f2cab3984926a779 ]

Missing synchronization with VGPR restore leads to intermittent VGPR trashing in the user shader.

---
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler.h    | 139 +++++++++---------
 .../amd/amdkfd/cwsr_trap_handler_gfx10.asm    |   1 +
 2 files changed, 71 insertions(+), 69 deletions(-)
drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +70 -69
index 901fe35901656..d3400da6ab643 100644
@@ -905,7 +905,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x7a5d0000, 0x807c817c,
 	0x807aff7a, 0x00000080,
 	0xbf0a717c, 0xbf85fff8,
-	0xbf820141, 0xbef4037e,
+	0xbf820142, 0xbef4037e,
 	0x8775ff7f, 0x0000ffff,
 	0x8875ff75, 0x00040000,
 	0xbef60380, 0xbef703ff,
@@ -967,7 +967,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x725d0000, 0xe0304080,
 	0x725d0100, 0xe0304100,
 	0x725d0200, 0xe0304180,
-	0x725d0300, 0xbf820031,
+	0x725d0300, 0xbf820032,
 	0xbef603ff, 0x01000000,
 	0xbef20378, 0x8078ff78,
 	0x00000400, 0xbefc0384,
@@ -992,83 +992,84 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x725d0000, 0xe0304100,
 	0x725d0100, 0xe0304200,
 	0x725d0200, 0xe0304300,
-	0x725d0300, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0x80f8ff78,
-	0x00000050, 0xbef603ff,
-	0x01000000, 0xbefc03ff,
-	0x0000006c, 0x80f89078,
-	0xf429003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc847c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0x80f8a078,
-	0xf42d003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc887c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0x80f8c078,
-	0xf431003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0xbe883108,
-	0xbe8a310a, 0xbe8c310c,
-	0xbe8e310e, 0xbf06807c,
-	0xbf84fff0, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0xbef603ff,
-	0x01000000, 0xf4211bfa,
+	0x725d0300, 0xbf8c3f70,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0x80f8ff78, 0x00000050,
+	0xbef603ff, 0x01000000,
+	0xbefc03ff, 0x0000006c,
+	0x80f89078, 0xf429003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc847c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0x80f8a078, 0xf42d003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc887c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0x80f8c078, 0xf431003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0xbe883108, 0xbe8a310a,
+	0xbe8c310c, 0xbe8e310e,
+	0xbf06807c, 0xbf84fff0,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0xbef603ff, 0x01000000,
+	0xf4211bfa, 0xf0000000,
+	0x80788478, 0xf4211b3a,
 	0xf0000000, 0x80788478,
-	0xf4211b3a, 0xf0000000,
-	0x80788478, 0xf4211b7a,
+	0xf4211b7a, 0xf0000000,
+	0x80788478, 0xf4211eba,
 	0xf0000000, 0x80788478,
-	0xf4211eba, 0xf0000000,
-	0x80788478, 0xf4211efa,
+	0xf4211efa, 0xf0000000,
+	0x80788478, 0xf4211c3a,
 	0xf0000000, 0x80788478,
-	0xf4211c3a, 0xf0000000,
-	0x80788478, 0xf4211c7a,
+	0xf4211c7a, 0xf0000000,
+	0x80788478, 0xf4211e7a,
 	0xf0000000, 0x80788478,
-	0xf4211e7a, 0xf0000000,
-	0x80788478, 0xf4211cfa,
+	0xf4211cfa, 0xf0000000,
+	0x80788478, 0xf4211bba,
 	0xf0000000, 0x80788478,
+	0xbf8cc07f, 0xb9eef814,
 	0xf4211bba, 0xf0000000,
 	0x80788478, 0xbf8cc07f,
-	0xb9eef814, 0xf4211bba,
-	0xf0000000, 0x80788478,
-	0xbf8cc07f, 0xb9eef815,
-	0xbef2036d, 0x876dff72,
-	0x0000ffff, 0xbefc036f,
-	0xbefe037a, 0xbeff037b,
-	0x876f71ff, 0x000003ff,
-	0xb9ef4803, 0xb9f9f816,
-	0x876f71ff, 0xfffff800,
-	0x906f8b6f, 0xb9efa2c3,
-	0xb9f3f801, 0x876fff72,
-	0xfc000000, 0x906f9a6f,
-	0x8f6f906f, 0xbef30380,
+	0xb9eef815, 0xbef2036d,
+	0x876dff72, 0x0000ffff,
+	0xbefc036f, 0xbefe037a,
+	0xbeff037b, 0x876f71ff,
+	0x000003ff, 0xb9ef4803,
+	0xb9f9f816, 0x876f71ff,
+	0xfffff800, 0x906f8b6f,
+	0xb9efa2c3, 0xb9f3f801,
+	0x876fff72, 0xfc000000,
+	0x906f9a6f, 0x8f6f906f,
+	0xbef30380, 0x88736f73,
+	0x876fff72, 0x02000000,
+	0x906f996f, 0x8f6f8f6f,
 	0x88736f73, 0x876fff72,
-	0x02000000, 0x906f996f,
-	0x8f6f8f6f, 0x88736f73,
-	0x876fff72, 0x01000000,
-	0x906f986f, 0x8f6f996f,
-	0x88736f73, 0x876fff70,
-	0x00800000, 0x906f976f,
-	0xb9f3f807, 0x87fe7e7e,
-	0x87ea6a6a, 0xb9f0f802,
-	0xbf8a0000, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0x01000000, 0x906f986f,
+	0x8f6f996f, 0x88736f73,
+	0x876fff70, 0x00800000,
+	0x906f976f, 0xb9f3f807,
+	0x87fe7e7e, 0x87ea6a6a,
+	0xb9f0f802, 0xbf8a0000,
+	0xbe80226c, 0xbf810000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
+	0xbf9f0000, 0x00000000,
 };
 static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0xbf820001, 0xbf8202c4,
drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +1 -0
index cdaa523ce6bee..4433bda2ce25e 100644
@@ -758,6 +758,7 @@ L_RESTORE_V0:
 	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256
 	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*2
 	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*3
+	s_waitcnt	vmcnt(0)
 
 	/* restore SGPRs */
 	//will be 2+8+16*6
Signature · 1 line
2.25.1
author maintainer
#32 lore raw

PATCH 32/388 f2fs: avoid kernel panic on corruption test

In reply to Greg Kroah-Hartman

From: Jaegeuk Kim <[email protected]>

[ Upstream commit bc005a4d5347da68e690f78d365d8927c87dc85a ]

xfstests/generic/475 complains kernel warn/panic while testing corrupted disk.

---
 fs/f2fs/node.c | 1 -
 1 file changed, 1 deletion(-)
fs/f2fs/node.c +0 -1
index 8a67b933ccd42..ed12e96681842 100644
@@ -2353,7 +2353,6 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
 
 			if (ret) {
 				up_read(&nm_i->nat_tree_lock);
-				f2fs_bug_on(sbi, !mount);
 				f2fs_err(sbi, "NAT is corrupt, run fsck to fix it");
 				return ret;
 			}
Signature · 1 line
2.25.1
author maintainer
#18 lore raw

PATCH 18/388 ASoC: kirkwood: fix IRQ error handling

In reply to Greg Kroah-Hartman

From: Russell King <[email protected]>

[ Upstream commit 175fc928198236037174e5c5c066fe3c4691903e ]

Propagate the error code from request_irq(), rather than returning -EBUSY.

---
 sound/soc/kirkwood/kirkwood-dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/soc/kirkwood/kirkwood-dma.c +1 -1
index 6f69f314f2c2a..d2d5c25bf5502 100644
@@ -132,7 +132,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream)
 		err = request_irq(priv->irq, kirkwood_dma_irq, IRQF_SHARED,
 				  "kirkwood-i2s", priv);
 		if (err)
-			return -EBUSY;
+			return err;
 
 		/*
 		 * Enable Error interrupts. We're only ack'ing them but
Signature · 1 line
2.25.1
author maintainer
#2 lore raw

PATCH 2/388 scsi: lpfc: Fix pt2pt discovery on SLI3 HBAs

In reply to Greg Kroah-Hartman

From: James Smart <[email protected]>

[ Upstream commit 359e10f087dbb7b9c9f3035a8cc4391af45bd651 ]

After exchanging PLOGI on an SLI-3 adapter, the PRLI exchange failed. Link trace showed the port was assigned a non-zero n_port_id, but didn't use the address on the PRLI. The assigned address is set on the port by the CONFIG_LINK mailbox command. The driver responded to the PRLI before the mailbox command completed. Thus the PRLI response used the old n_port_id.

Defer the PRLI response until CONFIG_LINK completes.

---
 drivers/scsi/lpfc/lpfc_nportdisc.c | 141 +++++++++++++++++++++++------
 1 file changed, 115 insertions(+), 26 deletions(-)
drivers/scsi/lpfc/lpfc_nportdisc.c +115 -26
index 6961713825585..2a340624bfc99 100644
@@ -279,6 +279,55 @@ lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	lpfc_cancel_retry_delay_tmo(phba->pport, ndlp);
 }
 
+/* lpfc_defer_pt2pt_acc - Complete SLI3 pt2pt processing on link up
+ * @phba: pointer to lpfc hba data structure.
+ * @link_mbox: pointer to CONFIG_LINK mailbox object
+ *
+ * This routine is only called if we are SLI3, direct connect pt2pt
+ * mode and the remote NPort issues the PLOGI after link up.
+ */
+void
+lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox)
+{
+	LPFC_MBOXQ_t *login_mbox;
+	MAILBOX_t *mb = &link_mbox->u.mb;
+	struct lpfc_iocbq *save_iocb;
+	struct lpfc_nodelist *ndlp;
+	int rc;
+
+	ndlp = link_mbox->ctx_ndlp;
+	login_mbox = link_mbox->context3;
+	save_iocb = login_mbox->context3;
+	link_mbox->context3 = NULL;
+	login_mbox->context3 = NULL;
+
+	/* Check for CONFIG_LINK error */
+	if (mb->mbxStatus) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4575 CONFIG_LINK fails pt2pt discovery: %x\n",
+				mb->mbxStatus);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+		mempool_free(link_mbox, phba->mbox_mem_pool);
+		lpfc_sli_release_iocbq(phba, save_iocb);
+		return;
+	}
+
+	/* Now that CONFIG_LINK completed, and our SID is configured,
+	 * we can now proceed with sending the PLOGI ACC.
+	 */
+	rc = lpfc_els_rsp_acc(link_mbox->vport, ELS_CMD_PLOGI,
+			      save_iocb, ndlp, login_mbox);
+	if (rc) {
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4576 PLOGI ACC fails pt2pt discovery: %x\n",
+				rc);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+	}
+
+	mempool_free(link_mbox, phba->mbox_mem_pool);
+	lpfc_sli_release_iocbq(phba, save_iocb);
+}
+
 static int
 lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	       struct lpfc_iocbq *cmdiocb)
@@ -291,10 +340,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	IOCB_t *icmd;
 	struct serv_parm *sp;
 	uint32_t ed_tov;
-	LPFC_MBOXQ_t *mbox;
+	LPFC_MBOXQ_t *link_mbox;
+	LPFC_MBOXQ_t *login_mbox;
+	struct lpfc_iocbq *save_iocb;
 	struct ls_rjt stat;
 	uint32_t vid, flag;
-	int rc;
+	int rc, defer_acc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
 	pcmd = (struct lpfc_dmabuf *) cmdiocb->context2;
@@ -343,6 +394,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	else
 		ndlp->nlp_fcp_info |= CLASS3;
 
+	defer_acc = 0;
 	ndlp->nlp_class_sup = 0;
 	if (sp->cls1.classValid)
 		ndlp->nlp_class_sup |= FC_COS_CLASS1;
@@ -354,7 +406,6 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->nlp_class_sup |= FC_COS_CLASS4;
 	ndlp->nlp_maxframe =
 		((sp->cmn.bbRcvSizeMsb & 0x0F) << 8) | sp->cmn.bbRcvSizeLsb;
-
 	/* if already logged in, do implicit logout */
 	switch (ndlp->nlp_state) {
 	case  NLP_STE_NPR_NODE:
@@ -396,6 +447,10 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 	ndlp->nlp_flag &= ~NLP_FIRSTBURST;
 
+	login_mbox = NULL;
+	link_mbox = NULL;
+	save_iocb = NULL;
+
 	/* Check for Nport to NPort pt2pt protocol */
 	if ((vport->fc_flag & FC_PT2PT) &&
 	    !(vport->fc_flag & FC_PT2PT_PLOGI)) {
@@ -423,17 +478,22 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		if (phba->sli_rev == LPFC_SLI_REV4)
 			lpfc_issue_reg_vfi(vport);
 		else {
-			mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-			if (mbox == NULL)
+			defer_acc = 1;
+			link_mbox = mempool_alloc(phba->mbox_mem_pool,
+						  GFP_KERNEL);
+			if (!link_mbox)
 				goto out;
-			lpfc_config_link(phba, mbox);
-			mbox->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
-			mbox->vport = vport;
-			rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
-			if (rc == MBX_NOT_FINISHED) {
-				mempool_free(mbox, phba->mbox_mem_pool);
+			lpfc_config_link(phba, link_mbox);
+			link_mbox->mbox_cmpl = lpfc_defer_pt2pt_acc;
+			link_mbox->vport = vport;
+			link_mbox->ctx_ndlp = ndlp;
+
+			save_iocb = lpfc_sli_get_iocbq(phba);
+			if (!save_iocb)
 				goto out;
-			}
+			/* Save info from cmd IOCB used in rsp */
+			memcpy((uint8_t *)save_iocb, (uint8_t *)cmdiocb,
+			       sizeof(struct lpfc_iocbq));
 		}
 
 		lpfc_can_disctmo(vport);
@@ -448,8 +508,8 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			ndlp->nlp_flag |= NLP_SUPPRESS_RSP;
 	}
 
-	mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-	if (!mbox)
+	login_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+	if (!login_mbox)
 		goto out;
 
 	/* Registering an existing RPI behaves differently for SLI3 vs SLI4 */
@@ -457,21 +517,19 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		lpfc_unreg_rpi(vport, ndlp);
 
 	rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID,
-			    (uint8_t *) sp, mbox, ndlp->nlp_rpi);
-	if (rc) {
-		mempool_free(mbox, phba->mbox_mem_pool);
+			    (uint8_t *)sp, login_mbox, ndlp->nlp_rpi);
+	if (rc)
 		goto out;
-	}
 
 	/* ACC PLOGI rsp command needs to execute first,
-	 * queue this mbox command to be processed later.
+	 * queue this login_mbox command to be processed later.
 	 */
-	mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
+	login_mbox->mbox_cmpl = lpfc_mbx_cmpl_reg_login;
 	/*
-	 * mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox
+	 * login_mbox->ctx_ndlp = lpfc_nlp_get(ndlp) deferred until mailbox
 	 * command issued in lpfc_cmpl_els_acc().
 	 */
-	mbox->vport = vport;
+	login_mbox->vport = vport;
 	spin_lock_irq(shost->host_lock);
 	ndlp->nlp_flag |= (NLP_ACC_REGLOGIN | NLP_RCV_PLOGI);
 	spin_unlock_irq(shost->host_lock);
@@ -506,16 +564,47 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		stat.un.b.lsRjtRsnCode = LSRJT_INVALID_CMD;
 		stat.un.b.lsRjtRsnCodeExp = LSEXP_NOTHING_MORE;
 		rc = lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb,
-			ndlp, mbox);
+			ndlp, login_mbox);
 		if (rc)
-			mempool_free(mbox, phba->mbox_mem_pool);
+			mempool_free(login_mbox, phba->mbox_mem_pool);
 		return 1;
 	}
-	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, mbox);
+	if (defer_acc) {
+		/* So the order here should be:
+		 * Issue CONFIG_LINK mbox
+		 * CONFIG_LINK cmpl
+		 * Issue PLOGI ACC
+		 * PLOGI ACC cmpl
+		 * Issue REG_LOGIN mbox
+		 */
+
+		/* Save the REG_LOGIN mbox for and rcv IOCB copy later */
+		link_mbox->context3 = login_mbox;
+		login_mbox->context3 = save_iocb;
+
+		/* Start the ball rolling by issuing CONFIG_LINK here */
+		rc = lpfc_sli_issue_mbox(phba, link_mbox, MBX_NOWAIT);
+		if (rc == MBX_NOT_FINISHED)
+			goto out;
+		return 1;
+	}
+
+	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb, ndlp, login_mbox);
 	if (rc)
-		mempool_free(mbox, phba->mbox_mem_pool);
+		mempool_free(login_mbox, phba->mbox_mem_pool);
 	return 1;
 out:
+	if (defer_acc)
+		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
+				"4577 pt2pt discovery failure: %p %p %p\n",
+				save_iocb, link_mbox, login_mbox);
+	if (save_iocb)
+		lpfc_sli_release_iocbq(phba, save_iocb);
+	if (link_mbox)
+		mempool_free(link_mbox, phba->mbox_mem_pool);
+	if (login_mbox)
+		mempool_free(login_mbox, phba->mbox_mem_pool);
+
 	stat.un.b.lsRjtRsnCode = LSRJT_UNABLE_TPC;
 	stat.un.b.lsRjtRsnCodeExp = LSEXP_OUT_OF_RESOURCE;
 	lpfc_els_rsp_reject(vport, stat.un.lsRjtError, cmdiocb, ndlp, NULL);
Signature · 1 line
2.25.1
author maintainer
#24 lore raw

PATCH 24/388 dm table: do not allow request-based DM to stack on partitions

In reply to Greg Kroah-Hartman

From: Mike Snitzer <[email protected]>

[ Upstream commit 6ba01df72b4b63a26b4977790f58d8f775d2992c ]

Partitioned request-based devices cannot be used as underlying devices for request-based DM because no partition offsets are added to each incoming request. As such, until now, stacking on partitioned devices would _always_ result in data corruption (e.g. wiping the partition table, writing to other partitions, etc). Fix this by disallowing request-based stacking on partitions.

While at it, since all .request_fn support has been removed from block core, remove legacy dm-table code that differentiated between blk-mq and .request_fn request-based.

---
 drivers/md/dm-table.c | 27 ++++++++-------------------
 1 file changed, 8 insertions(+), 19 deletions(-)
drivers/md/dm-table.c +8 -19
index edc3660759131..13ad791126618 100644
@@ -922,21 +922,15 @@ bool dm_table_supports_dax(struct dm_table *t,
 
 static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
 
-struct verify_rq_based_data {
-	unsigned sq_count;
-	unsigned mq_count;
-};
-
-static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev,
-			      sector_t start, sector_t len, void *data)
+static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
+				  sector_t start, sector_t len, void *data)
 {
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	struct verify_rq_based_data *v = data;
+	struct block_device *bdev = dev->bdev;
+	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (queue_is_mq(q))
-		v->mq_count++;
-	else
-		v->sq_count++;
+	/* request-based cannot stack on partitions! */
+	if (bdev != bdev->bd_contains)
+		return false;
 
 	return queue_is_mq(q);
 }
@@ -945,7 +939,6 @@ static int dm_table_determine_type(struct dm_table *t)
 {
 	unsigned i;
 	unsigned bio_based = 0, request_based = 0, hybrid = 0;
-	struct verify_rq_based_data v = {.sq_count = 0, .mq_count = 0};
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
@@ -1049,14 +1042,10 @@ verify_rq_based:
 
 	/* Non-request-stackable devices can't be used for request-based dm */
 	if (!tgt->type->iterate_devices ||
-	    !tgt->type->iterate_devices(tgt, device_is_rq_based, &v)) {
+	    !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) {
 		DMERR("table load rejected: including non-request-stackable devices");
 		return -EINVAL;
 	}
-	if (v.sq_count > 0) {
-		DMERR("table load rejected: not all devices are blk-mq request-stackable");
-		return -EINVAL;
-	}
 
 	return 0;
 }
Signature · 1 line
2.25.1
author maintainer
#72 lore raw

PATCH 72/388 module: Remove accidental change of module_enable_x()

In reply to Greg Kroah-Hartman

From: Steven Rostedt (VMware) <[email protected]>

[ Upstream commit af74262337faa65d5ac2944553437d3f5fb29123 ]

When pulling in Divya Indi's patch, I made a minor fix to remove unneeded braces. I commited my fix up via "git commit -a --amend". Unfortunately, I didn't realize I had some changes I was testing in the module code, and those changes were applied to Divya's patch as well.

This reverts the accidental updates to the module code.

Cc Jessica Yu <[email protected]>
Cc Divya Indi <[email protected]>
Fixes e585e6469d6f ("tracing: Verify if trace array exists before destroying it.")
---
 kernel/module.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)
kernel/module.c +1 -5
index 0e3743dd3a568..819c5d3b4c295 100644
@@ -3753,6 +3753,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
 
 	module_enable_ro(mod, false);
 	module_enable_nx(mod);
+	module_enable_x(mod);
 
 	/* Mark state as coming so strong_try_module_get() ignores us,
 	 * but kallsyms etc. can see us. */
@@ -3775,11 +3776,6 @@ static int prepare_coming_module(struct module *mod)
 	if (err)
 		return err;
 
-	/* Make module executable after ftrace is enabled */
-	mutex_lock(&module_mutex);
-	module_enable_x(mod);
-	mutex_unlock(&module_mutex);
-
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_COMING, mod);
 	return 0;
Signature · 1 line
2.25.1
author maintainer
#76 lore raw

PATCH 76/388 vcc_seq_next should increase position index

In reply to Greg Kroah-Hartman

From: Vasily Averin <[email protected]>

[ Upstream commit 8bf7092021f283944f0c5f4c364853201c45c611 ]

if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283

---
 net/atm/proc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
net/atm/proc.c +1 -2
index d79221fd4dae2..c318967073139 100644
@@ -134,8 +134,7 @@ static void vcc_seq_stop(struct seq_file *seq, void *v)
 static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	v = vcc_walk(seq, 1);
-	if (v)
-		(*pos)++;
+	(*pos)++;
 	return v;
 }
 
Signature · 1 line
2.25.1
author maintainer
#17 lore raw

PATCH 17/388 gma/gma500: fix a memory disclosure bug due to uninitialized bytes

In reply to Greg Kroah-Hartman

From: Kangjie Lu <[email protected]>

[ Upstream commit 57a25a5f754ce27da2cfa6f413cfd366f878db76 ]

best_clock is an object that may be sent out. Object clock contains uninitialized bytes that are copied to best_clock, which leads to memory disclosure and information leak.

---
 drivers/gpu/drm/gma500/cdv_intel_display.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/gpu/drm/gma500/cdv_intel_display.c +2 -0
index f56852a503e8d..8b784947ed3b9 100644
@@ -405,6 +405,8 @@ static bool cdv_intel_find_dp_pll(const struct gma_limit_t *limit,
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct gma_clock_t clock;
 
+	memset(&clock, 0, sizeof(clock));
+
 	switch (refclk) {
 	case 27000:
 		if (target < 200000) {
Signature · 1 line
2.25.1
author maintainer
#107 lore raw

PATCH 107/388 mm: pagewalk: fix termination condition in walk_pte_range()

In reply to Greg Kroah-Hartman

From: Steven Price <[email protected]>

[ Upstream commit c02a98753e0a36ba65a05818626fa6adeb4e7c97 ]

If walk_pte_range() is called with a 'end' argument that is beyond the last page of memory (e.g. ~0UL) then the comparison between 'addr' and 'end' will always fail and the loop will be infinite. Instead change the comparison to >= while accounting for overflow.

Cc Albert Ou <[email protected]>
Cc Alexandre Ghiti <[email protected]>
Cc Andy Lutomirski <[email protected]>
Cc Ard Biesheuvel <[email protected]>
Cc Arnd Bergmann <[email protected]>
Cc Benjamin Herrenschmidt <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Catalin Marinas <[email protected]>
Cc Christian Borntraeger <[email protected]>
Cc Dave Hansen <[email protected]>
Cc David S. Miller <[email protected]>
Cc Heiko Carstens <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc James Hogan <[email protected]>
Cc James Morse <[email protected]>
Cc Jerome Glisse <[email protected]>
Cc "Liang, Kan" <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Michael Ellerman <[email protected]>
Cc Paul Burton <[email protected]>
Cc Paul Mackerras <[email protected]>
Cc Paul Walmsley <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ralf Baechle <[email protected]>
Cc Russell King <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Vasily Gorbik <[email protected]>
Cc Vineet Gupta <[email protected]>
Cc Will Deacon <[email protected]>
Cc Zong Li <[email protected]>
---
 mm/pagewalk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
mm/pagewalk.c +2 -2
index d48c2a986ea3f..4eb09e0898817 100644
@@ -16,9 +16,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
-		addr += PAGE_SIZE;
-		if (addr == end)
+		if (addr >= end - PAGE_SIZE)
 			break;
+		addr += PAGE_SIZE;
 		pte++;
 	}
 
Signature · 1 line
2.25.1
author maintainer
#118 lore raw

PATCH 118/388 scsi: lpfc: Fix coverity errors in fmdi attribute handling

In reply to Greg Kroah-Hartman

From: James Smart <[email protected]>

[ Upstream commit 4cb9e1ddaa145be9ed67b6a7de98ca705a43f998 ]

Coverity reported a memory corruption error for the fdmi attributes routines:

CID 15768 [Memory Corruption] Out-of-bounds access on FDMI

Sloppy coding of the fmdi structures. In both the lpfc_fdmi_attr_def and lpfc_fdmi_reg_port_list structures, a field was placed at the start of payload that may have variable content. The field was given an arbitrary type (uint32_t). The code then uses the field name to derive an address, which it used in things such as memset and memcpy. The memset sizes or memcpy lengths were larger than the arbitrary type, thus coverity reported an error.

Fix by replacing the arbitrary fields with the real field structures describing the payload.

---
 drivers/scsi/lpfc/lpfc_ct.c | 137 ++++++++++++++++++------------------
 drivers/scsi/lpfc/lpfc_hw.h |  36 +++++-----
 2 files changed, 85 insertions(+), 88 deletions(-)
drivers/scsi/lpfc/lpfc_ct.c +69 -68
index 4a09f21cb235f..e672fa9e842c9 100644
@@ -2056,8 +2056,8 @@ lpfc_fdmi_hba_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -2073,8 +2073,8 @@ lpfc_fdmi_hba_attr_manufacturer(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	/* This string MUST be consistent with other FC platforms
 	 * supported by Broadcom.
@@ -2098,8 +2098,8 @@ lpfc_fdmi_hba_attr_sn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad)
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->SerialNumber,
 		sizeof(ae->un.AttrString));
@@ -2120,8 +2120,8 @@ lpfc_fdmi_hba_attr_model(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelName,
 		sizeof(ae->un.AttrString));
@@ -2141,8 +2141,8 @@ lpfc_fdmi_hba_attr_description(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelDesc,
 		sizeof(ae->un.AttrString));
@@ -2164,8 +2164,8 @@ lpfc_fdmi_hba_attr_hdw_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t i, j, incr, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	/* Convert JEDEC ID to ascii for hardware version */
 	incr = vp->rev.biuRev;
@@ -2194,8 +2194,8 @@ lpfc_fdmi_hba_attr_drvr_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, lpfc_release_version,
 		sizeof(ae->un.AttrString));
@@ -2216,8 +2216,8 @@ lpfc_fdmi_hba_attr_rom_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1);
@@ -2241,8 +2241,8 @@ lpfc_fdmi_hba_attr_fmw_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1);
 	len = strnlen(ae->un.AttrString,
@@ -2261,8 +2261,8 @@ lpfc_fdmi_hba_attr_os_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s %s %s",
 		 init_utsname()->sysname,
@@ -2284,7 +2284,7 @@ lpfc_fdmi_hba_attr_ct_len(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	ae->un.AttrInt =  cpu_to_be32(LPFC_MAX_CT_SIZE);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -2300,8 +2300,8 @@ lpfc_fdmi_hba_attr_symbolic_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	len = lpfc_vport_symbolic_node_name(vport,
 				ae->un.AttrString, 256);
@@ -2319,7 +2319,7 @@ lpfc_fdmi_hba_attr_vendor_info(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Nothing is defined for this currently */
 	ae->un.AttrInt =  cpu_to_be32(0);
@@ -2336,7 +2336,7 @@ lpfc_fdmi_hba_attr_num_ports(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Each driver instance corresponds to a single port */
 	ae->un.AttrInt =  cpu_to_be32(1);
@@ -2353,8 +2353,8 @@ lpfc_fdmi_hba_attr_fabric_wwnn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fabric_nodename,
 	       sizeof(struct lpfc_name));
@@ -2372,8 +2372,8 @@ lpfc_fdmi_hba_attr_bios_ver(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strlcat(ae->un.AttrString, phba->BIOSVersion,
 		sizeof(ae->un.AttrString));
@@ -2393,7 +2393,7 @@ lpfc_fdmi_hba_attr_bios_state(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* Driver doesn't have access to this information */
 	ae->un.AttrInt =  cpu_to_be32(0);
@@ -2410,8 +2410,8 @@ lpfc_fdmi_hba_attr_vendor_id(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "EMULEX",
 		sizeof(ae->un.AttrString));
@@ -2433,8 +2433,8 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 32);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */
@@ -2459,7 +2459,7 @@ lpfc_fdmi_port_attr_support_speed(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	ae->un.AttrInt = 0;
 	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
@@ -2513,7 +2513,7 @@ lpfc_fdmi_port_attr_speed(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
 		switch (phba->fc_linkspeed) {
@@ -2583,7 +2583,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	hsp = (struct serv_parm *)&vport->fc_sparam;
 	ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb & 0x0F) << 8) |
@@ -2603,8 +2603,8 @@ lpfc_fdmi_port_attr_os_devname(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString),
 		 "/sys/class/scsi_host/host%d", shost->host_no);
@@ -2624,8 +2624,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	scnprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
 		  vport->phba->os_host_name);
@@ -2645,8 +2645,8 @@ lpfc_fdmi_port_attr_wwnn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -2663,8 +2663,8 @@ lpfc_fdmi_port_attr_wwpn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fc_sparam.portName,
 	       sizeof(struct lpfc_name));
@@ -2681,8 +2681,8 @@ lpfc_fdmi_port_attr_symbolic_name(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	len = lpfc_vport_symbolic_port_name(vport, ae->un.AttrString, 256);
 	len += (len & 3) ? (4 - (len & 3)) : 4;
@@ -2700,7 +2700,7 @@ lpfc_fdmi_port_attr_port_type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	if (phba->fc_topology == LPFC_TOPOLOGY_LOOP)
 		ae->un.AttrInt =  cpu_to_be32(LPFC_FDMI_PORTTYPE_NLPORT);
 	else
@@ -2718,7 +2718,7 @@ lpfc_fdmi_port_attr_class(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt = cpu_to_be32(FC_COS_CLASS2 | FC_COS_CLASS3);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2733,8 +2733,8 @@ lpfc_fdmi_port_attr_fabric_wwpn(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0,  sizeof(struct lpfc_name));
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrWWN, &vport->fabric_portname,
 	       sizeof(struct lpfc_name));
@@ -2751,8 +2751,8 @@ lpfc_fdmi_port_attr_active_fc4type(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 32);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */
@@ -2775,7 +2775,7 @@ lpfc_fdmi_port_attr_port_state(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	/* Link Up - operational */
 	ae->un.AttrInt =  cpu_to_be32(LPFC_FDMI_PORTSTATE_ONLINE);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -2791,7 +2791,7 @@ lpfc_fdmi_port_attr_num_disc(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	vport->fdmi_num_disc = lpfc_find_map_node(vport);
 	ae->un.AttrInt = cpu_to_be32(vport->fdmi_num_disc);
 	size = FOURBYTES + sizeof(uint32_t);
@@ -2807,7 +2807,7 @@ lpfc_fdmi_port_attr_nportid(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(vport->fc_myDID);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2822,8 +2822,8 @@ lpfc_fdmi_smart_attr_service(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "Smart SAN Initiator",
 		sizeof(ae->un.AttrString));
@@ -2843,8 +2843,8 @@ lpfc_fdmi_smart_attr_guid(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	memcpy(&ae->un.AttrString, &vport->fc_sparam.nodeName,
 	       sizeof(struct lpfc_name));
@@ -2864,8 +2864,8 @@ lpfc_fdmi_smart_attr_version(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, "Smart SAN Version 2.0",
 		sizeof(ae->un.AttrString));
@@ -2886,8 +2886,8 @@ lpfc_fdmi_smart_attr_model(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t len, size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
-	memset(ae, 0, 256);
+	ae = &ad->AttrValue;
+	memset(ae, 0, sizeof(*ae));
 
 	strncpy(ae->un.AttrString, phba->ModelName,
 		sizeof(ae->un.AttrString));
@@ -2906,7 +2906,7 @@ lpfc_fdmi_smart_attr_port_info(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 
 	/* SRIOV (type 3) is not supported */
 	if (vport->vpi)
@@ -2926,7 +2926,7 @@ lpfc_fdmi_smart_attr_qos(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(0);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -2941,7 +2941,7 @@ lpfc_fdmi_smart_attr_security(struct lpfc_vport *vport,
 	struct lpfc_fdmi_attr_entry *ae;
 	uint32_t size;
 
-	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
+	ae = &ad->AttrValue;
 	ae->un.AttrInt =  cpu_to_be32(1);
 	size = FOURBYTES + sizeof(uint32_t);
 	ad->AttrLen = cpu_to_be16(size);
@@ -3089,7 +3089,8 @@ lpfc_fdmi_cmd(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			/* Registered Port List */
 			/* One entry (port) per adapter */
 			rh->rpl.EntryCnt = cpu_to_be32(1);
-			memcpy(&rh->rpl.pe, &phba->pport->fc_sparam.portName,
+			memcpy(&rh->rpl.pe.PortName,
+			       &phba->pport->fc_sparam.portName,
 			       sizeof(struct lpfc_name));
 
 			/* point to the HBA attribute block */
drivers/scsi/lpfc/lpfc_hw.h +16 -20
index 436cdc8c5ef46..b5642c8725938 100644
@@ -1340,25 +1340,8 @@ struct fc_rdp_res_frame {
 /* lpfc_sli_ct_request defines the CT_IU preamble for FDMI commands */
 #define  SLI_CT_FDMI_Subtypes     0x10	/* Management Service Subtype */
 
-/*
- * Registered Port List Format
- */
-struct lpfc_fdmi_reg_port_list {
-	uint32_t EntryCnt;
-	uint32_t pe;		/* Variable-length array */
-};
-
-
 /* Definitions for HBA / Port attribute entries */
 
-struct lpfc_fdmi_attr_def { /* Defined in TLV format */
-	/* Structure is in Big Endian format */
-	uint32_t AttrType:16;
-	uint32_t AttrLen:16;
-	uint32_t AttrValue;  /* Marks start of Value (ATTRIBUTE_ENTRY) */
-};
-
-
 /* Attribute Entry */
 struct lpfc_fdmi_attr_entry {
 	union {
@@ -1369,7 +1352,13 @@ struct lpfc_fdmi_attr_entry {
 	} un;
 };
 
-#define LPFC_FDMI_MAX_AE_SIZE	sizeof(struct lpfc_fdmi_attr_entry)
+struct lpfc_fdmi_attr_def { /* Defined in TLV format */
+	/* Structure is in Big Endian format */
+	uint32_t AttrType:16;
+	uint32_t AttrLen:16;
+	/* Marks start of Value (ATTRIBUTE_ENTRY) */
+	struct lpfc_fdmi_attr_entry AttrValue;
+} __packed;
 
 /*
  * HBA Attribute Block
@@ -1393,13 +1382,20 @@ struct lpfc_fdmi_hba_ident {
 	struct lpfc_name PortName;
 };
 
+/*
+ * Registered Port List Format
+ */
+struct lpfc_fdmi_reg_port_list {
+	uint32_t EntryCnt;
+	struct lpfc_fdmi_port_entry pe;
+} __packed;
+
 /*
  * Register HBA(RHBA)
  */
 struct lpfc_fdmi_reg_hba {
 	struct lpfc_fdmi_hba_ident hi;
-	struct lpfc_fdmi_reg_port_list rpl;	/* variable-length array */
-/* struct lpfc_fdmi_attr_block   ab; */
+	struct lpfc_fdmi_reg_port_list rpl;
 };
 
 /*
Signature · 1 line
2.25.1
author maintainer
#30 lore raw

PATCH 30/388 dax: Fix alloc_dax_region() compile warning

In reply to Greg Kroah-Hartman

From: Dan Williams <[email protected]>

[ Upstream commit 460370ab20b6cc174256e46e192adf01e730faf6 ]

PFN flags are (unsigned long long), fix the alloc_dax_region() calling convention to fix warnings of the form:

Quoted 1 line
Quoted 1 line

include/linux/pfn_t.h:18:17: warning: large integer implicitly truncated to unsigned type [-Woverflow]

    #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
---
 drivers/dax/bus.c         | 2 +-
 drivers/dax/bus.h         | 2 +-
 drivers/dax/dax-private.h | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)
drivers/dax/bus.c +1 -1
index 8fafbeab510a8..eccdda1f7b71b 100644
@@ -227,7 +227,7 @@ static void dax_region_unregister(void *region)
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long pfn_flags)
+		unsigned long long pfn_flags)
 {
 	struct dax_region *dax_region;
 
drivers/dax/bus.h +1 -1
index 8619e32999436..9e4eba67e8b98 100644
@@ -11,7 +11,7 @@ struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, int target_node, unsigned int align,
-		unsigned long flags);
+		unsigned long long flags);
 
 enum dev_dax_subsys {
 	DEV_DAX_BUS,
drivers/dax/dax-private.h +1 -1
index 6ccca3b890d6f..3107ce80e8090 100644
@@ -32,7 +32,7 @@ struct dax_region {
 	struct device *dev;
 	unsigned int align;
 	struct resource res;
-	unsigned long pfn_flags;
+	unsigned long long pfn_flags;
 };
 
 /**
Signature · 1 line
2.25.1
author maintainer
#56 lore raw

PATCH 56/388 mt76: add missing locking around ampdu action

In reply to Greg Kroah-Hartman

From: Felix Fietkau <[email protected]>

[ Upstream commit 1a817fa73c3b27a593aadf0029de24db1bbc1a3e ]

This is needed primarily to avoid races in dealing with rx aggregation related data structures

---
 drivers/net/wireless/mediatek/mt76/mt7603/main.c  | 2 ++
 drivers/net/wireless/mediatek/mt76/mt7615/main.c  | 2 ++
 drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 2 ++
 3 files changed, 6 insertions(+)
drivers/net/wireless/mediatek/mt76/mt7603/main.c +2 -0
index 25d5b1608bc91..0a5695c3d9241 100644
@@ -561,6 +561,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mtxq = (struct mt76_txq *)txq->drv_priv;
 
+	mutex_lock(&dev->mt76.mutex);
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn,
@@ -590,6 +591,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
+	mutex_unlock(&dev->mt76.mutex);
 
 	return 0;
 }
drivers/net/wireless/mediatek/mt76/mt7615/main.c +2 -0
index 87c748715b5d7..38183aef0eb92 100644
@@ -455,6 +455,7 @@ mt7615_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mtxq = (struct mt76_txq *)txq->drv_priv;
 
+	mutex_lock(&dev->mt76.mutex);
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn,
@@ -485,6 +486,7 @@ mt7615_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
+	mutex_unlock(&dev->mt76.mutex);
 
 	return 0;
 }
drivers/net/wireless/mediatek/mt76/mt76x02_util.c +2 -0
index aec73a0295e86..de0d6f21c621c 100644
@@ -371,6 +371,7 @@ int mt76x02_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mtxq = (struct mt76_txq *)txq->drv_priv;
 
+	mutex_lock(&dev->mt76.mutex);
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid,
@@ -400,6 +401,7 @@ int mt76x02_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
+	mutex_unlock(&dev->mt76.mutex);
 
 	return 0;
 }
Signature · 1 line
2.25.1
author maintainer
#68 lore raw

PATCH 68/388 selftests/bpf: De-flake test_tcpbpf

In reply to Greg Kroah-Hartman

From: Stanislav Fomichev <[email protected]>

[ Upstream commit ef8c84effce3c7a0b8196fcda8f430c815ab511c ]

It looks like BPF program that handles BPF_SOCK_OPS_STATE_CB state can race with the bpf_map_lookup_elem("global_map"); I sometimes see the failures in this test and re-running helps.

Since we know that we expect the callback to be called 3 times (one time for listener socket, two times for both ends of the connection), let's export this number and add simple retry logic around that.

Also, let's make EXPECT_EQ() not return on failure, but continue evaluating all conditions; that should make potential debugging easier.

With this fix in place I don't observe the flakiness anymore.

---
 .../selftests/bpf/progs/test_tcpbpf_kern.c    |  1 +
 tools/testing/selftests/bpf/test_tcpbpf.h     |  1 +
 .../testing/selftests/bpf/test_tcpbpf_user.c  | 25 +++++++++++++------
 3 files changed, 20 insertions(+), 7 deletions(-)
tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +1 -0
index 2e233613d1fc0..7fa4595d2b66b 100644
@@ -131,6 +131,7 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 				g.bytes_received = skops->bytes_received;
 				g.bytes_acked = skops->bytes_acked;
 			}
+			g.num_close_events++;
 			bpf_map_update_elem(&global_map, &key, &g,
 					    BPF_ANY);
 		}
tools/testing/selftests/bpf/test_tcpbpf.h +1 -0
index 7bcfa62070056..6220b95cbd02c 100644
@@ -13,5 +13,6 @@ struct tcpbpf_globals {
 	__u64 bytes_received;
 	__u64 bytes_acked;
 	__u32 num_listen;
+	__u32 num_close_events;
 };
 #endif
tools/testing/selftests/bpf/test_tcpbpf_user.c +18 -7
index 716b4e3be5813..3ae127620463d 100644
@@ -16,6 +16,9 @@
 
 #include "test_tcpbpf.h"
 
+/* 3 comes from one listening socket + both ends of the connection */
+#define EXPECTED_CLOSE_EVENTS		3
+
 #define EXPECT_EQ(expected, actual, fmt)			\
 	do {							\
 		if ((expected) != (actual)) {			\
@@ -23,13 +26,14 @@
 			       "    Actual: %" fmt "\n"		\
 			       "  Expected: %" fmt "\n",	\
 			       (actual), (expected));		\
-			goto err;				\
+			ret--;					\
 		}						\
 	} while (0)
 
 int verify_result(const struct tcpbpf_globals *result)
 {
 	__u32 expected_events;
+	int ret = 0;
 
 	expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
 			   (1 << BPF_SOCK_OPS_RWND_INIT) |
@@ -48,15 +52,15 @@ int verify_result(const struct tcpbpf_globals *result)
 	EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
 	EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
 	EXPECT_EQ(1, result->num_listen, PRIu32);
+	EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32);
 
-	return 0;
-err:
-	return -1;
+	return ret;
 }
 
 int verify_sockopt_result(int sock_map_fd)
 {
 	__u32 key = 0;
+	int ret = 0;
 	int res;
 	int rv;
 
@@ -69,9 +73,7 @@ int verify_sockopt_result(int sock_map_fd)
 	rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
 	EXPECT_EQ(0, rv, "d");
 	EXPECT_EQ(1, res, "d");
-	return 0;
-err:
-	return -1;
+	return ret;
 }
 
 static int bpf_find_map(const char *test, struct bpf_object *obj,
@@ -96,6 +98,7 @@ int main(int argc, char **argv)
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
 	int cg_fd = -1;
+	int retry = 10;
 	__u32 key = 0;
 	int rv;
 
@@ -134,12 +137,20 @@ int main(int argc, char **argv)
 	if (sock_map_fd < 0)
 		goto err;
 
+retry_lookup:
 	rv = bpf_map_lookup_elem(map_fd, &key, &g);
 	if (rv != 0) {
 		printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
 		goto err;
 	}
 
+	if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) {
+		printf("Unexpected number of close events (%d), retrying!\n",
+		       g.num_close_events);
+		usleep(100);
+		goto retry_lookup;
+	}
+
 	if (verify_result(&g)) {
 		printf("FAILED: Wrong stats\n");
 		goto err;
Signature · 1 line
2.25.1
author maintainer
#57 lore raw

PATCH 57/388 debugfs: Fix !DEBUG_FS debugfs_create_automount

In reply to Greg Kroah-Hartman

From: Kusanagi Kouichi <[email protected]>

[ Upstream commit 4250b047039d324e0ff65267c8beb5bad5052a86 ]

If DEBUG_FS=n, compile fails with the following error:

kernel/trace/trace.c: In function 'tracing_init_dentry':
kernel/trace/trace.c:8658:9: error: passing argument 3 of 'debugfs_create_automount' from incompatible pointer type [-Werror=incompatible-pointer-types]

 8658 |         trace_automount, NULL);
      |         ^~~~~~~~~~~~~~~
      |         |
      |         struct vfsmount * (*)(struct dentry *, void *)
In file included from kernel/trace/trace.c:24:
./include/linux/debugfs.h:206:25: note: expected 'struct vfsmount * (*)(void *)' but argument is of type 'struct vfsmount * (*)(struct dentry *, void *)'
  206 |      struct vfsmount *(*f)(void *),
      |      ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~
---
 include/linux/debugfs.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
include/linux/debugfs.h +3 -2
index 58424eb3b3291..798f0b9b43aee 100644
@@ -54,6 +54,8 @@ static const struct file_operations __fops = {				\
 	.llseek  = no_llseek,						\
 }
 
+typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
+
 #if defined(CONFIG_DEBUG_FS)
 
 struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
@@ -75,7 +77,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent);
 struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 				      const char *dest);
 
-typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
 struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
 					debugfs_automount_t f,
@@ -203,7 +204,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name,
 
 static inline struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
-					struct vfsmount *(*f)(void *),
+					debugfs_automount_t f,
 					void *data)
 {
 	return ERR_PTR(-ENODEV);
Signature · 1 line
2.25.1
author maintainer
#83 lore raw

PATCH 83/388 media: ti-vpe: cal: Restrict DMA to avoid memory corruption

In reply to Greg Kroah-Hartman

From: Nikhil Devshatwar <[email protected]>

[ Upstream commit 6e72eab2e7b7a157d554b8f9faed7676047be7c1 ]

When setting DMA for video capture from CSI channel, if the DMA size is not given, it ends up writing as much data as sent by the camera.

This may lead to overwriting the buffers causing memory corruption. Observed green lines on the default framebuffer.

Restrict the DMA to maximum height as specified in the S_FMT ioctl.

---
 drivers/media/platform/ti-vpe/cal.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/media/platform/ti-vpe/cal.c +4 -2
index 955a49b8e9c08..f06408009a9c2 100644
@@ -678,12 +678,13 @@ static void pix_proc_config(struct cal_ctx *ctx)
 }
 
 static void cal_wr_dma_config(struct cal_ctx *ctx,
-			      unsigned int width)
+			      unsigned int width, unsigned int height)
 {
 	u32 val;
 
 	val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port));
 	set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK);
+	set_field(&val, height, CAL_WR_DMA_CTRL_YSIZE_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT,
 		  CAL_WR_DMA_CTRL_DTAG_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST,
@@ -1306,7 +1307,8 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count)
 	csi2_lane_config(ctx);
 	csi2_ctx_config(ctx);
 	pix_proc_config(ctx);
-	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline);
+	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline,
+			  ctx->v_fmt.fmt.pix.height);
 	cal_wr_dma_addr(ctx, addr);
 	csi2_ppi_enable(ctx);
 
Signature · 1 line
2.25.1
author maintainer
#134 lore raw

PATCH 134/388 dmaengine: stm32-dma: use vchan_terminate_vdesc() in .terminate_all

In reply to Greg Kroah-Hartman

From: Amelie Delaunay <[email protected]>

[ Upstream commit d80cbef35bf89b763f06e03bb4ff8f933bf012c5 ]

To avoid race with vchan_complete, use the race free way to terminate running transfer.

Move vdesc->node list_del in stm32_dma_start_transfer instead of in stm32_mdma_chan_complete to avoid another race in vchan_dma_desc_free_list.

---
 drivers/dma/stm32-dma.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/dma/stm32-dma.c +6 -3
index 5989b08935211..6c5771de32c67 100644
@@ -488,8 +488,10 @@ static int stm32_dma_terminate_all(struct dma_chan *c)
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 
-	if (chan->busy) {
-		stm32_dma_stop(chan);
+	if (chan->desc) {
+		vchan_terminate_vdesc(&chan->desc->vdesc);
+		if (chan->busy)
+			stm32_dma_stop(chan);
 		chan->desc = NULL;
 	}
 
@@ -545,6 +547,8 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan)
 		if (!vdesc)
 			return;
 
+		list_del(&vdesc->node);
+
 		chan->desc = to_stm32_dma_desc(vdesc);
 		chan->next_sg = 0;
 	}
@@ -622,7 +626,6 @@ static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan)
 		} else {
 			chan->busy = false;
 			if (chan->next_sg == chan->desc->num_sgs) {
-				list_del(&chan->desc->vdesc.node);
 				vchan_cookie_complete(&chan->desc->vdesc);
 				chan->desc = NULL;
 			}
Signature · 1 line
2.25.1
author maintainer
#139 lore raw

PATCH 139/388 iavf: use tc_cls_can_offload_and_chain0() instead of chain check

In reply to Greg Kroah-Hartman

From: Jiri Pirko <[email protected]>

[ Upstream commit bb0858d8bc828ebc3eaa90be02a0f32bca3c2351 ]

Looks like the iavf code actually experienced a race condition, when a developer took code before the check for chain 0 was put to helper. So use tc_cls_can_offload_and_chain0() helper instead of direct check and move the check to _cb() so this is similar to i40e code.

---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/iavf/iavf_main.c +5 -3
index 34124c213d27c..222ae76809aa1 100644
@@ -3077,9 +3077,6 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter,
 static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
 				    struct flow_cls_offload *cls_flower)
 {
-	if (cls_flower->common.chain_index)
-		return -EOPNOTSUPP;
-
 	switch (cls_flower->command) {
 	case FLOW_CLS_REPLACE:
 		return iavf_configure_clsflower(adapter, cls_flower);
@@ -3103,6 +3100,11 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
 static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				  void *cb_priv)
 {
+	struct iavf_adapter *adapter = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data))
+		return -EOPNOTSUPP;
+
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return iavf_setup_tc_cls_flower(cb_priv, type_data);
Signature · 1 line
2.25.1
author maintainer
#124 lore raw

PATCH 124/388 mt76: fix handling full tx queues in mt76_dma_tx_queue_skb_raw

In reply to Greg Kroah-Hartman

From: Felix Fietkau <[email protected]>

[ Upstream commit 93eaec7625f13cffb593b471405b017c7e64d4ee ]

Fixes a theoretical issue where it could potentially overwrite an existing descriptor entry (and leaking its skb)

---
 drivers/net/wireless/mediatek/mt76/dma.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/net/wireless/mediatek/mt76/dma.c +8 -1
index 6249a46c19762..026d996612fbe 100644
@@ -261,10 +261,13 @@ mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid,
 	struct mt76_queue_buf buf;
 	dma_addr_t addr;
 
+	if (q->queued + 1 >= q->ndesc - 1)
+		goto error;
+
 	addr = dma_map_single(dev->dev, skb->data, skb->len,
 			      DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev->dev, addr)))
-		return -ENOMEM;
+		goto error;
 
 	buf.addr = addr;
 	buf.len = skb->len;
@@ -275,6 +278,10 @@ mt76_dma_tx_queue_skb_raw(struct mt76_dev *dev, enum mt76_txq_id qid,
 	spin_unlock_bh(&q->lock);
 
 	return 0;
+
+error:
+	dev_kfree_skb(skb);
+	return -ENOMEM;
 }
 
 static int
Signature · 1 line
2.25.1
author maintainer
#110 lore raw

PATCH 110/388 ALSA: hda: Clear RIRB status before reading WP

In reply to Greg Kroah-Hartman

From: Mohan Kumar <[email protected]>

[ Upstream commit 6d011d5057ff88ee556c000ac6fe0be23bdfcd72 ]

RIRB interrupt status getting cleared after the write pointer is read causes a race condition, where last response(s) into RIRB may remain unserviced by IRQ, eventually causing azx_rirb_get_response to fall back to polling mode. Clearing the RIRB interrupt status ahead of write pointer access ensures that this condition is avoided.

---
 sound/pci/hda/hda_controller.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
sound/pci/hda/hda_controller.c +9 -2
index 76b507058cb4d..5e6081750bd9b 100644
@@ -1159,16 +1159,23 @@ irqreturn_t azx_interrupt(int irq, void *dev_id)
 		if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update))
 			active = true;
 
-		/* clear rirb int */
 		status = azx_readb(chip, RIRBSTS);
 		if (status & RIRB_INT_MASK) {
+			/*
+			 * Clearing the interrupt status here ensures that no
+			 * interrupt gets masked after the RIRB wp is read in
+			 * snd_hdac_bus_update_rirb. This avoids a possible
+			 * race condition where codec response in RIRB may
+			 * remain unserviced by IRQ, eventually falling back
+			 * to polling mode in azx_rirb_get_response.
+			 */
+			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 			active = true;
 			if (status & RIRB_INT_RESPONSE) {
 				if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND)
 					udelay(80);
 				snd_hdac_bus_update_rirb(bus);
 			}
-			azx_writeb(chip, RIRBSTS, RIRB_INT_MASK);
 		}
 	} while (active && ++repeat < 10);
 
Signature · 1 line
2.25.1
author maintainer
#176 lore raw

PATCH 176/388 drm/msm/a5xx: Always set an OPP supported hardware value

In reply to Greg Kroah-Hartman

From: Jordan Crouse <[email protected]>

[ Upstream commit 0478b4fc5f37f4d494245fe7bcce3f531cf380e9 ]

If the opp table specifies opp-supported-hw as a property but the driver has not set a supported hardware value the OPP subsystem will reject all the table entries.

Set a "default" value that will match the default table entries but not conflict with any possible real bin values. Also fix a small memory leak and free the buffer allocated by nvmem_cell_read().

---
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)
drivers/gpu/drm/msm/adreno/a5xx_gpu.c +20 -7
index 24b55103bfe00..c8fb21cc0d6ff 100644
@@ -1414,18 +1414,31 @@ static const struct adreno_gpu_funcs funcs = {
 static void check_speed_bin(struct device *dev)
 {
 	struct nvmem_cell *cell;
-	u32 bin, val;
+	u32 val;
+
+	/*
+	 * If the OPP table specifies a opp-supported-hw property then we have
+	 * to set something with dev_pm_opp_set_supported_hw() or the table
+	 * doesn't get populated so pick an arbitrary value that should
+	 * ensure the default frequencies are selected but not conflict with any
+	 * actual bins
+	 */
+	val = 0x80;
 
 	cell = nvmem_cell_get(dev, "speed_bin");
 
-	/* If a nvmem cell isn't defined, nothing to do */
-	if (IS_ERR(cell))
-		return;
+	if (!IS_ERR(cell)) {
+		void *buf = nvmem_cell_read(cell, NULL);
+
+		if (!IS_ERR(buf)) {
+			u8 bin = *((u8 *) buf);
 
-	bin = *((u32 *) nvmem_cell_read(cell, NULL));
-	nvmem_cell_put(cell);
+			val = (1 << bin);
+			kfree(buf);
+		}
 
-	val = (1 << bin);
+		nvmem_cell_put(cell);
+	}
 
 	dev_pm_opp_set_supported_hw(dev, &val, 1);
 }
Signature · 1 line
2.25.1
author maintainer
#182 lore raw

PATCH 182/388 btrfs: free the reloc_control in a consistent way

In reply to Greg Kroah-Hartman

From: Josef Bacik <[email protected]>

[ Upstream commit 1a0afa0ecfc4dbc8d7583d03cafd3f68f781df0c ]

If we have an error while processing the reloc roots we could leak roots that were added to rc->reloc_roots before we hit the error. We could have also not removed the reloc tree mapping from our rb_tree, so clean up any remaining nodes in the reloc root rb_tree.

[ use rbtree_postorder_for_each_entry_safe ]
---
 fs/btrfs/relocation.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
fs/btrfs/relocation.c +14 -2
index 1313506a7ecb5..ece53d2f55ae3 100644
@@ -4354,6 +4354,18 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
 	return rc;
 }
 
+static void free_reloc_control(struct reloc_control *rc)
+{
+	struct mapping_node *node, *tmp;
+
+	free_reloc_roots(&rc->reloc_roots);
+	rbtree_postorder_for_each_entry_safe(node, tmp,
+			&rc->reloc_root_tree.rb_root, rb_node)
+		kfree(node);
+
+	kfree(rc);
+}
+
 /*
  * Print the block group being relocated
  */
@@ -4486,7 +4498,7 @@ out:
 		btrfs_dec_block_group_ro(rc->block_group);
 	iput(rc->data_inode);
 	btrfs_put_block_group(rc->block_group);
-	kfree(rc);
+	free_reloc_control(rc);
 	return err;
 }
 
@@ -4659,7 +4671,7 @@ out_clean:
 		err = ret;
 out_unset:
 	unset_reloc_control(rc);
-	kfree(rc);
+	free_reloc_control(rc);
 out:
 	if (!list_empty(&reloc_roots))
 		free_reloc_roots(&reloc_roots);
Signature · 1 line
2.25.1
author maintainer
#152 lore raw

PATCH 152/388 drm/amdgpu: increase atombios cmd timeout

In reply to Greg Kroah-Hartman

From: John Clements <[email protected]>

[ Upstream commit 1b3460a8b19688ad3033b75237d40fa580a5a953 ]

mitigates race condition on BACO reset between GPU bootcode and driver reload

---
 drivers/gpu/drm/amd/amdgpu/atom.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/atom.c +2 -2
index dd30f4e61a8cd..cae426c7c0863 100644
@@ -744,8 +744,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg)
 			cjiffies = jiffies;
 			if (time_after(cjiffies, ctx->last_jump_jiffies)) {
 				cjiffies -= ctx->last_jump_jiffies;
-				if ((jiffies_to_msecs(cjiffies) > 5000)) {
-					DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n");
+				if ((jiffies_to_msecs(cjiffies) > 10000)) {
+					DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n");
 					ctx->abort = true;
 				}
 			} else {
Signature · 1 line
2.25.1
author maintainer
#195 lore raw

PATCH 195/388 kernel/kcmp.c: Use new infrastructure to fix deadlocks in execve

In reply to Greg Kroah-Hartman

From: Bernd Edlinger <[email protected]>

[ Upstream commit 454e3126cb842388e22df6b3ac3da44062c00765 ]

This changes kcmp_epoll_target to use the new exec_update_mutex instead of cred_guard_mutex.

This should be safe, as the credentials are only used for reading, and furthermore ->mm and ->sighand are updated on execve, but only under the new exec_update_mutex.

---
 kernel/kcmp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
kernel/kcmp.c +4 -4
index a0e3d7a0e8b81..b3ff9288c6cc9 100644
@@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	/*
 	 * One should have enough rights to inspect task details.
 	 */
-	ret = kcmp_lock(&task1->signal->cred_guard_mutex,
-			&task2->signal->cred_guard_mutex);
+	ret = kcmp_lock(&task1->signal->exec_update_mutex,
+			&task2->signal->exec_update_mutex);
 	if (ret)
 		goto err;
 	if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
@@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 	}
 
 err_unlock:
-	kcmp_unlock(&task1->signal->cred_guard_mutex,
-		    &task2->signal->cred_guard_mutex);
+	kcmp_unlock(&task1->signal->exec_update_mutex,
+		    &task2->signal->exec_update_mutex);
 err:
 	put_task_struct(task1);
 	put_task_struct(task2);
Signature · 1 line
2.25.1
author maintainer
#160 lore raw

PATCH 160/388 ath10k: use kzalloc to read for ath10k_sdio_hif_diag_read

In reply to Greg Kroah-Hartman

From: Wen Gong <[email protected]>

[ Upstream commit 402f2992b4d62760cce7c689ff216ea3bf4d6e8a ]

When use command to read values, it crashed.

command:
dd if=/sys/kernel/debug/ieee80211/phy0/ath10k/mem_value count=1 bs=4 skip=$((0x100233))

It will call to ath10k_sdio_hif_diag_read with address = 0x4008cc and buf_len = 4.

Then system crash:

[ 1786.013258] Unable to handle kernel paging request at virtual address ffffffc00bd45000
[ 1786.013273] Mem abort info:
[ 1786.013281]   ESR = 0x96000045
[ 1786.013291]   Exception class = DABT (current EL), IL = 32 bits
[ 1786.013299]   SET = 0, FnV = 0
[ 1786.013307]   EA = 0, S1PTW = 0
[ 1786.013314] Data abort info:
[ 1786.013322]   ISV = 0, ISS = 0x00000045
[ 1786.013330]   CM = 0, WnR = 1
[ 1786.013342] swapper pgtable: 4k pages, 39-bit VAs, pgdp = 000000008542a60e
[ 1786.013350] [ffffffc00bd45000] pgd=0000000000000000, pud=0000000000000000
[ 1786.013368] Internal error: Oops: 96000045 [#1] PREEMPT SMP
[ 1786.013609] Process swapper/0 (pid: 0, stack limit = 0x0000000084b153c6)
[ 1786.013623] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.86 #137
[ 1786.013631] Hardware name: MediaTek krane sku176 board (DT)
[ 1786.013643] pstate: 80000085 (Nzcv daIf -PAN -UAO)
[ 1786.013662] pc : __memcpy+0x94/0x180
[ 1786.013678] lr : swiotlb_tbl_unmap_single+0x84/0x150
[ 1786.013686] sp : ffffff8008003c60
[ 1786.013694] x29: ffffff8008003c90 x28: ffffffae96411f80
[ 1786.013708] x27: ffffffae960d2018 x26: ffffff8019a4b9a8
[ 1786.013721] x25: 0000000000000000 x24: 0000000000000001
[ 1786.013734] x23: ffffffae96567000 x22: 00000000000051d4
[ 1786.013747] x21: 0000000000000000 x20: 00000000fe6e9000
[ 1786.013760] x19: 0000000000000004 x18: 0000000000000020
[ 1786.013773] x17: 0000000000000001 x16: 0000000000000000
[ 1786.013787] x15: 00000000ffffffff x14: 00000000000044c0
[ 1786.013800] x13: 0000000000365ba4 x12: 0000000000000000
[ 1786.013813] x11: 0000000000000001 x10: 00000037be6e9000
[ 1786.013826] x9 : ffffffc940000000 x8 : 000000000bd45000
[ 1786.013839] x7 : 0000000000000000 x6 : ffffffc00bd45000
[ 1786.013852] x5 : 0000000000000000 x4 : 0000000000000000
[ 1786.013865] x3 : 0000000000000c00 x2 : 0000000000000004
[ 1786.013878] x1 : fffffff7be6e9004 x0 : ffffffc00bd45000
[ 1786.013891] Call trace:
[ 1786.013903]  __memcpy+0x94/0x180
[ 1786.013914]  unmap_single+0x6c/0x84
[ 1786.013925]  swiotlb_unmap_sg_attrs+0x54/0x80
[ 1786.013938]  __swiotlb_unmap_sg_attrs+0x8c/0xa4
[ 1786.013952]  msdc_unprepare_data+0x6c/0x84
[ 1786.013963]  msdc_request_done+0x58/0x84
[ 1786.013974]  msdc_data_xfer_done+0x1a0/0x1c8
[ 1786.013985]  msdc_irq+0x12c/0x17c
[ 1786.013996]  __handle_irq_event_percpu+0xe4/0x250
[ 1786.014006]  handle_irq_event_percpu+0x28/0x68
[ 1786.014015]  handle_irq_event+0x48/0x78
[ 1786.014026]  handle_fasteoi_irq+0xd0/0x1a0
[ 1786.014039]  __handle_domain_irq+0x84/0xc4
[ 1786.014050]  gic_handle_irq+0x124/0x1a4
[ 1786.014059]  el1_irq+0xb0/0x128
[ 1786.014072]  cpuidle_enter_state+0x298/0x328
[ 1786.014082]  cpuidle_enter+0x30/0x40
[ 1786.014094]  do_idle+0x190/0x268
[ 1786.014104]  cpu_startup_entry+0x24/0x28
[ 1786.014116]  rest_init+0xd4/0xe0
[ 1786.014126]  start_kernel+0x30c/0x38c
[ 1786.014139] Code: f8408423 f80084c3 36100062 b8404423 (b80044c3)
[ 1786.014150] ---[ end trace 3b02ddb698ea69ee ]---
[ 1786.015415] Kernel panic - not syncing: Fatal exception in interrupt
[ 1786.015433] SMP: stopping secondary CPUs
[ 1786.015447] Kernel Offset: 0x2e8d200000 from 0xffffff8008000000
[ 1786.015458] CPU features: 0x0,2188200c
[ 1786.015466] Memory Limit: none

For sdio chip, it need the memory which is kmalloc, if it is vmalloc from ath10k_mem_value_read, then it have a memory error. kzalloc of ath10k_sdio_hif_diag_read32 is the correct type, so add kzalloc in ath10k_sdio_hif_diag_read to replace the buffer which is vmalloc from ath10k_mem_value_read.

This patch only effect sdio chip.

Tested with QCA6174 SDIO with firmware WLAN.RMH.4.4.1-00029.

---
 drivers/net/wireless/ath/ath10k/sdio.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)
drivers/net/wireless/ath/ath10k/sdio.c +14 -4
index 9870d2d095c87..8fe626deadeb0 100644
@@ -1582,23 +1582,33 @@ static int ath10k_sdio_hif_diag_read(struct ath10k *ar, u32 address, void *buf,
 				     size_t buf_len)
 {
 	int ret;
+	void *mem;
+
+	mem = kzalloc(buf_len, GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
 
 	/* set window register to start read cycle */
 	ret = ath10k_sdio_write32(ar, MBOX_WINDOW_READ_ADDR_ADDRESS, address);
 	if (ret) {
 		ath10k_warn(ar, "failed to set mbox window read address: %d", ret);
-		return ret;
+		goto out;
 	}
 
 	/* read the data */
-	ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, buf, buf_len);
+	ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, mem, buf_len);
 	if (ret) {
 		ath10k_warn(ar, "failed to read from mbox window data address: %d\n",
 			    ret);
-		return ret;
+		goto out;
 	}
 
-	return 0;
+	memcpy(buf, mem, buf_len);
+
+out:
+	kfree(mem);
+
+	return ret;
 }
 
 static int ath10k_sdio_hif_diag_read32(struct ath10k *ar, u32 address,
Signature · 1 line
2.25.1
author maintainer
#196 lore raw

PATCH 196/388 proc: Use new infrastructure to fix deadlocks in execve

In reply to Greg Kroah-Hartman

From: Bernd Edlinger <[email protected]>

[ Upstream commit 2db9dbf71bf98d02a0bf33e798e5bfd2a9944696 ]

This changes lock_trace to use the new exec_update_mutex instead of cred_guard_mutex.

This fixes possible deadlocks when the trace is accessing /proc/$pid/stack for instance.

This should be safe, as the credentials are only used for reading, and task->mm is updated on execve under the new exec_update_mutex.

---
 fs/proc/base.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
fs/proc/base.c +3 -3
index ebea9501afb84..4fdfe4faa74ee 100644
@@ -403,11 +403,11 @@ print0:
 
 static int lock_trace(struct task_struct *task)
 {
-	int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	int err = mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
-		mutex_unlock(&task->signal->cred_guard_mutex);
+		mutex_unlock(&task->signal->exec_update_mutex);
 		return -EPERM;
 	}
 	return 0;
@@ -415,7 +415,7 @@ static int lock_trace(struct task_struct *task)
 
 static void unlock_trace(struct task_struct *task)
 {
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 }
 
 #ifdef CONFIG_STACKTRACE
Signature · 1 line
2.25.1
author maintainer
#200 lore raw

PATCH 200/388 nvme: Fix ctrl use-after-free during sysfs deletion

In reply to Greg Kroah-Hartman

From: Israel Rukshin <[email protected]>

[ Upstream commit b780d7415aacec855e2f2370cbf98f918b224903 ]

In case nvme_sysfs_delete() is called by the user before taking the ctrl reference count, the ctrl may be freed during the creation and cause the bug. Take the reference as soon as the controller is externally visible, which is done by cdev_device_add() in nvme_init_ctrl(). Also take the reference count at the core layer instead of taking it on each transport separately.

---
 drivers/nvme/host/core.c   | 2 ++
 drivers/nvme/host/fc.c     | 4 +---
 drivers/nvme/host/pci.c    | 1 -
 drivers/nvme/host/rdma.c   | 3 +--
 drivers/nvme/host/tcp.c    | 3 +--
 drivers/nvme/target/loop.c | 3 +--
 6 files changed, 6 insertions(+), 10 deletions(-)
drivers/nvme/host/core.c +2 -0
index 8247e58624c10..32cefbd80bdfb 100644
@@ -4082,6 +4082,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	if (ret)
 		goto out_release_instance;
 
+	nvme_get_ctrl(ctrl);
 	cdev_init(&ctrl->cdev, &nvme_dev_fops);
 	ctrl->cdev.owner = ops->module;
 	ret = cdev_device_add(&ctrl->cdev, ctrl->device);
@@ -4100,6 +4101,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 
 	return 0;
 out_free_name:
+	nvme_put_ctrl(ctrl);
 	kfree_const(ctrl->device->kobj.name);
 out_release_instance:
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
drivers/nvme/host/fc.c +1 -3
index dae050d1f814d..da801a14cd13d 100644
@@ -3171,10 +3171,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 		goto fail_ctrl;
 	}
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
-		nvme_put_ctrl(&ctrl->ctrl);
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: failed to schedule initial connect\n",
 			ctrl->cnum);
@@ -3199,6 +3196,7 @@ fail_ctrl:
 
 	/* initiate nvme ctrl ref counting teardown */
 	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 
 	/* Remove core ctrl ref. */
 	nvme_put_ctrl(&ctrl->ctrl);
drivers/nvme/host/pci.c +0 -1
index a91433bdf5de4..75f26d2ec6429 100644
@@ -2850,7 +2850,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	nvme_reset_ctrl(&dev->ctrl);
-	nvme_get_ctrl(&dev->ctrl);
 	async_schedule(nvme_async_probe, dev);
 
 	return 0;
drivers/nvme/host/rdma.c +1 -2
index f9444272f861e..abe4fe496d05c 100644
@@ -2088,8 +2088,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
@@ -2099,6 +2097,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
drivers/nvme/host/tcp.c +1 -2
index c782005ee99f9..6d7a813e7183a 100644
@@ -2404,8 +2404,6 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
 	mutex_unlock(&nvme_tcp_ctrl_mutex);
@@ -2415,6 +2413,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
 		ret = -EIO;
 	return ERR_PTR(ret);
drivers/nvme/target/loop.c +1 -2
index 11f5aea97d1b1..82b87a4c50f63 100644
@@ -619,8 +619,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 	dev_info(ctrl->ctrl.device,
 		 "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
 
-	nvme_get_ctrl(&ctrl->ctrl);
-
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
 	WARN_ON_ONCE(!changed);
 
@@ -638,6 +636,7 @@ out_free_queues:
 	kfree(ctrl->queues);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
+	nvme_put_ctrl(&ctrl->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&ctrl->ctrl);
 	if (ret > 0)
Signature · 1 line
2.25.1
author maintainer
#186 lore raw

PATCH 186/388 serial: 8250: 8250_omap: Terminate DMA before pushing data on RX timeout

In reply to Greg Kroah-Hartman

From: Vignesh Raghavendra <[email protected]>

[ Upstream commit 7cf4df30a98175033e9849f7f16c46e96ba47f41 ]

Terminate and flush DMA internal buffers, before pushing RX data to higher layer. Otherwise, this will lead to data corruption, as driver would end up pushing stale buffer data to higher layer while actual data is still stuck inside DMA hardware and has yet not arrived at the memory.
While at that, replace deprecated dmaengine_terminate_all() with dmaengine_terminate_async().

---
 drivers/tty/serial/8250/8250_omap.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/tty/serial/8250/8250_omap.c +4 -2
index 2624b5d083366..f2c6d9d3bb28f 100644
@@ -790,7 +790,10 @@ static void __dma_rx_do_complete(struct uart_8250_port *p)
 	dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);
 
 	count = dma->rx_size - state.residue;
-
+	if (count < dma->rx_size)
+		dmaengine_terminate_async(dma->rxchan);
+	if (!count)
+		goto unlock;
 	ret = tty_insert_flip_string(tty_port, dma->rx_buf, count);
 
 	p->port.icount.rx += ret;
@@ -852,7 +855,6 @@ static void omap_8250_rx_dma_flush(struct uart_8250_port *p)
 	spin_unlock_irqrestore(&priv->rx_dma_lock, flags);
 
 	__dma_rx_do_complete(p);
-	dmaengine_terminate_all(dma->rxchan);
 }
 
 static int omap_8250_rx_dma(struct uart_8250_port *p)
Signature · 1 line
2.25.1
author maintainer
#203 lore raw

PATCH 203/388 xfs: prohibit fs freezing when using empty transactions

In reply to Greg Kroah-Hartman

From: Darrick J. Wong <[email protected]>

[ Upstream commit 27fb5a72f50aa770dd38b0478c07acacef97e3e7 ]

I noticed that fsfreeze can take a very long time to freeze an XFS if there happens to be a GETFSMAP caller running in the background. I also happened to notice the following in dmesg:

------------[ cut here ]------------
WARNING: CPU: 2 PID: 43492 at fs/xfs/xfs_super.c:853 xfs_quiesce_attr+0x83/0x90 [xfs]
Modules linked in: xfs libcrc32c ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 ip_set_hash_ip ip_set_hash_net xt_tcpudp xt_set ip_set_hash_mac ip_set nfnetlink ip6table_filter ip6_tables bfq iptable_filter sch_fq_codel ip_tables x_tables nfsv4 af_packet [last unloaded: xfs]
CPU: 2 PID: 43492 Comm: xfs_io Not tainted 5.6.0-rc4-djw #rc4
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-1ubuntu1 04/01/2014
RIP: 0010:xfs_quiesce_attr+0x83/0x90 [xfs]
Code: 7c 07 00 00 85 c0 75 22 48 89 df 5b e9 96 c1 00 00 48 c7 c6 b0 2d 38 a0 48 89 df e8 57 64 ff ff 8b 83 7c 07 00 00 85 c0 74 de <0f> 0b 48 89 df 5b e9 72 c1 00 00 66 90 0f 1f 44 00 00 41 55 41 54
RSP: 0018:ffffc900030f3e28 EFLAGS: 00010202
RAX: 0000000000000001 RBX: ffff88802ac54000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff81e4a6f0 RDI: 00000000ffffffff
RBP: ffff88807859f070 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000010 R12: 0000000000000000
R13: ffff88807859f388 R14: ffff88807859f4b8 R15: ffff88807859f5e8
FS:  00007fad1c6c0fc0(0000) GS:ffff88807e000000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f0c7d237000 CR3: 0000000077f01003 CR4: 00000000001606a0
Call Trace:
 xfs_fs_freeze+0x25/0x40 [xfs]
 freeze_super+0xc8/0x180
 do_vfs_ioctl+0x70b/0x750
 ? __fget_files+0x135/0x210
 ksys_ioctl+0x3a/0xb0
 __x64_sys_ioctl+0x16/0x20
 do_syscall_64+0x50/0x1a0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

These two things appear to be related. The assertion trips when another thread initiates a fsmap request (which uses an empty transaction) after the freezer waited for m_active_trans to hit zero but before the the freezer executes the WARN_ON just prior to calling xfs_log_quiesce.

The lengthy delays in freezing happen because the freezer calls xfs_wait_buftarg to clean out the buffer lru list. Meanwhile, the GETFSMAP caller is continuing to grab and release buffers, which means that it can take a very long time for the buffer lru list to empty out.

We fix both of these races by calling sb_start_write to obtain freeze protection while using empty transactions for GETFSMAP and for metadata scrubbing. The other two users occur during mount, during which time we cannot fs freeze.

---
 fs/xfs/scrub/scrub.c | 9 +++++++++
 fs/xfs/xfs_fsmap.c   | 9 +++++++++
 fs/xfs/xfs_trans.c   | 5 +++++
 3 files changed, 23 insertions(+)
fs/xfs/scrub/scrub.c +9 -0
index 15c8c5f3f688d..720bef5779989 100644
@@ -167,6 +167,7 @@ xchk_teardown(
 			xfs_irele(sc->ip);
 		sc->ip = NULL;
 	}
+	sb_end_write(sc->mp->m_super);
 	if (sc->flags & XCHK_REAPING_DISABLED)
 		xchk_start_reaping(sc);
 	if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) {
@@ -489,6 +490,14 @@ xfs_scrub_metadata(
 	sc.ops = &meta_scrub_ops[sm->sm_type];
 	sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
 retry_op:
+	/*
+	 * If freeze runs concurrently with a scrub, the freeze can be delayed
+	 * indefinitely as we walk the filesystem and iterate over metadata
+	 * buffers.  Freeze quiesces the log (which waits for the buffer LRU to
+	 * be emptied) and that won't happen while checking is running.
+	 */
+	sb_start_write(mp->m_super);
+
 	/* Set up for the operation. */
 	error = sc.ops->setup(&sc, ip);
 	if (error)
fs/xfs/xfs_fsmap.c +9 -0
index d082143feb5ab..c13754e119be1 100644
@@ -895,6 +895,14 @@ xfs_getfsmap(
 	info.format_arg = arg;
 	info.head = head;
 
+	/*
+	 * If fsmap runs concurrently with a scrub, the freeze can be delayed
+	 * indefinitely as we walk the rmapbt and iterate over metadata
+	 * buffers.  Freeze quiesces the log (which waits for the buffer LRU to
+	 * be emptied) and that won't happen while we're reading buffers.
+	 */
+	sb_start_write(mp->m_super);
+
 	/* For each device we support... */
 	for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
 		/* Is this device within the range the user asked for? */
@@ -934,6 +942,7 @@ xfs_getfsmap(
 
 	if (tp)
 		xfs_trans_cancel(tp);
+	sb_end_write(mp->m_super);
 	head->fmh_oflags = FMH_OF_DEV_T;
 	return error;
 }
fs/xfs/xfs_trans.c +5 -0
index f4795fdb7389c..b32a66452d441 100644
@@ -306,6 +306,11 @@ xfs_trans_alloc(
  *
  * Note the zero-length reservation; this transaction MUST be cancelled
  * without any dirty data.
+ *
+ * Callers should obtain freeze protection to avoid two conflicts with fs
+ * freezing: (1) having active transactions trip the m_active_trans ASSERTs;
+ * and (2) grabbing buffers at the same time that freeze is trying to drain
+ * the buffer LRU list.
  */
 int
 xfs_trans_alloc_empty(
Signature · 1 line
2.25.1
author maintainer
#202 lore raw

PATCH 202/388 brcmfmac: Fix double freeing in the fmac usb data path

In reply to Greg Kroah-Hartman

From: Raveendran Somu <[email protected]>

[ Upstream commit 78179869dc3f5c0059bbf5d931a2717f1ad97ecd ]

When the brcmf_fws_process_skb() fails to get hanger slot for queuing the skb, it tries to free the skb.
But the caller brcmf_netdev_start_xmit() of that funciton frees the packet on error return value.
This causes the double freeing and which caused the kernel crash.

---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c +1 -2
index eadc64454839d..3d36b6ee158bb 100644
@@ -2149,8 +2149,7 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 		brcmf_fws_enq(fws, BRCMF_FWS_SKBSTATE_DELAYED, fifo, skb);
 		brcmf_fws_schedule_deq(fws);
 	} else {
-		bphy_err(drvr, "drop skb: no hanger slot\n");
-		brcmf_txfinalize(ifp, skb, false);
+		bphy_err(drvr, "no hanger slot available\n");
 		rc = -ENOMEM;
 	}
 	brcmf_fws_unlock(fws);
Signature · 1 line
2.25.1
author maintainer
#206 lore raw

PATCH 206/388 scsi: hpsa: correct race condition in offload enabled

In reply to Greg Kroah-Hartman

From: Don Brace <[email protected]>

[ Upstream commit 3e16e83a62edac7617bfd8dbb4e55d04ff6adbe1 ]

Correct race condition where ioaccel is re-enabled before the raid_map is updated. For RAID_1, RAID_1ADM, and RAID 5/6 there is a BUG_ON called which is bad.

- Change event thread to disable ioaccel only. Send all requests down the RAID path instead.

- Have rescan thread handle offload_enable.

- Since there is only one rescan allowed at a time, turning offload_enabled on/off should not be racy. Each handler queues up a rescan if one is already in progress.

- For timing diagram, offload_enabled is initially off due to a change (transformation: splitmirror/remirror), ...

otbe = offload_to_be_enabled
oe = offload_enabled

  Time Event         Rescan              Completion     Request
       Worker        Worker              Thread         Thread
  ---- ------        ------              ----------     -------
   T0   |             |                       + UA      |
   T1   |             + rescan started        | 0x3f    |
   T2   + Event       |                       | 0x0e    |
   T3   + Ack msg     |                       |         |
   T4   |             + if (!dev[i]->oe &&    |         |
   T5   |             |     dev[i]->otbe)     |         |
   T6   |             |      get_raid_map     |         |
   T7   + otbe = 1    |                       |         |
   T8   |             |                       |         |
   T9   |             + oe = otbe             |         |
   T10  |             |                       |         + ioaccel request
   T11                                                  * BUG_ON

T0 - I/O completion with UA 0x3f 0x0e sets rescan flag. T1 - rescan worker thread starts a rescan.
T2 - event comes in
T3 - event thread starts and issues "Acknowledge" message
...
T6 - rescan thread has bypassed code to reload new raid map.
...
T7 - event thread runs and sets offload_to_be_enabled
...
T9 - rescan thread turns on offload_enabled.
T10- request comes in and goes down ioaccel path. T11- BUG_ON.

- After the patch is applied, ioaccel_enabled can only be re-enabled in the re-scan thread.

---
 drivers/scsi/hpsa.c | 80 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 57 insertions(+), 23 deletions(-)
drivers/scsi/hpsa.c +57 -23
index 216e557f703e6..e67cb4561aace 100644
@@ -504,6 +504,12 @@ static ssize_t host_store_rescan(struct device *dev,
 	return count;
 }
 
+static void hpsa_turn_off_ioaccel_for_device(struct hpsa_scsi_dev_t *device)
+{
+	device->offload_enabled = 0;
+	device->offload_to_be_enabled = 0;
+}
+
 static ssize_t host_show_firmware_revision(struct device *dev,
 	     struct device_attribute *attr, char *buf)
 {
@@ -1738,8 +1744,7 @@ static void hpsa_figure_phys_disk_ptrs(struct ctlr_info *h,
 				__func__,
 				h->scsi_host->host_no, logical_drive->bus,
 				logical_drive->target, logical_drive->lun);
-			logical_drive->offload_enabled = 0;
-			logical_drive->offload_to_be_enabled = 0;
+			hpsa_turn_off_ioaccel_for_device(logical_drive);
 			logical_drive->queue_depth = 8;
 		}
 	}
@@ -2499,8 +2504,7 @@ static void process_ioaccel2_completion(struct ctlr_info *h,
 			IOACCEL2_SERV_RESPONSE_FAILURE) {
 		if (c2->error_data.status ==
 			IOACCEL2_STATUS_SR_IOACCEL_DISABLED) {
-			dev->offload_enabled = 0;
-			dev->offload_to_be_enabled = 0;
+			hpsa_turn_off_ioaccel_for_device(dev);
 		}
 
 		if (dev->in_reset) {
@@ -3670,10 +3674,17 @@ static void hpsa_get_ioaccel_status(struct ctlr_info *h,
 	this_device->offload_config =
 		!!(ioaccel_status & OFFLOAD_CONFIGURED_BIT);
 	if (this_device->offload_config) {
-		this_device->offload_to_be_enabled =
+		bool offload_enabled =
 			!!(ioaccel_status & OFFLOAD_ENABLED_BIT);
-		if (hpsa_get_raid_map(h, scsi3addr, this_device))
-			this_device->offload_to_be_enabled = 0;
+		/*
+		 * Check to see if offload can be enabled.
+		 */
+		if (offload_enabled) {
+			rc = hpsa_get_raid_map(h, scsi3addr, this_device);
+			if (rc) /* could not load raid_map */
+				goto out;
+			this_device->offload_to_be_enabled = 1;
+		}
 	}
 
 out:
@@ -3996,8 +4007,7 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 	} else {
 		this_device->raid_level = RAID_UNKNOWN;
 		this_device->offload_config = 0;
-		this_device->offload_enabled = 0;
-		this_device->offload_to_be_enabled = 0;
+		hpsa_turn_off_ioaccel_for_device(this_device);
 		this_device->hba_ioaccel_enabled = 0;
 		this_device->volume_offline = 0;
 		this_device->queue_depth = h->nr_cmds;
@@ -5230,8 +5240,12 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		/* Handles load balance across RAID 1 members.
 		 * (2-drive R1 and R10 with even # of drives.)
 		 * Appropriate for SSDs, not optimal for HDDs
+		 * Ensure we have the correct raid_map.
 		 */
-		BUG_ON(le16_to_cpu(map->layout_map_count) != 2);
+		if (le16_to_cpu(map->layout_map_count) != 2) {
+			hpsa_turn_off_ioaccel_for_device(dev);
+			return IO_ACCEL_INELIGIBLE;
+		}
 		if (dev->offload_to_mirror)
 			map_index += le16_to_cpu(map->data_disks_per_row);
 		dev->offload_to_mirror = !dev->offload_to_mirror;
@@ -5239,8 +5253,12 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 	case HPSA_RAID_ADM:
 		/* Handles N-way mirrors  (R1-ADM)
 		 * and R10 with # of drives divisible by 3.)
+		 * Ensure we have the correct raid_map.
 		 */
-		BUG_ON(le16_to_cpu(map->layout_map_count) != 3);
+		if (le16_to_cpu(map->layout_map_count) != 3) {
+			hpsa_turn_off_ioaccel_for_device(dev);
+			return IO_ACCEL_INELIGIBLE;
+		}
 
 		offload_to_mirror = dev->offload_to_mirror;
 		raid_map_helper(map, offload_to_mirror,
@@ -5265,7 +5283,10 @@ static int hpsa_scsi_ioaccel_raid_map(struct ctlr_info *h,
 		r5or6_blocks_per_row =
 			le16_to_cpu(map->strip_size) *
 			le16_to_cpu(map->data_disks_per_row);
-		BUG_ON(r5or6_blocks_per_row == 0);
+		if (r5or6_blocks_per_row == 0) {
+			hpsa_turn_off_ioaccel_for_device(dev);
+			return IO_ACCEL_INELIGIBLE;
+		}
 		stripesize = r5or6_blocks_per_row *
 			le16_to_cpu(map->layout_map_count);
 #if BITS_PER_LONG == 32
@@ -8285,7 +8306,7 @@ static int detect_controller_lockup(struct ctlr_info *h)
  *
  * Called from monitor controller worker (hpsa_event_monitor_worker)
  *
- * A Volume (or Volumes that comprise an Array set may be undergoing a
+ * A Volume (or Volumes that comprise an Array set) may be undergoing a
  * transformation, so we will be turning off ioaccel for all volumes that
  * make up the Array.
  */
@@ -8308,6 +8329,9 @@ static void hpsa_set_ioaccel_status(struct ctlr_info *h)
 	 * Run through current device list used during I/O requests.
 	 */
 	for (i = 0; i < h->ndevices; i++) {
+		int offload_to_be_enabled = 0;
+		int offload_config = 0;
+
 		device = h->dev[i];
 
 		if (!device)
@@ -8325,25 +8349,35 @@ static void hpsa_set_ioaccel_status(struct ctlr_info *h)
 			continue;
 
 		ioaccel_status = buf[IOACCEL_STATUS_BYTE];
-		device->offload_config =
+
+		/*
+		 * Check if offload is still configured on
+		 */
+		offload_config =
 				!!(ioaccel_status & OFFLOAD_CONFIGURED_BIT);
-		if (device->offload_config)
-			device->offload_to_be_enabled =
+		/*
+		 * If offload is configured on, check to see if ioaccel
+		 * needs to be enabled.
+		 */
+		if (offload_config)
+			offload_to_be_enabled =
 				!!(ioaccel_status & OFFLOAD_ENABLED_BIT);
 
+		/*
+		 * If ioaccel is to be re-enabled, re-enable later during the
+		 * scan operation so the driver can get a fresh raidmap
+		 * before turning ioaccel back on.
+		 */
+		if (offload_to_be_enabled)
+			continue;
+
 		/*
 		 * Immediately turn off ioaccel for any volume the
 		 * controller tells us to. Some of the reasons could be:
 		 *    transformation - change to the LVs of an Array.
 		 *    degraded volume - component failure
-		 *
-		 * If ioaccel is to be re-enabled, re-enable later during the
-		 * scan operation so the driver can get a fresh raidmap
-		 * before turning ioaccel back on.
-		 *
 		 */
-		if (!device->offload_to_be_enabled)
-			device->offload_enabled = 0;
+		hpsa_turn_off_ioaccel_for_device(device);
 	}
 
 	kfree(buf);
Signature · 1 line
2.25.1
author maintainer
#212 lore raw

PATCH 212/388 ubifs: ubifs_add_orphan: Fix a memory leak bug

In reply to Greg Kroah-Hartman

From: Zhihao Cheng <[email protected]>

[ Upstream commit 927cc5cec35f01fe4f8af0ba80830a90b0533983 ]

Memory leak occurs when files with extended attributes are added to orphan list.

Fixes 988bec41318f3fa897e2f8 ("ubifs: orphan: Handle xattrs like files")
---
 fs/ubifs/orphan.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
fs/ubifs/orphan.c +7 -2
index 7dd740e3692da..283f9eb48410d 100644
@@ -157,7 +157,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
 	int err = 0;
 	ino_t xattr_inum;
 	union ubifs_key key;
-	struct ubifs_dent_node *xent;
+	struct ubifs_dent_node *xent, *pxent = NULL;
 	struct fscrypt_name nm = {0};
 	struct ubifs_orphan *xattr_orphan;
 	struct ubifs_orphan *orphan;
@@ -181,11 +181,16 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum)
 		xattr_inum = le64_to_cpu(xent->inum);
 
 		xattr_orphan = orphan_add(c, xattr_inum, orphan);
-		if (IS_ERR(xattr_orphan))
+		if (IS_ERR(xattr_orphan)) {
+			kfree(xent);
 			return PTR_ERR(xattr_orphan);
+		}
 
+		kfree(pxent);
+		pxent = xent;
 		key_read(c, &xent->key, &key);
 	}
+	kfree(pxent);
 
 	return 0;
 }
Signature · 1 line
2.25.1
author maintainer
#209 lore raw

PATCH 209/388 netfilter: nf_tables: silence a RCU-list warning in nft_table_lookup()

In reply to Greg Kroah-Hartman

From: Qian Cai <[email protected]>

[ Upstream commit 0a6a9515fe390976cd762c52d8d4f446d7a14285 ]

It is safe to traverse &net->nft.tables with &net->nft.commit_mutex held using list_for_each_entry_rcu(). Silence the PROVE_RCU_LIST false positive,

WARNING: suspicious RCU usage
net/netfilter/nf_tables_api.c:523 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by iptables/1384:
#0: ffffffff9745c4a8 (&net->nft.commit_mutex){+.+.}, at: nf_tables_valid_genid+0x25/0x60 [nf_tables]

Call Trace:
 dump_stack+0xa1/0xea
 lockdep_rcu_suspicious+0x103/0x10d
 nft_table_lookup.part.0+0x116/0x120 [nf_tables]
 nf_tables_newtable+0x12c/0x7d0 [nf_tables]
 nfnetlink_rcv_batch+0x559/0x1190 [nfnetlink]
 nfnetlink_rcv+0x1da/0x210 [nfnetlink]
 netlink_unicast+0x306/0x460
 netlink_sendmsg+0x44b/0x770
 ____sys_sendmsg+0x46b/0x4a0
 ___sys_sendmsg+0x138/0x1a0
 __sys_sendmsg+0xb6/0x130
 __x64_sys_sendmsg+0x48/0x50
 do_syscall_64+0x69/0xf4
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
---
 net/netfilter/nf_tables_api.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/netfilter/nf_tables_api.c +2 -1
index 2023650c27249..ff2d2b514506e 100644
@@ -456,7 +456,8 @@ static struct nft_table *nft_table_lookup(const struct net *net,
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	list_for_each_entry_rcu(table, &net->nft.tables, list) {
+	list_for_each_entry_rcu(table, &net->nft.tables, list,
+				lockdep_is_held(&net->nft.commit_mutex)) {
 		if (!nla_strcmp(nla, table->name) &&
 		    table->family == family &&
 		    nft_active_genmask(table, genmask))
Signature · 1 line
2.25.1
author maintainer
#211 lore raw

PATCH 211/388 ubifs: ubifs_jnl_write_inode: Fix a memory leak bug

In reply to Greg Kroah-Hartman

From: Zhihao Cheng <[email protected]>

[ Upstream commit 81423c78551654953d746250f1721300b470be0e ]

When inodes with extended attributes are evicted, xent is not freed in one exit branch.

Fixes 9ca2d732644484488db3112 ("ubifs: Limit number of xattrs per inode")
---
 fs/ubifs/journal.c | 1 +
 1 file changed, 1 insertion(+)
fs/ubifs/journal.c +1 -0
index a6ae2428e4c96..5f2ac5ef0891e 100644
@@ -906,6 +906,7 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode)
 				ubifs_err(c, "dead directory entry '%s', error %d",
 					  xent->name, err);
 				ubifs_ro_mode(c, err);
+				kfree(xent);
 				goto out_release;
 			}
 			ubifs_assert(c, ubifs_inode(xino)->xattr);
Signature · 1 line
2.25.1
author maintainer
#210 lore raw

PATCH 210/388 PCI: Use ioremap(), not phys_to_virt() for platform ROM

In reply to Greg Kroah-Hartman

From: Mikel Rychliski <[email protected]>

[ Upstream commit 72e0ef0e5f067fd991f702f0b2635d911d0cf208 ]

On some EFI systems, the video BIOS is provided by the EFI firmware. The boot stub code stores the physical address of the ROM image in pdev->rom. Currently we attempt to access this pointer using phys_to_virt(), which doesn't work with CONFIG_HIGHMEM.

On these systems, attempting to load the radeon module on a x86_32 kernel can result in the following:

  BUG: unable to handle page fault for address: 3e8ed03c
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  *pde = 00000000
  Oops: 0000 [#1] PREEMPT SMP
  CPU: 0 PID: 317 Comm: systemd-udevd Not tainted 5.6.0-rc3-next-20200228 #2
  Hardware name: Apple Computer, Inc. MacPro1,1/Mac-F4208DC8, BIOS     MP11.88Z.005C.B08.0707021221 07/02/07
  EIP: radeon_get_bios+0x5ed/0xe50 [radeon]
  Code: 00 00 84 c0 0f 85 12 fd ff ff c7 87 64 01 00 00 00 00 00 00 8b 47 08 8b 55 b0 e8 1e 83 e1 d6 85 c0 74 1a 8b 55 c0 85 d2 74 13 <80> 38 55 75 0e 80 78 01 aa 0f 84 a4 03 00 00 8d 74 26 00 68 dc 06
  EAX: 3e8ed03c EBX: 00000000 ECX: 3e8ed03c EDX: 00010000
  ESI: 00040000 EDI: eec04000 EBP: eef3fc60 ESP: eef3fbe0
  DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010206
  CR0: 80050033 CR2: 3e8ed03c CR3: 2ec77000 CR4: 000006d0
  Call Trace:
   r520_init+0x26/0x240 [radeon]
   radeon_device_init+0x533/0xa50 [radeon]
   radeon_driver_load_kms+0x80/0x220 [radeon]
   drm_dev_register+0xa7/0x180 [drm]
   radeon_pci_probe+0x10f/0x1a0 [radeon]
   pci_device_probe+0xd4/0x140

Fix the issue by updating all drivers which can access a platform provided ROM. Instead of calling the helper function pci_platform_rom() which uses phys_to_virt(), call ioremap() directly on the pdev->rom.

radeon_read_platform_bios() previously directly accessed an __iomem pointer. Avoid this by calling memcpy_fromio() instead of kmemdup().

pci_platform_rom() now has no remaining callers, so remove it.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c      | 31 +++++++++++--------
 .../drm/nouveau/nvkm/subdev/bios/shadowpci.c  | 17 ++++++++--
 drivers/gpu/drm/radeon/radeon_bios.c          | 30 +++++++++++-------
 drivers/pci/rom.c                             | 17 ----------
 include/linux/pci.h                           |  1 -
 5 files changed, 52 insertions(+), 44 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +18 -13
index 50dff69a0f6e3..b1172d93c99c3 100644
@@ -192,30 +192,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev)
 
 static bool amdgpu_read_platform_bios(struct amdgpu_device *adev)
 {
-	uint8_t __iomem *bios;
-	size_t size;
+	phys_addr_t rom = adev->pdev->rom;
+	size_t romlen = adev->pdev->romlen;
+	void __iomem *bios;
 
 	adev->bios = NULL;
 
-	bios = pci_platform_rom(adev->pdev, &size);
-	if (!bios) {
+	if (!rom || romlen == 0)
 		return false;
-	}
 
-	adev->bios = kzalloc(size, GFP_KERNEL);
-	if (adev->bios == NULL)
+	adev->bios = kzalloc(romlen, GFP_KERNEL);
+	if (!adev->bios)
 		return false;
 
-	memcpy_fromio(adev->bios, bios, size);
+	bios = ioremap(rom, romlen);
+	if (!bios)
+		goto free_bios;
 
-	if (!check_atom_bios(adev->bios, size)) {
-		kfree(adev->bios);
-		return false;
-	}
+	memcpy_fromio(adev->bios, bios, romlen);
+	iounmap(bios);
 
-	adev->bios_size = size;
+	if (!check_atom_bios(adev->bios, romlen))
+		goto free_bios;
+
+	adev->bios_size = romlen;
 
 	return true;
+free_bios:
+	kfree(adev->bios);
+	return false;
 }
 
 #ifdef CONFIG_ACPI
drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c +15 -2
index 9b91da09dc5f8..8d9812a51ef63 100644
@@ -101,9 +101,13 @@ platform_init(struct nvkm_bios *bios, const char *name)
 	else
 		return ERR_PTR(-ENODEV);
 
+	if (!pdev->rom || pdev->romlen == 0)
+		return ERR_PTR(-ENODEV);
+
 	if ((priv = kmalloc(sizeof(*priv), GFP_KERNEL))) {
+		priv->size = pdev->romlen;
 		if (ret = -ENODEV,
-		    (priv->rom = pci_platform_rom(pdev, &priv->size)))
+		    (priv->rom = ioremap(pdev->rom, pdev->romlen)))
 			return priv;
 		kfree(priv);
 	}
@@ -111,11 +115,20 @@ platform_init(struct nvkm_bios *bios, const char *name)
 	return ERR_PTR(ret);
 }
 
+static void
+platform_fini(void *data)
+{
+	struct priv *priv = data;
+
+	iounmap(priv->rom);
+	kfree(priv);
+}
+
 const struct nvbios_source
 nvbios_platform = {
 	.name = "PLATFORM",
 	.init = platform_init,
-	.fini = (void(*)(void *))kfree,
+	.fini = platform_fini,
 	.read = pcirom_read,
 	.rw = true,
 };
drivers/gpu/drm/radeon/radeon_bios.c +19 -11
index 4d1490fbb0750..756a50e8aff20 100644
@@ -108,25 +108,33 @@ static bool radeon_read_bios(struct radeon_device *rdev)
 
 static bool radeon_read_platform_bios(struct radeon_device *rdev)
 {
-	uint8_t __iomem *bios;
-	size_t size;
+	phys_addr_t rom = rdev->pdev->rom;
+	size_t romlen = rdev->pdev->romlen;
+	void __iomem *bios;
 
 	rdev->bios = NULL;
 
-	bios = pci_platform_rom(rdev->pdev, &size);
-	if (!bios) {
+	if (!rom || romlen == 0)
 		return false;
-	}
 
-	if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) {
+	rdev->bios = kzalloc(romlen, GFP_KERNEL);
+	if (!rdev->bios)
 		return false;
-	}
-	rdev->bios = kmemdup(bios, size, GFP_KERNEL);
-	if (rdev->bios == NULL) {
-		return false;
-	}
+
+	bios = ioremap(rom, romlen);
+	if (!bios)
+		goto free_bios;
+
+	memcpy_fromio(rdev->bios, bios, romlen);
+	iounmap(bios);
+
+	if (rdev->bios[0] != 0x55 || rdev->bios[1] != 0xaa)
+		goto free_bios;
 
 	return true;
+free_bios:
+	kfree(rdev->bios);
+	return false;
 }
 
 #ifdef CONFIG_ACPI
drivers/pci/rom.c +0 -17
index 137bf0cee897c..8fc9a4e911e3a 100644
@@ -195,20 +195,3 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
 		pci_disable_rom(pdev);
 }
 EXPORT_SYMBOL(pci_unmap_rom);
-
-/**
- * pci_platform_rom - provides a pointer to any ROM image provided by the
- * platform
- * @pdev: pointer to pci device struct
- * @size: pointer to receive size of pci window over ROM
- */
-void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size)
-{
-	if (pdev->rom && pdev->romlen) {
-		*size = pdev->romlen;
-		return phys_to_virt((phys_addr_t)pdev->rom);
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL(pci_platform_rom);
include/linux/pci.h +0 -1
index f39f22f9ee474..e92bd9b32f369 100644
@@ -1216,7 +1216,6 @@ int pci_enable_rom(struct pci_dev *pdev);
 void pci_disable_rom(struct pci_dev *pdev);
 void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
 void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
-void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);
 
 /* Power management related routines */
 int pci_save_state(struct pci_dev *dev);
Signature · 1 line
2.25.1
author maintainer
#208 lore raw

PATCH 208/388 svcrdma: Fix leak of transport addresses

In reply to Greg Kroah-Hartman

From: Chuck Lever <[email protected]>

[ Upstream commit 1a33d8a284b1e85e03b8c7b1ea8fb985fccd1d71 ]

Kernel memory leak detected:

unreferenced object 0xffff888849cdf480 (size 8):
comm "kworker/u8:3", pid 2086, jiffies 4297898756 (age 4269.856s) hex dump (first 8 bytes):

    30 00 cd 49 88 88 ff ff                          0..I....
  backtrace:
    [<00000000acfc370b>] __kmalloc_track_caller+0x137/0x183
    [<00000000a2724354>] kstrdup+0x2b/0x43
    [<0000000082964f84>] xprt_rdma_format_addresses+0x114/0x17d [rpcrdma]
    [<00000000dfa6ed00>] xprt_setup_rdma_bc+0xc0/0x10c [rpcrdma]
    [<0000000073051a83>] xprt_create_transport+0x3f/0x1a0 [sunrpc]
    [<0000000053531a8e>] rpc_create+0x118/0x1cd [sunrpc]
    [<000000003a51b5f8>] setup_callback_client+0x1a5/0x27d [nfsd]
    [<000000001bd410af>] nfsd4_process_cb_update.isra.7+0x16c/0x1ac [nfsd]
    [<000000007f4bbd56>] nfsd4_run_cb_work+0x4c/0xbd [nfsd]
    [<0000000055c5586b>] process_one_work+0x1b2/0x2fe
    [<00000000b1e3e8ef>] worker_thread+0x1a6/0x25a
    [<000000005205fb78>] kthread+0xf6/0xfb
    [<000000006d2dc057>] ret_from_fork+0x3a/0x50

Introduce a call to xprt_rdma_free_addresses() similar to the way that the TCP backchannel releases a transport's peer address strings.

Fixes 5d252f90a800 ("svcrdma: Add class for RDMA backwards direction transport")
---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 1 +
 1 file changed, 1 insertion(+)
net/sunrpc/xprtrdma/svc_rdma_backchannel.c +1 -0
index cf80394b2db33..325eef1f85824 100644
@@ -252,6 +252,7 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
 
+	xprt_rdma_free_addresses(xprt);
 	xprt_free(xprt);
 }
 
Signature · 1 line
2.25.1
author maintainer
#193 lore raw

PATCH 193/388 exec: Fix a deadlock in strace

In reply to Greg Kroah-Hartman

From: Bernd Edlinger <[email protected]>

[ Upstream commit 3e74fabd39710ee29fa25618d2c2b40cfa7d76c7 ]

This fixes a deadlock in the tracer when tracing a multi-threaded application that calls execve while more than one thread are running.

I observed that when running strace on the gcc test suite, it always blocks after a while, when expect calls execve, because other threads have to be terminated. They send ptrace events, but the strace is no longer able to respond, since it is blocked in vm_access.

The deadlock is always happening when strace needs to access the tracees process mmap, while another thread in the tracee starts to execve a child process, but that cannot continue until the PTRACE_EVENT_EXIT is handled and the WIFEXITED event is received:

strace D 0 30614 30584 0x00000000

Call Trace:
__schedule+0x3ce/0x6e0
schedule+0x5c/0xd0
schedule_preempt_disabled+0x15/0x20
__mutex_lock.isra.13+0x1ec/0x520
__mutex_lock_killable_slowpath+0x13/0x20
mutex_lock_killable+0x28/0x30
mm_access+0x27/0xa0
process_vm_rw_core.isra.3+0xff/0x550
process_vm_rw+0xdd/0xf0
__x64_sys_process_vm_readv+0x31/0x40
do_syscall_64+0x64/0x220
entry_SYSCALL_64_after_hwframe+0x44/0xa9

expect D 0 31933 30876 0x80004003

Call Trace:
__schedule+0x3ce/0x6e0
schedule+0x5c/0xd0
flush_old_exec+0xc4/0x770
load_elf_binary+0x35a/0x16c0
search_binary_handler+0x97/0x1d0
__do_execve_file.isra.40+0x5d4/0x8a0
__x64_sys_execve+0x49/0x60
do_syscall_64+0x64/0x220
entry_SYSCALL_64_after_hwframe+0x44/0xa9

This changes mm_access to use the new exec_update_mutex instead of cred_guard_mutex.

This patch is based on the following patch by Eric W. Biederman:
"[PATCH 0/5] Infrastructure to allow fixing exec deadlocks"

---
 kernel/fork.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/fork.c +2 -2
index cfdc57658ad88..594272569a80f 100644
@@ -1221,7 +1221,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 	struct mm_struct *mm;
 	int err;
 
-	err =  mutex_lock_killable(&task->signal->cred_guard_mutex);
+	err =  mutex_lock_killable(&task->signal->exec_update_mutex);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1231,7 +1231,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
 		mmput(mm);
 		mm = ERR_PTR(-EACCES);
 	}
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&task->signal->exec_update_mutex);
 
 	return mm;
 }
Signature · 1 line
2.25.1
author maintainer
#190 lore raw

PATCH 190/388 cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_work_fn

In reply to Greg Kroah-Hartman

From: Pratik Rajesh Sampat <[email protected]>

[ Upstream commit d95fe371ecd28901f11256c610b988ed44e36ee2 ]

The patch avoids allocating cpufreq_policy on stack hence fixing frame size overflow in 'powernv_cpufreq_work_fn'

Fixes 227942809b52 ("cpufreq: powernv: Restore cpu frequency to policy->cur on unthrottling")
---
 drivers/cpufreq/powernv-cpufreq.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)
drivers/cpufreq/powernv-cpufreq.c +8 -5
index 1806b1da43665..3a2f022f6bde2 100644
@@ -902,6 +902,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {
 void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
+	struct cpufreq_policy *policy;
 	unsigned int cpu;
 	cpumask_t mask;
 
@@ -916,12 +917,14 @@ void powernv_cpufreq_work_fn(struct work_struct *work)
 	chip->restore = false;
 	for_each_cpu(cpu, &mask) {
 		int index;
-		struct cpufreq_policy policy;
 
-		cpufreq_get_policy(&policy, cpu);
-		index = cpufreq_table_find_index_c(&policy, policy.cur);
-		powernv_cpufreq_target_index(&policy, index);
-		cpumask_andnot(&mask, &mask, policy.cpus);
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy)
+			continue;
+		index = cpufreq_table_find_index_c(policy, policy->cur);
+		powernv_cpufreq_target_index(policy, index);
+		cpumask_andnot(&mask, &mask, policy->cpus);
+		cpufreq_cpu_put(policy);
 	}
 out:
 	put_online_cpus();
Signature · 1 line
2.25.1
author maintainer
#226 lore raw

PATCH 226/388 drm/amdgpu/sriov add amdgpu_amdkfd_pre_reset in gpu reset

In reply to Greg Kroah-Hartman

From: Jack Zhang <[email protected]>

[ Upstream commit 04bef61e5da18c2b301c629a209ccdba4d4c6fbb ]

kfd_pre_reset will free mem_objs allocated by kfd_gtt_sa_allocate

Without this change, sriov tdr code path will never free those allocated memories and get memory leak.

v2:add a bugfix for kiq ring test fail

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c  | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c         | 2 ++
 3 files changed, 8 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +3 -0
index d10f483f5e273..ce30d4e8bf25f 100644
@@ -644,6 +644,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v10_compute_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 #if 0
 	unsigned long flags;
 	int retry;
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +3 -0
index e262f2ac07a35..92754cfb98086 100644
@@ -540,6 +540,9 @@ int kgd_gfx_v9_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (amdgpu_sriov_vf(adev) && adev->in_gpu_reset)
+		return 0;
+
 	if (adev->in_gpu_reset)
 		return -EIO;
 
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2 -0
index 5e1dce4241547..4105fbf571674 100644
@@ -3466,6 +3466,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
Signature · 1 line
2.25.1
author maintainer
#159 lore raw

PATCH 159/388 perf cs-etm: Correct synthesizing instruction samples

In reply to Greg Kroah-Hartman

From: Leo Yan <[email protected]>

[ Upstream commit c9f5baa136777b2c982f6f7a90c9da69a88be148 ]

When 'etm->instructions_sample_period' is less than 'tidq->period_instructions', the function cs_etm__sample() cannot handle this case properly with its logic.

Let's see below flow as an example:

- If we set itrace option '--itrace=i4', then function cs_etm__sample() has variables with initialized values:

tidq->period_instructions = 0
etm->instructions_sample_period = 4

- When the first packet is coming:

packet->instr_count = 10; the number of instructions executed in this packet is 10, thus update period_instructions as below:

tidq->period_instructions = 0 + 10 = 10
instrs_over = 10 - 4 = 6
offset = 10 - 6 - 1 = 3
tidq->period_instructions = instrs_over = 6

- When the second packet is coming:

packet->instr_count = 10; in the second pass, assume 10 instructions in the trace sample again:

tidq->period_instructions = 6 + 10 = 16 instrs_over = 16 - 4 = 12
offset = 10 - 12 - 1 = -3 -> the negative value tidq->period_instructions = instrs_over = 12

So after handle these two packets, there have below issues:

The first issue is that cs_etm__instr_addr() returns the address within the current trace sample of the instruction related to offset, so the offset is supposed to be always unsigned value. But in fact, function cs_etm__sample() might calculate a negative offset value (in handling the second packet, the offset is -3) and pass to cs_etm__instr_addr() with u64 type with a big positive integer.

The second issue is it only synthesizes 2 samples for sample period = 4. In theory, every packet has 10 instructions so the two packets have total 20 instructions, 20 instructions should generate 5 samples (4 x 5 = 20). This is because cs_etm__sample() only calls once cs_etm__synth_instruction_sample() to generate instruction sample per range packet.

This patch fixes the logic in function cs_etm__sample(); the basic idea for handling coming packet is:

- To synthesize the first instruction sample, it combines the left instructions from the previous packet and the head of the new packet; then generate continuous samples with sample period;
- At the tail of the new packet, if it has the rest instructions, these instructions will be left for the sequential sample.

---
 tools/perf/util/cs-etm.c | 87 ++++++++++++++++++++++++++++++++--------
 1 file changed, 70 insertions(+), 17 deletions(-)
tools/perf/util/cs-etm.c +70 -17
index 38298cbb07524..451eee24165ee 100644
@@ -1359,9 +1359,12 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
-	u64 instrs_executed = tidq->packet->instr_count;
+	u64 instrs_prev;
 
-	tidq->period_instructions += instrs_executed;
+	/* Get instructions remainder from previous packet */
+	instrs_prev = tidq->period_instructions;
+
+	tidq->period_instructions += tidq->packet->instr_count;
 
 	/*
 	 * Record a branch when the last instruction in
@@ -1379,26 +1382,76 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
-		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = tidq->period_instructions -
-			etm->instructions_sample_period;
+		/*
+		 * Below diagram demonstrates the instruction samples
+		 * generation flows:
+		 *
+		 *    Instrs     Instrs       Instrs       Instrs
+		 *   Sample(n)  Sample(n+1)  Sample(n+2)  Sample(n+3)
+		 *    |            |            |            |
+		 *    V            V            V            V
+		 *   --------------------------------------------------
+		 *            ^                                  ^
+		 *            |                                  |
+		 *         Period                             Period
+		 *    instructions(Pi)                   instructions(Pi')
+		 *
+		 *            |                                  |
+		 *            \---------------- -----------------/
+		 *                             V
+		 *                 tidq->packet->instr_count
+		 *
+		 * Instrs Sample(n...) are the synthesised samples occurring
+		 * every etm->instructions_sample_period instructions - as
+		 * defined on the perf command line.  Sample(n) is being the
+		 * last sample before the current etm packet, n+1 to n+3
+		 * samples are generated from the current etm packet.
+		 *
+		 * tidq->packet->instr_count represents the number of
+		 * instructions in the current etm packet.
+		 *
+		 * Period instructions (Pi) contains the the number of
+		 * instructions executed after the sample point(n) from the
+		 * previous etm packet.  This will always be less than
+		 * etm->instructions_sample_period.
+		 *
+		 * When generate new samples, it combines with two parts
+		 * instructions, one is the tail of the old packet and another
+		 * is the head of the new coming packet, to generate
+		 * sample(n+1); sample(n+2) and sample(n+3) consume the
+		 * instructions with sample period.  After sample(n+3), the rest
+		 * instructions will be used by later packet and it is assigned
+		 * to tidq->period_instructions for next round calculation.
+		 */
 
 		/*
-		 * Calculate the address of the sampled instruction (-1 as
-		 * sample is reported as though instruction has just been
-		 * executed, but PC has not advanced to next instruction)
+		 * Get the initial offset into the current packet instructions;
+		 * entry conditions ensure that instrs_prev is less than
+		 * etm->instructions_sample_period.
 		 */
-		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
-					      tidq->packet, offset);
+		u64 offset = etm->instructions_sample_period - instrs_prev;
+		u64 addr;
 
-		ret = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr, etm->instructions_sample_period);
-		if (ret)
-			return ret;
+		while (tidq->period_instructions >=
+				etm->instructions_sample_period) {
+			/*
+			 * Calculate the address of the sampled instruction (-1
+			 * as sample is reported as though instruction has just
+			 * been executed, but PC has not advanced to next
+			 * instruction)
+			 */
+			addr = cs_etm__instr_addr(etmq, trace_chan_id,
+						  tidq->packet, offset - 1);
+			ret = cs_etm__synth_instruction_sample(
+				etmq, tidq, addr,
+				etm->instructions_sample_period);
+			if (ret)
+				return ret;
 
-		/* Carry remaining instructions into next sample period */
-		tidq->period_instructions = instrs_over;
+			offset += etm->instructions_sample_period;
+			tidq->period_instructions -=
+				etm->instructions_sample_period;
+		}
 	}
 
 	if (etm->sample_branches) {
Signature · 9 lines
2.25.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
author maintainer
#192 lore raw

PATCH 192/388 exec: Add exec_update_mutex to replace cred_guard_mutex

In reply to Greg Kroah-Hartman

From: Eric W. Biederman <[email protected]>

[ Upstream commit eea9673250db4e854e9998ef9da6d4584857f0ea ]

The cred_guard_mutex is problematic as it is held over possibly indefinite waits for userspace. The possible indefinite waits for userspace that I have identified are: The cred_guard_mutex is held in PTRACE_EVENT_EXIT waiting for the tracer. The cred_guard_mutex is held over "put_user(0, tsk->clear_child_tid)" in exit_mm(). The cred_guard_mutex is held over "get_user(futex_offset, ...") in exit_robust_list. The cred_guard_mutex held over copy_strings.

The functions get_user and put_user can trigger a page fault which can potentially wait indefinitely in the case of userfaultfd or if userspace implements part of the page fault path.

In any of those cases the userspace process that the kernel is waiting for might make a different system call that winds up taking the cred_guard_mutex and result in deadlock.

Holding a mutex over any of those possibly indefinite waits for userspace does not appear necessary. Add exec_update_mutex that will just cover updating the process during exec where the permissions and the objects pointed to by the task struct may be out of sync.

The plan is to switch the users of cred_guard_mutex to exec_update_mutex one by one. This lets us move forward while still being careful and not introducing any regressions.

Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")

---
 fs/exec.c                    | 22 +++++++++++++++++++---
 include/linux/binfmts.h      |  8 +++++++-
 include/linux/sched/signal.h |  9 ++++++++-
 init/init_task.c             |  1 +
 kernel/fork.c                |  1 +
 5 files changed, 36 insertions(+), 5 deletions(-)
fs/exec.c +19 -3
index d62cd1d71098f..de833553ae27d 100644
@@ -1007,16 +1007,26 @@ ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 }
 EXPORT_SYMBOL(read_code);
 
+/*
+ * Maps the mm_struct mm into the current task struct.
+ * On success, this function returns with the mutex
+ * exec_update_mutex locked.
+ */
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
 	struct mm_struct *old_mm, *active_mm;
+	int ret;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
 
+	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
+	if (ret)
+		return ret;
+
 	if (old_mm) {
 		sync_mm_rss(old_mm);
 		/*
@@ -1028,9 +1038,11 @@ static int exec_mmap(struct mm_struct *mm)
 		down_read(&old_mm->mmap_sem);
 		if (unlikely(old_mm->core_state)) {
 			up_read(&old_mm->mmap_sem);
+			mutex_unlock(&tsk->signal->exec_update_mutex);
 			return -EINTR;
 		}
 	}
+
 	task_lock(tsk);
 	active_mm = tsk->active_mm;
 	membarrier_exec_mmap(mm);
@@ -1285,11 +1297,12 @@ int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	/*
-	 * After clearing bprm->mm (to mark that current is using the
-	 * prepared mm now), we have nothing left of the original
+	 * After setting bprm->called_exec_mmap (to mark that current is
+	 * using the prepared mm now), we have nothing left of the original
 	 * process. If anything from here on returns an error, the check
 	 * in search_binary_handler() will SEGV current.
 	 */
+	bprm->called_exec_mmap = 1;
 	bprm->mm = NULL;
 
 	set_fs(USER_DS);
@@ -1423,6 +1436,8 @@ static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		if (bprm->called_exec_mmap)
+			mutex_unlock(&current->signal->exec_update_mutex);
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1472,6 +1487,7 @@ void install_exec_creds(struct linux_binprm *bprm)
 	 * credentials; any time after this it may be unlocked.
 	 */
 	security_bprm_committed_creds(bprm);
+	mutex_unlock(&current->signal->exec_update_mutex);
 	mutex_unlock(&current->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
@@ -1663,7 +1679,7 @@ int search_binary_handler(struct linux_binprm *bprm)
 
 		read_lock(&binfmt_lock);
 		put_binfmt(fmt);
-		if (retval < 0 && !bprm->mm) {
+		if (retval < 0 && bprm->called_exec_mmap) {
 			/* we got to flush_old_exec() and failed after it */
 			read_unlock(&binfmt_lock);
 			force_sigsegv(SIGSEGV);
include/linux/binfmts.h +7 -1
index b40fc633f3be6..a345d9fed3d8d 100644
@@ -44,7 +44,13 @@ struct linux_binprm {
 		 * exec has happened. Used to sanitize execution environment
 		 * and to set AT_SECURE auxv for glibc.
 		 */
-		secureexec:1;
+		secureexec:1,
+		/*
+		 * Set by flush_old_exec, when exec_mmap has been called.
+		 * This is past the point of no return, when the
+		 * exec_update_mutex has been taken.
+		 */
+		called_exec_mmap:1;
 #ifdef __alpha__
 	unsigned int taso:1;
 #endif
include/linux/sched/signal.h +8 -1
index 88050259c466e..a29df79540ce6 100644
@@ -224,7 +224,14 @@ struct signal_struct {
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
-					 * (notably. ptrace) */
+					 * (notably. ptrace)
+					 * Deprecated do not use in new code.
+					 * Use exec_update_mutex instead.
+					 */
+	struct mutex exec_update_mutex;	/* Held while task_struct is being
+					 * updated during exec, and may have
+					 * inconsistent permissions.
+					 */
 } __randomize_layout;
 
 /*
init/init_task.c +1 -0
index 9e5cbe5eab7b1..bd403ed3e4184 100644
@@ -26,6 +26,7 @@ static struct signal_struct init_signals = {
 	.multiprocess	= HLIST_HEAD_INIT,
 	.rlim		= INIT_RLIMITS,
 	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+	.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
 #ifdef CONFIG_POSIX_TIMERS
 	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
 	.cputimer	= {
kernel/fork.c +1 -0
index 9180f4416dbab..cfdc57658ad88 100644
@@ -1586,6 +1586,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
 	mutex_init(&sig->cred_guard_mutex);
+	mutex_init(&sig->exec_update_mutex);
 
 	return 0;
 }
Signature · 1 line
2.25.1
author maintainer
#184 lore raw

PATCH 184/388 serial: 8250_port: Dont service RX FIFO if throttled

In reply to Greg Kroah-Hartman

From: Vignesh Raghavendra <[email protected]>

[ Upstream commit f19c3f6c8109b8bab000afd35580929958e087a9 ]

When port's throttle callback is called, it should stop pushing any more data into TTY buffer to avoid buffer overflow. This means driver has to stop HW from receiving more data and assert the HW flow control. For UARTs with auto HW flow control (such as 8250_omap) manual assertion of flow control line is not possible and only way is to allow RX FIFO to fill up, thus trigger auto HW flow control logic.

Therefore make sure that 8250 generic IRQ handler does not drain data when port is stopped (i.e UART_LSR_DR is unset in read_status_mask). Not servicing, RX FIFO would trigger auto HW flow control when FIFO occupancy reaches preset threshold, thus halting RX.
Since, error conditions in UART_LSR register are cleared just by reading the register, data has to be drained in case there are FIFO errors, else error information will lost.

---
 drivers/tty/serial/8250/8250_port.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/tty/serial/8250/8250_port.c +15 -1
index 90f09ed6e5ad3..5b673077639ba 100644
@@ -1816,6 +1816,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 	unsigned char status;
 	unsigned long flags;
 	struct uart_8250_port *up = up_to_u8250p(port);
+	bool skip_rx = false;
 
 	if (iir & UART_IIR_NO_INT)
 		return 0;
@@ -1824,7 +1825,20 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 
 	status = serial_port_in(port, UART_LSR);
 
-	if (status & (UART_LSR_DR | UART_LSR_BI)) {
+	/*
+	 * If port is stopped and there are no error conditions in the
+	 * FIFO, then don't drain the FIFO, as this may lead to TTY buffer
+	 * overflow. Not servicing, RX FIFO would trigger auto HW flow
+	 * control when FIFO occupancy reaches preset threshold, thus
+	 * halting RX. This only works when auto HW flow control is
+	 * available.
+	 */
+	if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) &&
+	    (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) &&
+	    !(port->read_status_mask & UART_LSR_DR))
+		skip_rx = true;
+
+	if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) {
 		if (!up->dma || handle_rx_dma(up, iir))
 			status = serial8250_rx_chars(up, status);
 	}
Signature · 1 line
2.25.1
author maintainer
#158 lore raw

PATCH 158/388 perf cs-etm: Swap packets for instruction samples

In reply to Greg Kroah-Hartman

From: Leo Yan <[email protected]>

[ Upstream commit d01751563caf0dec7be36f81de77cc0197b77e59 ]

If use option '--itrace=iNNN' with Arm CoreSight trace data, perf tool fails inject instruction samples; the root cause is the packets are only swapped for branch samples and last branches but not for instruction samples, so the new coming packets cannot be properly handled for only synthesizing instruction samples.

To fix this issue, this patch refactors the code with a new function cs_etm__packet_swap() which is used to swap packets and adds the condition for instruction samples.

---
 tools/perf/util/cs-etm.c | 39 +++++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 20 deletions(-)
tools/perf/util/cs-etm.c +19 -20
index f5f855fff412e..38298cbb07524 100644
@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
 	return NULL;
 }
 
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+				struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *tmp;
+
+	if (etm->sample_branches || etm->synth_opts.last_branch ||
+	    etm->sample_instructions) {
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
+	}
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -1340,7 +1357,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
 	u64 instrs_executed = tidq->packet->instr_count;
@@ -1404,15 +1420,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return 0;
 }
@@ -1441,7 +1449,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 
 	/* Handle start tracing packet */
 	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1476,15 +1483,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	}
 
 swap_packet:
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return err;
 }
Signature · 9 lines
2.25.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
author maintainer
#217 lore raw

PATCH 217/388 drm/amdgpu/vcn2.0: stall DPG when WPTR/RPTR reset

In reply to Greg Kroah-Hartman

From: James Zhu <[email protected]>

[ Upstream commit ef563ff403404ef2f234abe79bdd9f04ab6481c9 ]

Add vcn dpg harware synchronization to fix race condition issue between vcn driver and hardware.

---
 drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +16 -0
index 36ad0c0e8efbc..cd2cbe760e883 100644
@@ -1026,6 +1026,10 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_CNTL, tmp);
 
+	/* Stall DPG before WPTR/RPTR reset */
+	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+		UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+		~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 	/* set the write pointer delay */
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR_CNTL, 0);
 
@@ -1048,6 +1052,9 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 		lower_32_bits(ring->wptr));
 
+	/* Unstall DPG */
+	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+		0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 	return 0;
 }
 
@@ -1357,8 +1364,13 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
 					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
 					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
 
+				/* Stall DPG before WPTR/RPTR reset */
+				WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+					   UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
+					   ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 				/* Restore */
 				ring = &adev->vcn.inst->ring_enc[0];
+				ring->wptr = 0;
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE, ring->ring_size / 4);
@@ -1366,6 +1378,7 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
 				WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
 
 				ring = &adev->vcn.inst->ring_enc[1];
+				ring->wptr = 0;
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_LO2, ring->gpu_addr);
 				WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
@@ -1374,6 +1387,9 @@ static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
 
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 					   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
+				/* Unstall DPG */
+				WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS),
+					   0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
 
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
 					   UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
Signature · 1 line
2.25.1
author maintainer
#189 lore raw

PATCH 189/388 net: axienet: Propagate failure of DMA descriptor setup

In reply to Greg Kroah-Hartman

From: Andre Przywara <[email protected]>

[ Upstream commit ee44d0b78839b21591501424fd3cb3648cc803b5 ]

When we fail allocating the DMA buffers in axienet_dma_bd_init(), we report this error, but carry on with initialisation nevertheless.

This leads to a kernel panic when the driver later wants to send a packet, as it uses uninitialised data structures.

Make the axienet_device_reset() routine return an error value, as it contains the DMA buffer initialisation. Make sure we propagate the error up the chain and eventually fail the driver initialisation, to avoid relying on non-initialised buffers.

---
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 26 ++++++++++++++-----
 1 file changed, 19 insertions(+), 7 deletions(-)
drivers/net/ethernet/xilinx/xilinx_axienet_main.c +19 -7
index 345a795666e92..bb6e52f3bdf9b 100644
@@ -437,9 +437,10 @@ static void axienet_setoptions(struct net_device *ndev, u32 options)
 	lp->options |= options;
 }
 
-static void __axienet_device_reset(struct axienet_local *lp)
+static int __axienet_device_reset(struct axienet_local *lp)
 {
 	u32 timeout;
+
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
 	 * commands/transfers will be flushed or completed during this
@@ -455,9 +456,11 @@ static void __axienet_device_reset(struct axienet_local *lp)
 		if (--timeout == 0) {
 			netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
 				   __func__);
-			break;
+			return -ETIMEDOUT;
 		}
 	}
+
+	return 0;
 }
 
 /**
@@ -470,13 +473,17 @@ static void __axienet_device_reset(struct axienet_local *lp)
  * areconnected to Axi Ethernet reset lines, this in turn resets the Axi
  * Ethernet core. No separate hardware reset is done for the Axi Ethernet
  * core.
+ * Returns 0 on success or a negative error number otherwise.
  */
-static void axienet_device_reset(struct net_device *ndev)
+static int axienet_device_reset(struct net_device *ndev)
 {
 	u32 axienet_status;
 	struct axienet_local *lp = netdev_priv(ndev);
+	int ret;
 
-	__axienet_device_reset(lp);
+	ret = __axienet_device_reset(lp);
+	if (ret)
+		return ret;
 
 	lp->max_frm_size = XAE_MAX_VLAN_FRAME_SIZE;
 	lp->options |= XAE_OPTION_VLAN;
@@ -491,9 +498,11 @@ static void axienet_device_reset(struct net_device *ndev)
 			lp->options |= XAE_OPTION_JUMBO;
 	}
 
-	if (axienet_dma_bd_init(ndev)) {
+	ret = axienet_dma_bd_init(ndev);
+	if (ret) {
 		netdev_err(ndev, "%s: descriptor allocation failed\n",
 			   __func__);
+		return ret;
 	}
 
 	axienet_status = axienet_ior(lp, XAE_RCW1_OFFSET);
@@ -518,6 +527,8 @@ static void axienet_device_reset(struct net_device *ndev)
 	axienet_setoptions(ndev, lp->options);
 
 	netif_trans_update(ndev);
+
+	return 0;
 }
 
 /**
@@ -921,8 +932,9 @@ static int axienet_open(struct net_device *ndev)
 	 */
 	mutex_lock(&lp->mii_bus->mdio_lock);
 	axienet_mdio_disable(lp);
-	axienet_device_reset(ndev);
-	ret = axienet_mdio_enable(lp);
+	ret = axienet_device_reset(ndev);
+	if (ret == 0)
+		ret = axienet_mdio_enable(lp);
 	mutex_unlock(&lp->mii_bus->mdio_lock);
 	if (ret < 0)
 		return ret;
Signature · 1 line
2.25.1
author maintainer
#191 lore raw

PATCH 191/388 tools: gpio-hammer: Avoid potential overflow in main

In reply to Greg Kroah-Hartman

From: Gabriel Ravier <[email protected]>

[ Upstream commit d1ee7e1f5c9191afb69ce46cc7752e4257340a31 ]

If '-o' was used more than 64 times in a single invocation of gpio-hammer, this could lead to an overflow of the 'lines' array. This commit fixes this by avoiding the overflow and giving a proper diagnostic back to the user

---
 tools/gpio/gpio-hammer.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)
tools/gpio/gpio-hammer.c +16 -1
index 0e0060a6eb346..083399d276e4e 100644
@@ -135,7 +135,14 @@ int main(int argc, char **argv)
 			device_name = optarg;
 			break;
 		case 'o':
-			lines[i] = strtoul(optarg, NULL, 10);
+			/*
+			 * Avoid overflow. Do not immediately error, we want to
+			 * be able to accurately report on the amount of times
+			 * '-o' was given to give an accurate error message
+			 */
+			if (i < GPIOHANDLES_MAX)
+				lines[i] = strtoul(optarg, NULL, 10);
+
 			i++;
 			break;
 		case '?':
@@ -143,6 +150,14 @@ int main(int argc, char **argv)
 			return -1;
 		}
 	}
+
+	if (i >= GPIOHANDLES_MAX) {
+		fprintf(stderr,
+			"Only %d occurences of '-o' are allowed, %d were found\n",
+			GPIOHANDLES_MAX, i + 1);
+		return -1;
+	}
+
 	nlines = i;
 
 	if (!device_name || !nlines) {
Signature · 1 line
2.25.1
author maintainer
#218 lore raw

PATCH 218/388 powerpc/perf: Implement a global lock to avoid races between trace, core and thread imc events.

In reply to Greg Kroah-Hartman

From: Anju T Sudhakar <[email protected]>

[ Upstream commit a36e8ba60b991d563677227f172db69e030797e6 ]

IMC(In-memory Collection Counters) does performance monitoring in two different modes, i.e accumulation mode(core-imc and thread-imc events), and trace mode(trace-imc events). A cpu thread can either be in accumulation-mode or trace-mode at a time and this is done via the LDBAR register in POWER architecture. The current design does not address the races between thread-imc and trace-imc events.

Patch implements a global id and lock to avoid the races between core, trace and thread imc events. With this global id-lock implementation, the system can either run core, thread or trace imc events at a time. i.e. to run any core-imc events, thread/trace imc events should not be enabled/monitored.

---
 arch/powerpc/perf/imc-pmu.c | 173 +++++++++++++++++++++++++++++++-----
 1 file changed, 149 insertions(+), 24 deletions(-)
arch/powerpc/perf/imc-pmu.c +149 -24
index cb50a9e1fd2d7..eb82dda884e51 100644
@@ -44,6 +44,16 @@ static DEFINE_PER_CPU(u64 *, trace_imc_mem);
 static struct imc_pmu_ref *trace_imc_refc;
 static int trace_imc_mem_size;
 
+/*
+ * Global data structure used to avoid races between thread,
+ * core and trace-imc
+ */
+static struct imc_pmu_ref imc_global_refc = {
+	.lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+	.id = 0,
+	.refc = 0,
+};
+
 static struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct imc_pmu, pmu);
@@ -698,6 +708,16 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
 			return -EINVAL;
 
 		ref->refc = 0;
+		/*
+		 * Reduce the global reference count, if this is the
+		 * last cpu in this core and core-imc event running
+		 * in this cpu.
+		 */
+		mutex_lock(&imc_global_refc.lock);
+		if (imc_global_refc.id == IMC_DOMAIN_CORE)
+			imc_global_refc.refc--;
+
+		mutex_unlock(&imc_global_refc.lock);
 	}
 	return 0;
 }
@@ -710,6 +730,23 @@ static int core_imc_pmu_cpumask_init(void)
 				 ppc_core_imc_cpu_offline);
 }
 
+static void reset_global_refc(struct perf_event *event)
+{
+		mutex_lock(&imc_global_refc.lock);
+		imc_global_refc.refc--;
+
+		/*
+		 * If no other thread is running any
+		 * event for this domain(thread/core/trace),
+		 * set the global id to zero.
+		 */
+		if (imc_global_refc.refc <= 0) {
+			imc_global_refc.refc = 0;
+			imc_global_refc.id = 0;
+		}
+		mutex_unlock(&imc_global_refc.lock);
+}
+
 static void core_imc_counters_release(struct perf_event *event)
 {
 	int rc, core_id;
@@ -759,6 +796,8 @@ static void core_imc_counters_release(struct perf_event *event)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
+	reset_global_refc(event);
 }
 
 static int core_imc_event_init(struct perf_event *event)
@@ -819,6 +858,29 @@ static int core_imc_event_init(struct perf_event *event)
 	++ref->refc;
 	mutex_unlock(&ref->lock);
 
+	/*
+	 * Since the system can run either in accumulation or trace-mode
+	 * of IMC at a time, core-imc events are allowed only if no other
+	 * trace/thread imc events are enabled/monitored.
+	 *
+	 * Take the global lock, and check the refc.id
+	 * to know whether any other trace/thread imc
+	 * events are running.
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
+		/*
+		 * No other trace/thread imc events are running in
+		 * the system, so set the refc.id to core-imc.
+		 */
+		imc_global_refc.id = IMC_DOMAIN_CORE;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
 	event->destroy = core_imc_counters_release;
 	return 0;
@@ -877,7 +939,23 @@ static int ppc_thread_imc_cpu_online(unsigned int cpu)
 
 static int ppc_thread_imc_cpu_offline(unsigned int cpu)
 {
-	mtspr(SPRN_LDBAR, 0);
+	/*
+	 * Set the bit 0 of LDBAR to zero.
+	 *
+	 * If bit 0 of LDBAR is unset, it will stop posting
+	 * the counter data to memory.
+	 * For thread-imc, bit 0 of LDBAR will be set to 1 in the
+	 * event_add function. So reset this bit here, to stop the updates
+	 * to memory in the cpu_offline path.
+	 */
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
+
+	/* Reduce the refc if thread-imc event running on this cpu */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == IMC_DOMAIN_THREAD)
+		imc_global_refc.refc--;
+	mutex_unlock(&imc_global_refc.lock);
+
 	return 0;
 }
 
@@ -916,7 +994,22 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (!target)
 		return -EINVAL;
 
+	mutex_lock(&imc_global_refc.lock);
+	/*
+	 * Check if any other trace/core imc events are running in the
+	 * system, if not set the global id to thread-imc.
+	 */
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) {
+		imc_global_refc.id = IMC_DOMAIN_THREAD;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->pmu->task_ctx_nr = perf_sw_context;
+	event->destroy = reset_global_refc;
 	return 0;
 }
 
@@ -1063,10 +1156,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 	int core_id;
 	struct imc_pmu_ref *ref;
 
-	mtspr(SPRN_LDBAR, 0);
-
 	core_id = smp_processor_id() / threads_per_core;
 	ref = &core_imc_refc[core_id];
+	if (!ref) {
+		pr_debug("imc: Failed to get event reference count\n");
+		return;
+	}
 
 	mutex_lock(&ref->lock);
 	ref->refc--;
@@ -1082,6 +1177,10 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
+	/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
+
 	/*
 	 * Take a snapshot and calculate the delta and update
 	 * the event counter values.
@@ -1133,7 +1232,18 @@ static int ppc_trace_imc_cpu_online(unsigned int cpu)
 
 static int ppc_trace_imc_cpu_offline(unsigned int cpu)
 {
-	mtspr(SPRN_LDBAR, 0);
+	/*
+	 * No need to set bit 0 of LDBAR to zero, as
+	 * it is set to zero for imc trace-mode
+	 *
+	 * Reduce the refc if any trace-imc event running
+	 * on this cpu.
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == IMC_DOMAIN_TRACE)
+		imc_global_refc.refc--;
+	mutex_unlock(&imc_global_refc.lock);
+
 	return 0;
 }
 
@@ -1226,15 +1336,14 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
 	local_mem = get_trace_imc_event_base_addr();
 	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE;
 
-	if (core_imc_refc)
-		ref = &core_imc_refc[core_id];
+	/* trace-imc reference count */
+	if (trace_imc_refc)
+		ref = &trace_imc_refc[core_id];
 	if (!ref) {
-		/* If core-imc is not enabled, use trace-imc reference count */
-		if (trace_imc_refc)
-			ref = &trace_imc_refc[core_id];
-		if (!ref)
-			return -EINVAL;
+		pr_debug("imc: Failed to get the event reference count\n");
+		return -EINVAL;
 	}
+
 	mtspr(SPRN_LDBAR, ldbar_value);
 	mutex_lock(&ref->lock);
 	if (ref->refc == 0) {
@@ -1242,13 +1351,11 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
 				get_hard_smp_processor_id(smp_processor_id()))) {
 			mutex_unlock(&ref->lock);
 			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
-			mtspr(SPRN_LDBAR, 0);
 			return -EINVAL;
 		}
 	}
 	++ref->refc;
 	mutex_unlock(&ref->lock);
-
 	return 0;
 }
 
@@ -1274,16 +1381,13 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 	int core_id = smp_processor_id() / threads_per_core;
 	struct imc_pmu_ref *ref = NULL;
 
-	if (core_imc_refc)
-		ref = &core_imc_refc[core_id];
+	if (trace_imc_refc)
+		ref = &trace_imc_refc[core_id];
 	if (!ref) {
-		/* If core-imc is not enabled, use trace-imc reference count */
-		if (trace_imc_refc)
-			ref = &trace_imc_refc[core_id];
-		if (!ref)
-			return;
+		pr_debug("imc: Failed to get event reference count\n");
+		return;
 	}
-	mtspr(SPRN_LDBAR, 0);
+
 	mutex_lock(&ref->lock);
 	ref->refc--;
 	if (ref->refc == 0) {
@@ -1297,6 +1401,7 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
 	trace_imc_event_stop(event, flags);
 }
 
@@ -1314,10 +1419,30 @@ static int trace_imc_event_init(struct perf_event *event)
 	if (event->attr.sample_period == 0)
 		return -ENOENT;
 
+	/*
+	 * Take the global lock, and make sure
+	 * no other thread is running any core/thread imc
+	 * events
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
+		/*
+		 * No core/thread imc events are running in the
+		 * system, so set the refc.id to trace-imc.
+		 */
+		imc_global_refc.id = IMC_DOMAIN_TRACE;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->hw.idx = -1;
 	target = event->hw.target;
 
 	event->pmu->task_ctx_nr = perf_hw_context;
+	event->destroy = reset_global_refc;
 	return 0;
 }
 
@@ -1429,10 +1554,10 @@ static void cleanup_all_core_imc_memory(void)
 static void thread_imc_ldbar_disable(void *dummy)
 {
 	/*
-	 * By Zeroing LDBAR, we disable thread-imc
-	 * updates.
+	 * By setting 0th bit of LDBAR to zero, we disable thread-imc
+	 * updates to memory.
 	 */
-	mtspr(SPRN_LDBAR, 0);
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
 }
 
 void thread_imc_disable(void)
Signature · 1 line
2.25.1
author maintainer
#236 lore raw

PATCH 236/388 KVM: arm64: vgic-v3: Retire all pending LPIs on vcpu destroy

In reply to Greg Kroah-Hartman

From: Zenghui Yu <[email protected]>

[ Upstream commit 969ce8b5260d8ec01e6f1949d2927a86419663ce ]

It's likely that the vcpu fails to handle all virtual interrupts if userspace decides to destroy it, leaving the pending ones stay in the ap_list. If the un-handled one is a LPI, its vgic_irq structure will be eventually leaked because of an extra refcount increment in vgic_queue_irq_unlock().

This was detected by kmemleak on almost every guest destroy, the backtrace is as follows:

unreferenced object 0xffff80725aed5500 (size 128):
comm "CPU 5/KVM", pid 40711, jiffies 4298024754 (age 166366.512s) hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 08 01 a9 73 6d 80 ff ff ...........sm... c8 61 ee a9 00 20 ff ff 28 1e 55 81 6c 80 ff ff .a... ..(.U.l... backtrace:

[<000000004bcaa122>] kmem_cache_alloc_trace+0x2dc/0x418
[<0000000069c7dabb>] vgic_add_lpi+0x88/0x418
[<00000000bfefd5c5>] vgic_its_cmd_handle_mapi+0x4dc/0x588
[<00000000cf993975>] vgic_its_process_commands.part.5+0x484/0x1198
[<000000004bd3f8e3>] vgic_its_process_commands+0x50/0x80
[<00000000b9a65b2b>] vgic_mmio_write_its_cwriter+0xac/0x108
[<0000000009641ebb>] dispatch_mmio_write+0xd0/0x188
[<000000008f79d288>] __kvm_io_bus_write+0x134/0x240
[<00000000882f39ac>] kvm_io_bus_write+0xe0/0x150
[<0000000078197602>] io_mem_abort+0x484/0x7b8
[<0000000060954e3c>] kvm_handle_guest_abort+0x4cc/0xa58
[<00000000e0d0cd65>] handle_exit+0x24c/0x770
[<00000000b44a7fad>] kvm_arch_vcpu_ioctl_run+0x460/0x1988
[<0000000025fb897c>] kvm_vcpu_ioctl+0x4f8/0xee0
[<000000003271e317>] do_vfs_ioctl+0x160/0xcd8
[<00000000e7f39607>] ksys_ioctl+0x98/0xd8

Fix it by retiring all pending LPIs in the ap_list on the destroy path.

p.s. I can also reproduce it on a normal guest shutdown. It is because userspace still send LPIs to vcpu (through KVM_SIGNAL_MSI ioctl) while the guest is being shutdown and unable to handle it. A little strange though and haven't dig further...

[maz: moved the distributor deallocation down to avoid an UAF splat]
---
 virt/kvm/arm/vgic/vgic-init.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
virt/kvm/arm/vgic/vgic-init.c +8 -2
index 6d85c6d894c39..6899101538890 100644
@@ -358,6 +358,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 
+	/*
+	 * Retire all pending LPIs on this vcpu anyway as we're
+	 * going to destroy it.
+	 */
+	vgic_flush_pending_lpis(vcpu);
+
 	INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
 }
 
@@ -369,10 +375,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm)
 
 	vgic_debug_destroy(kvm);
 
-	kvm_vgic_dist_destroy(kvm);
-
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_vgic_vcpu_destroy(vcpu);
+
+	kvm_vgic_dist_destroy(kvm);
 }
 
 void kvm_vgic_destroy(struct kvm *kvm)
Signature · 1 line
2.25.1
author maintainer
#235 lore raw

PATCH 235/388 drivers: char: tlclk.c: Avoid data race between init and interrupt handler

In reply to Greg Kroah-Hartman

From: Madhuparna Bhowmik <[email protected]>

[ Upstream commit 44b8fb6eaa7c3fb770bf1e37619cdb3902cca1fc ]

After registering character device the file operation callbacks can be called. The open callback registers interrupt handler. Therefore interrupt handler can execute in parallel with rest of the init function. To avoid such data race initialize telclk_interrupt variable and struct alarm_events before registering character device.

Found by Linux Driver Verification project (linuxtesting.org).

---
 drivers/char/tlclk.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)
drivers/char/tlclk.c +10 -7
index 6d81bb3bb503f..896a3550fba9f 100644
@@ -777,17 +777,21 @@ static int __init tlclk_init(void)
 {
 	int ret;
 
+	telclk_interrupt = (inb(TLCLK_REG7) & 0x0f);
+
+	alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL);
+	if (!alarm_events) {
+		ret = -ENOMEM;
+		goto out1;
+	}
+
 	ret = register_chrdev(tlclk_major, "telco_clock", &tlclk_fops);
 	if (ret < 0) {
 		printk(KERN_ERR "tlclk: can't get major %d.\n", tlclk_major);
+		kfree(alarm_events);
 		return ret;
 	}
 	tlclk_major = ret;
-	alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL);
-	if (!alarm_events) {
-		ret = -ENOMEM;
-		goto out1;
-	}
 
 	/* Read telecom clock IRQ number (Set by BIOS) */
 	if (!request_region(TLCLK_BASE, 8, "telco_clock")) {
@@ -796,7 +800,6 @@ static int __init tlclk_init(void)
 		ret = -EBUSY;
 		goto out2;
 	}
-	telclk_interrupt = (inb(TLCLK_REG7) & 0x0f);
 
 	if (0x0F == telclk_interrupt ) { /* not MCPBL0010 ? */
 		printk(KERN_ERR "telclk_interrupt = 0x%x non-mcpbl0010 hw.\n",
@@ -837,8 +840,8 @@ out3:
 	release_region(TLCLK_BASE, 8);
 out2:
 	kfree(alarm_events);
-out1:
 	unregister_chrdev(tlclk_major, "telco_clock");
+out1:
 	return ret;
 }
 
Signature · 1 line
2.25.1
author maintainer
#234 lore raw

PATCH 234/388 bdev: Reduce time holding bd_mutex in sync in blkdev_close()

In reply to Greg Kroah-Hartman

From: Douglas Anderson <[email protected]>

[ Upstream commit b849dd84b6ccfe32622988b79b7b073861fcf9f7 ]

While trying to "dd" to the block device for a USB stick, I encountered a hung task warning (blocked for > 120 seconds). I managed to come up with an easy way to reproduce this on my system (where /dev/sdb is the block device for my USB stick) with:

while true; do dd if=/dev/zero of=/dev/sdb bs=4M; done

With my reproduction here are the relevant bits from the hung task detector:

 INFO: task udevd:294 blocked for more than 122 seconds.
 ...
 udevd           D    0   294      1 0x00400008
 Call trace:
  ...
  mutex_lock_nested+0x40/0x50
  __blkdev_get+0x7c/0x3d4
  blkdev_get+0x118/0x138
  blkdev_open+0x94/0xa8
  do_dentry_open+0x268/0x3a0
  vfs_open+0x34/0x40
  path_openat+0x39c/0xdf4
  do_filp_open+0x90/0x10c
  do_sys_open+0x150/0x3c8
  ...

...

 Showing all locks held in the system:
 ...
 1 lock held by dd/2798:
  #0: ffffff814ac1a3b8 (&bdev->bd_mutex){+.+.}, at: __blkdev_put+0x50/0x204
 ...
 dd              D    0  2798   2764 0x00400208
 Call trace:
  ...
  schedule+0x8c/0xbc
  io_schedule+0x1c/0x40
  wait_on_page_bit_common+0x238/0x338
  __lock_page+0x5c/0x68
  write_cache_pages+0x194/0x500
  generic_writepages+0x64/0xa4
  blkdev_writepages+0x24/0x30
  do_writepages+0x48/0xa8
  __filemap_fdatawrite_range+0xac/0xd8
  filemap_write_and_wait+0x30/0x84
  __blkdev_put+0x88/0x204
  blkdev_put+0xc4/0xe4
  blkdev_close+0x28/0x38
  __fput+0xe0/0x238
  ____fput+0x1c/0x28
  task_work_run+0xb0/0xe4
  do_notify_resume+0xfc0/0x14bc
  work_pending+0x8/0x14

The problem appears related to the fact that my USB disk is terribly slow and that I have a lot of RAM in my system to cache things. Specifically my writes seem to be happening at ~15 MB/s and I've got ~4 GB of RAM in my system that can be used for buffering. To write 4 GB of buffer to disk thus takes ~4000 MB / ~15 MB/s = ~267 seconds.

The 267 second number is a problem because in __blkdev_put() we call sync_blockdev() while holding the bd_mutex. Any other callers who want the bd_mutex will be blocked for the whole time.

The problem is made worse because I believe blkdev_put() specifically tells other tasks (namely udev) to go try to access the device at right around the same time we're going to hold the mutex for a long time.

Putting some traces around this (after disabling the hung task detector), I could confirm:
dd: 437.608600: __blkdev_put() right before sync_blockdev() for sdb
udevd: 437.623901: blkdev_open() right before blkdev_get() for sdb
dd: 661.468451: __blkdev_put() right after sync_blockdev() for sdb
udevd: 663.820426: blkdev_open() right after blkdev_get() for sdb

A simple fix for this is to realize that sync_blockdev() works fine if you're not holding the mutex. Also, it's not the end of the world if you sync a little early (though it can have performance impacts). Thus we can make a guess that we're going to need to do the sync and then do it without holding the mutex. We still do one last sync with the mutex but it should be much, much faster.

With this, my hung task warnings for my test case are gone.

---
 fs/block_dev.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
fs/block_dev.c +10 -0
index 2dc9c73a4cb29..79272cdbe8277 100644
@@ -1857,6 +1857,16 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
+	/*
+	 * Sync early if it looks like we're the last one.  If someone else
+	 * opens the block device between now and the decrement of bd_openers
+	 * then we did a sync that we didn't need to, but that's not the end
+	 * of the world and we want to avoid long (could be several minute)
+	 * syncs while holding the mutex.
+	 */
+	if (bdev->bd_openers == 1)
+		sync_blockdev(bdev);
+
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (for_part)
 		bdev->bd_part_count--;
Signature · 1 line
2.25.1
author maintainer
#233 lore raw

PATCH 233/388 perf stat: Force error in fallback on :k events

In reply to Greg Kroah-Hartman

From: Stephane Eranian <[email protected]>

[ Upstream commit bec49a9e05db3dbdca696fa07c62c52638fb6371 ]

When it is not possible for a non-privilege perf command to monitor at the kernel level (:k), the fallback code forces a :u. That works if the event was previously monitoring both levels. But if the event was already constrained to kernel only, then it does not make sense to restrict it to user only.

Given the code works by exclusion, a kernel only event would have:

attr->exclude_user = 1

The fallback code would add:

attr->exclude_kernel = 1

In the end the end would not monitor in either the user level or kernel level. In other words, it would count nothing.

An event programmed to monitor kernel only cannot be switched to user only without seriously warning the user.

This patch forces an error in this case to make it clear the request cannot really be satisfied.

Behavior with paranoid 1:

  $ sudo bash -c "echo 1 > /proc/sys/kernel/perf_event_paranoid"
  $ perf stat -e cycles:k sleep 1

Performance counter stats for 'sleep 1':

           1,520,413      cycles:k

         1.002361664 seconds time elapsed

         0.002480000 seconds user
         0.000000000 seconds sys

Old behavior with paranoid 2:

  $ sudo bash -c "echo 2 > /proc/sys/kernel/perf_event_paranoid"
  $ perf stat -e cycles:k sleep 1
   Performance counter stats for 'sleep 1':
                   0      cycles:ku

         1.002358127 seconds time elapsed

         0.002384000 seconds user
         0.000000000 seconds sys

New behavior with paranoid 2:

  $ sudo bash -c "echo 2 > /proc/sys/kernel/perf_event_paranoid"
  $ perf stat -e cycles:k sleep 1
  Error:
  You may not have permission to collect stats.

Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).

The current value is 2:

-1: Allow use of (almost) all events by all users
Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK

Quoted 1 line

= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN

Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN

Quoted 2 lines

= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN = 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN

To make this setting permanent, edit /etc/sysctl.conf too, e.g.:

kernel.perf_event_paranoid = -1

v2 of this patch addresses the review feedback from [email protected].

---
 tools/perf/util/evsel.c | 4 ++++
 1 file changed, 4 insertions(+)
tools/perf/util/evsel.c +4 -0
index dfc982baecab4..12b1755b136d3 100644
@@ -2358,6 +2358,10 @@ bool perf_evsel__fallback(struct evsel *evsel, int err,
 		char *new_name;
 		const char *sep = ":";
 
+		/* If event has exclude user then don't exclude kernel. */
+		if (evsel->core.attr.exclude_user)
+			return false;
+
 		/* Is there already the separator in the name. */
 		if (strchr(name, '/') ||
 		    strchr(name, ':'))
Signature · 1 line
2.25.1
author maintainer
#231 lore raw

PATCH 231/388 btrfs: fix setting last_trans for reloc roots

In reply to Greg Kroah-Hartman

From: Josef Bacik <[email protected]>

[ Upstream commit aec7db3b13a07d515c15ada752a7287a44a79ea0 ]

I made a mistake with my previous fix, I assumed that we didn't need to mess with the reloc roots once we were out of the part of relocation where we are actually moving the extents.

The subtle thing that I missed is that btrfs_init_reloc_root() also updates the last_trans for the reloc root when we do btrfs_record_root_in_trans() for the corresponding fs_root. I've added a comment to make sure future me doesn't make this mistake again.

This showed up as a WARN_ON() in btrfs_copy_root() because our last_trans didn't == the current transid. This could happen if we snapshotted a fs root with a reloc root after we set rc->create_reloc_tree = 0, but before we actually merge the reloc root.

Worth mentioning that the regression produced the following warning when running snapshot creation and balance in parallel:

BTRFS info (device sdc): relocating block group 30408704 flags metadata|dup

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 12823 at fs/btrfs/ctree.c:191 btrfs_copy_root+0x26f/0x430 [btrfs]
  CPU: 0 PID: 12823 Comm: btrfs Tainted: G        W 5.6.0-rc7-btrfs-next-58 #1
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
  RIP: 0010:btrfs_copy_root+0x26f/0x430 [btrfs]
  RSP: 0018:ffffb96e044279b8 EFLAGS: 00010202
  RAX: 0000000000000009 RBX: ffff9da70bf61000 RCX: ffffb96e04427a48
  RDX: ffff9da733a770c8 RSI: ffff9da70bf61000 RDI: ffff9da694163818
  RBP: ffff9da733a770c8 R08: fffffffffffffff8 R09: 0000000000000002
  R10: ffffb96e044279a0 R11: 0000000000000000 R12: ffff9da694163818
  R13: fffffffffffffff8 R14: ffff9da6d2512000 R15: ffff9da714cdac00
  FS:  00007fdeacf328c0(0000) GS:ffff9da735e00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 000055a2a5b8a118 CR3: 00000001eed78002 CR4: 00000000003606f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   ? create_reloc_root+0x49/0x2b0 [btrfs]
   ? kmem_cache_alloc_trace+0xe5/0x200
   create_reloc_root+0x8b/0x2b0 [btrfs]
   btrfs_reloc_post_snapshot+0x96/0x5b0 [btrfs]
   create_pending_snapshot+0x610/0x1010 [btrfs]
   create_pending_snapshots+0xa8/0xd0 [btrfs]
   btrfs_commit_transaction+0x4c7/0xc50 [btrfs]
   ? btrfs_mksubvol+0x3cd/0x560 [btrfs]
   btrfs_mksubvol+0x455/0x560 [btrfs]
   __btrfs_ioctl_snap_create+0x15f/0x190 [btrfs]
   btrfs_ioctl_snap_create_v2+0xa4/0xf0 [btrfs]
   ? mem_cgroup_commit_charge+0x6e/0x540
   btrfs_ioctl+0x12d8/0x3760 [btrfs]
   ? do_raw_spin_unlock+0x49/0xc0
   ? _raw_spin_unlock+0x29/0x40
   ? __handle_mm_fault+0x11b3/0x14b0
   ? ksys_ioctl+0x92/0xb0
   ksys_ioctl+0x92/0xb0
   ? trace_hardirqs_off_thunk+0x1a/0x1c
   __x64_sys_ioctl+0x16/0x20
   do_syscall_64+0x5c/0x280
   entry_SYSCALL_64_after_hwframe+0x49/0xbe
  RIP: 0033:0x7fdeabd3bdd7
Fixes 2abc726ab4b8 ("btrfs: do not init a reloc root if we aren't relocating")
---
 fs/btrfs/relocation.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)
fs/btrfs/relocation.c +17 -2
index ece53d2f55ae3..1bc57f7b91cfa 100644
@@ -1468,8 +1468,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	int clear_rsv = 0;
 	int ret;
 
-	if (!rc || !rc->create_reloc_tree ||
-	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+	if (!rc)
 		return 0;
 
 	/*
@@ -1479,12 +1478,28 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
 	if (reloc_root_is_dead(root))
 		return 0;
 
+	/*
+	 * This is subtle but important.  We do not do
+	 * record_root_in_transaction for reloc roots, instead we record their
+	 * corresponding fs root, and then here we update the last trans for the
+	 * reloc root.  This means that we have to do this for the entire life
+	 * of the reloc root, regardless of which stage of the relocation we are
+	 * in.
+	 */
 	if (root->reloc_root) {
 		reloc_root = root->reloc_root;
 		reloc_root->last_trans = trans->transid;
 		return 0;
 	}
 
+	/*
+	 * We are merging reloc roots, we do not need new reloc trees.  Also
+	 * reloc trees never need their own reloc tree.
+	 */
+	if (!rc->create_reloc_tree ||
+	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
+		return 0;
+
 	if (!trans->reloc_reserved) {
 		rsv = trans->block_rsv;
 		trans->block_rsv = rc->block_rsv;
Signature · 1 line
2.25.1
author maintainer
#232 lore raw

PATCH 232/388 KVM: Remove CREATE_IRQCHIP/SET_PIT2 race

In reply to Greg Kroah-Hartman

From: Steve Rutherford <[email protected]>

[ Upstream commit 7289fdb5dcdbc5155b5531529c44105868a762f2 ]

Fixes a NULL pointer dereference, caused by the PIT firing an interrupt before the interrupt table has been initialized.

SET_PIT2 can race with the creation of the IRQchip. In particular, if SET_PIT2 is called with a low PIT timer period (after the creation of the IOAPIC, but before the instantiation of the irq routes), the PIT can fire an interrupt at an uninitialized table.

Message-Id: <[email protected]>

---
 arch/x86/kvm/x86.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
arch/x86/kvm/x86.c +8 -2
index 8920ee7b28811..67ad417a29ca4 100644
@@ -5050,10 +5050,13 @@ set_identity_unlock:
 		r = -EFAULT;
 		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit_out;
 		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_GET_PIT2: {
@@ -5073,10 +5076,13 @@ set_identity_unlock:
 		r = -EFAULT;
 		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit2_out;
 		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_REINJECT_CONTROL: {
Signature · 1 line
2.25.1
author maintainer
#230 lore raw

PATCH 230/388 serial: uartps: Wait for tx_empty in console setup

In reply to Greg Kroah-Hartman

From: Raviteja Narayanam <[email protected]>

[ Upstream commit 42e11948ddf68b9f799cad8c0ddeab0a39da33e8 ]

On some platforms, the log is corrupted while console is being registered. It is observed that when set_termios is called, there are still some bytes in the FIFO to be transmitted.

So, wait for tx_empty inside cdns_uart_console_setup before calling set_termios.

---
 drivers/tty/serial/xilinx_uartps.c | 8 ++++++++
 1 file changed, 8 insertions(+)
drivers/tty/serial/xilinx_uartps.c +8 -0
index 8948970f795e6..9359c80fbb9f5 100644
@@ -1248,6 +1248,7 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 	int bits = 8;
 	int parity = 'n';
 	int flow = 'n';
+	unsigned long time_out;
 
 	if (!port->membase) {
 		pr_debug("console on " CDNS_UART_TTY_NAME "%i not present\n",
@@ -1258,6 +1259,13 @@ static int cdns_uart_console_setup(struct console *co, char *options)
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
 
+	/* Wait for tx_empty before setting up the console */
+	time_out = jiffies + usecs_to_jiffies(TX_TIMEOUT);
+
+	while (time_before(jiffies, time_out) &&
+	       cdns_uart_tx_empty(port) != TIOCSER_TEMT)
+		cpu_relax();
+
 	return uart_set_options(port, co, baud, parity, bits, flow);
 }
 
Signature · 1 line
2.25.1
author maintainer
#229 lore raw

PATCH 229/388 scsi: qedi: Fix termination timeouts in session logout

In reply to Greg Kroah-Hartman

From: Nilesh Javali <[email protected]>

[ Upstream commit b9b97e6903032ec56e6dcbe137a9819b74a17fea ]

The destroy connection ramrod timed out during session logout. Fix the wait delay for graceful vs abortive termination as per the FW requirements.

---
 drivers/scsi/qedi/qedi_iscsi.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/scsi/qedi/qedi_iscsi.c +3 -0
index 0f57c80734061..0f2622a48311c 100644
@@ -1062,6 +1062,9 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 		break;
 	}
 
+	if (!abrt_conn)
+		wait_delay += qedi->pf_params.iscsi_pf_params.two_msl_timer;
+
 	qedi_ep->state = EP_STATE_DISCONN_START;
 	ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn);
 	if (ret) {
Signature · 1 line
2.25.1
author maintainer
#248 lore raw

PATCH 248/388 media: venus: vdec: Init registered list unconditionally

In reply to Greg Kroah-Hartman

From: Stanimir Varbanov <[email protected]>

[ Upstream commit bc3d870e414b42d72cd386aa20a4fc3612e4feb7 ]

Presently the list initialization is done only in dynamic-resolution-change state, which leads to list corruptions and use-after-free. Init list_head unconditionally in vdec_stop_capture called by vb2 stop_streaming without takeing into account current codec state.

---
 drivers/media/platform/qcom/venus/vdec.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/media/platform/qcom/venus/vdec.c +3 -2
index 59ae7a1e63bc2..05b80a66e80ed 100644
@@ -987,13 +987,14 @@ static int vdec_stop_capture(struct venus_inst *inst)
 		ret = hfi_session_flush(inst, HFI_FLUSH_OUTPUT);
 		vdec_cancel_dst_buffers(inst);
 		inst->codec_state = VENUS_DEC_STATE_CAPTURE_SETUP;
-		INIT_LIST_HEAD(&inst->registeredbufs);
 		venus_helper_free_dpb_bufs(inst);
 		break;
 	default:
-		return 0;
+		break;
 	}
 
+	INIT_LIST_HEAD(&inst->registeredbufs);
+
 	return ret;
 }
 
Signature · 1 line
2.25.1
author maintainer
#245 lore raw

PATCH 245/388 dt-bindings: sound: wm8994: Correct required supplies based on actual implementaion

In reply to Greg Kroah-Hartman

From: Krzysztof Kozlowski <[email protected]>

[ Upstream commit 8c149b7d75e53be47648742f40fc90d9fc6fa63a ]

The required supplies in bindings were actually not matching implementation making the bindings incorrect and misleading. The Linux kernel driver requires all supplies to be present. Also for wlf,wm8994 uses just DBVDD-supply instead of DBVDDn-supply (n: <1,3>).

---
 .../devicetree/bindings/sound/wm8994.txt       | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)
Documentation/devicetree/bindings/sound/wm8994.txt +12 -6
index 68cccc4653ba3..367b58ce1bb92 100644
@@ -14,9 +14,15 @@ Required properties:
   - #gpio-cells : Must be 2. The first cell is the pin number and the
     second cell is used to specify optional parameters (currently unused).
 
-  - AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply, CPVDD-supply,
-    SPKVDD1-supply, SPKVDD2-supply : power supplies for the device, as covered
-    in Documentation/devicetree/bindings/regulator/regulator.txt
+  - power supplies for the device, as covered in
+    Documentation/devicetree/bindings/regulator/regulator.txt, depending
+    on compatible:
+    - for wlf,wm1811 and wlf,wm8958:
+      AVDD1-supply, AVDD2-supply, DBVDD1-supply, DBVDD2-supply, DBVDD3-supply,
+      DCVDD-supply, CPVDD-supply, SPKVDD1-supply, SPKVDD2-supply
+    - for wlf,wm8994:
+      AVDD1-supply, AVDD2-supply, DBVDD-supply, DCVDD-supply, CPVDD-supply,
+      SPKVDD1-supply, SPKVDD2-supply
 
 Optional properties:
 
@@ -73,11 +79,11 @@ wm8994: codec@1a {
 
 	lineout1-se;
 
+	AVDD1-supply = <&regulator>;
 	AVDD2-supply = <&regulator>;
 	CPVDD-supply = <&regulator>;
-	DBVDD1-supply = <&regulator>;
-	DBVDD2-supply = <&regulator>;
-	DBVDD3-supply = <&regulator>;
+	DBVDD-supply = <&regulator>;
+	DCVDD-supply = <&regulator>;
 	SPKVDD1-supply = <&regulator>;
 	SPKVDD2-supply = <&regulator>;
 };
Signature · 1 line
2.25.1
author maintainer
#263 lore raw

PATCH 263/388 svcrdma: Fix backchannel return code

In reply to Greg Kroah-Hartman

From: Chuck Lever <[email protected]>

[ Upstream commit ea740bd5f58e2912e74f401fd01a9d6aa985ca05 ]

Way back when I was writing the RPC/RDMA server-side backchannel code, I misread the TCP backchannel reply handler logic. When svc_tcp_recvfrom() successfully receives a backchannel reply, it does not return -EAGAIN. It sets XPT_DATA and returns zero.

Update svc_rdma_recvfrom() to return zero. Here, XPT_DATA doesn't need to be set again: it is set whenever a new message is received, behind a spin lock in a single threaded context.

Also, if handling the cb reply is not successful, the message is simply dropped. There's no special message framing to deal with as there is in the TCP case.

Now that the handle_bc_reply() return value is ignored, I've removed the dprintk call sites in the error exit of handle_bc_reply() in favor of trace points in other areas that already report the error cases.

---
 include/linux/sunrpc/svc_rdma.h            |  5 ++-
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 38 ++++++----------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c    | 11 +++----
 3 files changed, 17 insertions(+), 37 deletions(-)
include/linux/sunrpc/svc_rdma.h +2 -3
index 26f282e5e0822..77589ed787f5c 100644
@@ -154,9 +154,8 @@ struct svc_rdma_send_ctxt {
 };
 
 /* svc_rdma_backchannel.c */
-extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
-				    __be32 *rdma_resp,
-				    struct xdr_buf *rcvbuf);
+extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
+				     struct svc_rdma_recv_ctxt *rctxt);
 
 /* svc_rdma_recvfrom.c */
 extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma);
net/sunrpc/xprtrdma/svc_rdma_backchannel.c +10 -28
index 325eef1f85824..68d2dcf0a1be1 100644
@@ -15,26 +15,25 @@
 #undef SVCRDMA_BACKCHANNEL_DEBUG
 
 /**
- * svc_rdma_handle_bc_reply - Process incoming backchannel reply
- * @xprt: controlling backchannel transport
- * @rdma_resp: pointer to incoming transport header
- * @rcvbuf: XDR buffer into which to decode the reply
+ * svc_rdma_handle_bc_reply - Process incoming backchannel Reply
+ * @rqstp: resources for handling the Reply
+ * @rctxt: Received message
  *
- * Returns:
- *	%0 if @rcvbuf is filled in, xprt_complete_rqst called,
- *	%-EAGAIN if server should call ->recvfrom again.
  */
-int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
-			     struct xdr_buf *rcvbuf)
+void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp,
+			      struct svc_rdma_recv_ctxt *rctxt)
 {
+	struct svc_xprt *sxprt = rqstp->rq_xprt;
+	struct rpc_xprt *xprt = sxprt->xpt_bc_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct xdr_buf *rcvbuf = &rqstp->rq_arg;
 	struct kvec *dst, *src = &rcvbuf->head[0];
+	__be32 *rdma_resp = rctxt->rc_recv_buf;
 	struct rpc_rqst *req;
 	u32 credits;
 	size_t len;
 	__be32 xid;
 	__be32 *p;
-	int ret;
 
 	p = (__be32 *)src->iov_base;
 	len = src->iov_len;
@@ -49,14 +48,10 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 		__func__, (int)len, p);
 #endif
 
-	ret = -EAGAIN;
-	if (src->iov_len < 24)
-		goto out_shortreply;
-
 	spin_lock(&xprt->queue_lock);
 	req = xprt_lookup_rqst(xprt, xid);
 	if (!req)
-		goto out_notfound;
+		goto out_unlock;
 
 	dst = &req->rq_private_buf.head[0];
 	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
@@ -77,25 +72,12 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 	spin_unlock(&xprt->transport_lock);
 
 	spin_lock(&xprt->queue_lock);
-	ret = 0;
 	xprt_complete_rqst(req->rq_task, rcvbuf->len);
 	xprt_unpin_rqst(req);
 	rcvbuf->len = 0;
 
 out_unlock:
 	spin_unlock(&xprt->queue_lock);
-out:
-	return ret;
-
-out_shortreply:
-	dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n",
-		xprt, src->iov_len);
-	goto out;
-
-out_notfound:
-	dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n",
-		xprt, be32_to_cpu(xid));
-	goto out_unlock;
 }
 
 /* Send a backwards direction RPC call.
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +5 -6
index d803d814a03ad..fd5c1f1bb9885 100644
@@ -817,12 +817,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_drop;
 	rqstp->rq_xprt_hlen = ret;
 
-	if (svc_rdma_is_backchannel_reply(xprt, p)) {
-		ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
-					       &rqstp->rq_arg);
-		svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
-		return ret;
-	}
+	if (svc_rdma_is_backchannel_reply(xprt, p))
+		goto out_backchannel;
+
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
 	p += rpcrdma_fixed_maxsz;
@@ -852,6 +849,8 @@ out_postfail:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return ret;
 
+out_backchannel:
+	svc_rdma_handle_bc_reply(rqstp, ctxt);
 out_drop:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;
Signature · 1 line
2.25.1
author maintainer
#265 lore raw

PATCH 265/388 fuse: update attr_version counter on fuse_notify_inval_inode()

In reply to Greg Kroah-Hartman

From: Miklos Szeredi <[email protected]>

[ Upstream commit 5ddd9ced9aef6cfa76af27d384c17c9e2d610ce8 ]

A GETATTR request can race with FUSE_NOTIFY_INVAL_INODE, resulting in the attribute cache being updated with stale information after the invalidation.

Fix this by bumping the attribute version in fuse_reverse_inval_inode().

---
 fs/fuse/inode.c | 7 +++++++
 1 file changed, 7 insertions(+)
fs/fuse/inode.c +7 -0
index 5dca643a257c9..f58ab84b09fb3 100644
@@ -323,6 +323,8 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 			     loff_t offset, loff_t len)
 {
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+	struct fuse_inode *fi;
 	struct inode *inode;
 	pgoff_t pg_start;
 	pgoff_t pg_end;
@@ -331,6 +333,11 @@ int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
 	if (!inode)
 		return -ENOENT;
 
+	fi = get_fuse_inode(inode);
+	spin_lock(&fi->lock);
+	fi->attr_version = atomic64_inc_return(&fc->attr_version);
+	spin_unlock(&fi->lock);
+
 	fuse_invalidate_attr(inode);
 	forget_all_cached_acls(inode);
 	if (offset >= 0) {
Signature · 1 line
2.25.1
author maintainer
#266 lore raw

PATCH 266/388 USB: EHCI: ehci-mv: fix less than zero comparison of an unsigned int

In reply to Greg Kroah-Hartman

From: Colin Ian King <[email protected]>

[ Upstream commit a7f40c233a6b0540d28743267560df9cfb571ca9 ]

The comparison of hcd->irq to less than zero for an error check will never be true because hcd->irq is an unsigned int. Fix this by assigning the int retval to the return of platform_get_irq and checking this for the -ve error condition and assigning hcd->irq to retval.

Addresses-Coverity: ("Unsigned compared against 0")

Fixes c856b4b0fdb5 ("USB: EHCI: ehci-mv: fix error handling in mv_ehci_probe()")
---
 drivers/usb/host/ehci-mv.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/usb/host/ehci-mv.c +3 -4
index 15b2e8910e9b7..b6f196f5e252e 100644
@@ -156,11 +156,10 @@ static int mv_ehci_probe(struct platform_device *pdev)
 	hcd->rsrc_len = resource_size(r);
 	hcd->regs = ehci_mv->op_regs;
 
-	hcd->irq = platform_get_irq(pdev, 0);
-	if (hcd->irq < 0) {
-		retval = hcd->irq;
+	retval = platform_get_irq(pdev, 0);
+	if (retval < 0)
 		goto err_disable_clk;
-	}
+	hcd->irq = retval;
 
 	ehci = hcd_to_ehci(hcd);
 	ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs;
Signature · 1 line
2.25.1
author maintainer
#268 lore raw

PATCH 268/388 arm64: acpi: Make apei_claim_sea() synchronise with APEIs irq work

In reply to Greg Kroah-Hartman

From: James Morse <[email protected]>

[ Upstream commit 8fcc4ae6faf8b455eeef00bc9ae70744e3b0f462 ]

APEI is unable to do all of its error handling work in nmi-context, so it defers non-fatal work onto the irq_work queue. arch_irq_work_raise() sends an IPI to the calling cpu, but this is not guaranteed to be taken before returning to user-space.

Unless the exception interrupted a context with irqs-masked, irq_work_run() can run immediately. Otherwise return -EINPROGRESS to indicate ghes_notify_sea() found some work to do, but it hasn't finished yet.

With this apei_claim_sea() returning '0' means this external-abort was also notification of a firmware-first RAS error, and that APEI has processed the CPER records.

---
 arch/arm64/kernel/acpi.c | 25 +++++++++++++++++++++++++
 arch/arm64/mm/fault.c    | 12 +++++++-----
 2 files changed, 32 insertions(+), 5 deletions(-)
arch/arm64/kernel/acpi.c +25 -0
index a100483b47c42..46ec402e97edc 100644
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/irq_work.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/smp.h>
@@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 int apei_claim_sea(struct pt_regs *regs)
 {
 	int err = -ENOENT;
+	bool return_to_irqs_enabled;
 	unsigned long current_flags;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
@@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs)
 
 	current_flags = local_daif_save_flags();
 
+	/* current_flags isn't useful here as daif doesn't tell us about pNMI */
+	return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags());
+
+	if (regs)
+		return_to_irqs_enabled = interrupts_enabled(regs);
+
 	/*
 	 * SEA can interrupt SError, mask it and describe this as an NMI so
 	 * that APEI defers the handling.
@@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs)
 	nmi_enter();
 	err = ghes_notify_sea();
 	nmi_exit();
+
+	/*
+	 * APEI NMI-like notifications are deferred to irq_work. Unless
+	 * we interrupted irqs-masked code, we can do that now.
+	 */
+	if (!err) {
+		if (return_to_irqs_enabled) {
+			local_daif_restore(DAIF_PROCCTX_NOIRQ);
+			__irq_enter();
+			irq_work_run();
+			__irq_exit();
+		} else {
+			pr_warn_ratelimited("APEI work queued but not completed");
+			err = -EINPROGRESS;
+		}
+	}
+
 	local_daif_restore(current_flags);
 
 	return err;
arch/arm64/mm/fault.c +7 -5
index d26e6cd289539..2a7339aeb1ad4 100644
@@ -654,11 +654,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 
 	inf = esr_to_fault_info(esr);
 
-	/*
-	 * Return value ignored as we rely on signal merging.
-	 * Future patches will make this more robust.
-	 */
-	apei_claim_sea(regs);
+	if (user_mode(regs) && apei_claim_sea(regs) == 0) {
+		/*
+		 * APEI claimed this as a firmware-first notification.
+		 * Some processing deferred to task_work before ret_to_user().
+		 */
+		return 0;
+	}
 
 	if (esr & ESR_ELx_FnV)
 		siaddr = NULL;
Signature · 1 line
2.25.1
author maintainer
#267 lore raw

PATCH 267/388 coresight: etm4x: Fix use-after-free of per-cpu etm drvdata

In reply to Greg Kroah-Hartman

From: Suzuki K Poulose <[email protected]>

[ Upstream commit 3f4943d422c5febbb3c764670011a00eb2a86238 ]

etm probe could be deferred due to the dependency in the trace path chain and may be retried. We need to clear the per-cpu etmdrvdata entry for the etm in case of a failure to avoid use-after-free cases as reported below:

KASAN use-after-free bug in etm4_cpu_pm_notify():

[    8.574566] coresight etm0: CPU0: ETM v4.2 initialized
[    8.581920] BUG: KASAN: use-after-free in etm4_cpu_pm_notify+0x580/0x2024
[    8.581925] Read of size 8 at addr ffffff813304f8c8 by task swapper/3/0
[    8.581927]
[    8.581934] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G S      W         5.4.28 #314
[    8.587775] coresight etm1: CPU1: ETM v4.2 initialized
[    8.594195] Call trace:
[    8.594205]  dump_backtrace+0x0/0x188
[    8.594209]  show_stack+0x20/0x2c
[    8.594216]  dump_stack+0xdc/0x144
[    8.594227]  print_address_description+0x3c/0x494
[    8.594232]  __kasan_report+0x144/0x168
[    8.601598] coresight etm2: CPU2: ETM v4.2 initialized
[    8.602563]  kasan_report+0x10/0x18
[    8.602568]  check_memory_region+0x1a4/0x1b4
[    8.602572]  __kasan_check_read+0x18/0x24
[    8.602577]  etm4_cpu_pm_notify+0x580/0x2024
[    8.665945]  notifier_call_chain+0x5c/0x90
[    8.670166]  __atomic_notifier_call_chain+0x90/0xf8
[    8.675182]  cpu_pm_notify+0x40/0x6c
[    8.678858]  cpu_pm_enter+0x38/0x80
[    8.682451]  psci_enter_idle_state+0x34/0x70
[    8.686844]  cpuidle_enter_state+0xb8/0x20c
[    8.691143]  cpuidle_enter+0x38/0x4c
[    8.694820]  call_cpuidle+0x3c/0x68
[    8.698408]  do_idle+0x1a0/0x280
[    8.701729]  cpu_startup_entry+0x24/0x28
[    8.705768]  secondary_start_kernel+0x15c/0x170
[    8.710423]
[    8.711972] Allocated by task 242:
[    8.715473]  __kasan_kmalloc+0xf0/0x1ac
[    8.719426]  kasan_slab_alloc+0x14/0x1c
[    8.723375]  __kmalloc_track_caller+0x23c/0x388
[    8.728040]  devm_kmalloc+0x38/0x94
[    8.731632]  etm4_probe+0x48/0x3c8
[    8.735140]  amba_probe+0xbc/0x158
[    8.738645]  really_probe+0x144/0x408
[    8.742412]  driver_probe_device+0x70/0x140
[    8.746716]  __device_attach_driver+0x9c/0x110
[    8.751287]  bus_for_each_drv+0x90/0xd8
[    8.755236]  __device_attach+0xb4/0x164
[    8.759188]  device_initial_probe+0x20/0x2c
[    8.763490]  bus_probe_device+0x34/0x94
[    8.767436]  device_add+0x34c/0x3e0
[    8.771029]  amba_device_try_add+0x68/0x440
[    8.775332]  amba_deferred_retry_func+0x48/0xc8
[    8.779997]  process_one_work+0x344/0x648
[    8.784127]  worker_thread+0x2ac/0x47c
[    8.787987]  kthread+0x128/0x138
[    8.791313]  ret_from_fork+0x10/0x18
[    8.794993]
[    8.796532] Freed by task 242:
[    8.799684]  __kasan_slab_free+0x15c/0x22c
[    8.803897]  kasan_slab_free+0x10/0x1c
[    8.807761]  kfree+0x25c/0x4bc
[    8.810913]  release_nodes+0x240/0x2b0
[    8.814767]  devres_release_all+0x3c/0x54
[    8.818887]  really_probe+0x178/0x408
[    8.822661]  driver_probe_device+0x70/0x140
[    8.826963]  __device_attach_driver+0x9c/0x110
[    8.831539]  bus_for_each_drv+0x90/0xd8
[    8.835487]  __device_attach+0xb4/0x164
[    8.839431]  device_initial_probe+0x20/0x2c
[    8.843732]  bus_probe_device+0x34/0x94
[    8.847678]  device_add+0x34c/0x3e0
[    8.851274]  amba_device_try_add+0x68/0x440
[    8.855576]  amba_deferred_retry_func+0x48/0xc8
[    8.860240]  process_one_work+0x344/0x648
[    8.864366]  worker_thread+0x2ac/0x47c
[    8.868228]  kthread+0x128/0x138
[    8.871557]  ret_from_fork+0x10/0x18
[    8.875231]
[    8.876782] The buggy address belongs to the object at ffffff813304f800
[    8.876782]  which belongs to the cache kmalloc-1k of size 1024
[    8.889632] The buggy address is located 200 bytes inside of
[    8.889632]  1024-byte region [ffffff813304f800, ffffff813304fc00)
[    8.901761] The buggy address belongs to the page:
[    8.906695] page:ffffffff04ac1200 refcount:1 mapcount:0 mapping:ffffff8146c03800 index:0x0 compound_mapcount: 0
[    8.917047] flags: 0x4000000000010200(slab|head)
[    8.921799] raw: 4000000000010200 dead000000000100 dead000000000122 ffffff8146c03800
[    8.929753] raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000
[    8.937703] page dumped because: kasan: bad access detected
[    8.943433]
[    8.944974] Memory state around the buggy address:
[    8.949903]  ffffff813304f780: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[    8.957320]  ffffff813304f800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.964742] >ffffff813304f880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.972157]                                               ^
[    8.977886]  ffffff813304f900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.985298]  ffffff813304f980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[    8.992713] ==================================================================
Fixes f188b5e76aae ("coresight: etm4x: Save/restore state across CPU low power states")
Cc Mathieu Poirier <[email protected]>
Cc Mike Leach <[email protected]>
---
 drivers/hwtracing/coresight/coresight-etm4x.c | 1 +
 1 file changed, 1 insertion(+)
drivers/hwtracing/coresight/coresight-etm4x.c +1 -0
index a128b5063f46c..83dccdeef9069 100644
@@ -1184,6 +1184,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 	return 0;
 
 err_arch_supported:
+	etmdrvdata[drvdata->cpu] = NULL;
 	if (--etm4_count == 0) {
 		cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING);
 		if (hp_online)
Signature · 1 line
2.25.1
author maintainer
#269 lore raw

PATCH 269/388 scsi: cxlflash: Fix error return code in cxlflash_probe()

In reply to Greg Kroah-Hartman

From: Wei Yongjun <[email protected]>

[ Upstream commit d0b1e4a638d670a09f42017a3e567dc846931ba8 ]

Fix to return negative error code -ENOMEM from create_afu error handling case instead of 0, as done elsewhere in this function.

---
 drivers/scsi/cxlflash/main.c | 1 +
 1 file changed, 1 insertion(+)
drivers/scsi/cxlflash/main.c +1 -0
index 93ef97af22df4..67d681c53c295 100644
@@ -3746,6 +3746,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 	cfg->afu_cookie = cfg->ops->create_afu(pdev);
 	if (unlikely(!cfg->afu_cookie)) {
 		dev_err(dev, "%s: create_afu failed\n", __func__);
+		rc = -ENOMEM;
 		goto out_remove;
 	}
 
Signature · 1 line
2.25.1
author maintainer
#251 lore raw

PATCH 251/388 i2c: tegra: Restore pinmux on system resume

In reply to Greg Kroah-Hartman

From: Thierry Reding <[email protected]>

[ Upstream commit 44c99904cf61f945d02ac9976ab10dd5ccaea393 ]

Depending on the board design, the I2C controllers found on Tegra SoCs may require pinmuxing in order to function. This is done as part of the driver's runtime suspend/resume operations. However, the PM core does not allow devices to go into runtime suspend during system sleep to avoid potential races with the suspend/resume of their parents.

As a result of this, when Tegra SoCs resume from system suspend, their I2C controllers may have lost the pinmux state in hardware, whereas the pinctrl subsystem is not aware of this. To fix this, make sure that if the I2C controller is not runtime suspended, the runtime suspend code is still executed in order to disable the module clock (which we don't need to be enabled during sleep) and set the pinmux to the idle state.

Conversely, make sure that the I2C controller is properly resumed when waking up from sleep so that pinmux settings are properly restored.

This fixes a bug seen with DDC transactions to an HDMI monitor timing out when resuming from system suspend.

---
 drivers/i2c/busses/i2c-tegra.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)
drivers/i2c/busses/i2c-tegra.c +19 -4
index 5ca72fb0b406c..db94e96aed77e 100644
@@ -1721,10 +1721,14 @@ static int tegra_i2c_remove(struct platform_device *pdev)
 static int __maybe_unused tegra_i2c_suspend(struct device *dev)
 {
 	struct tegra_i2c_dev *i2c_dev = dev_get_drvdata(dev);
+	int err = 0;
 
 	i2c_mark_adapter_suspended(&i2c_dev->adapter);
 
-	return 0;
+	if (!pm_runtime_status_suspended(dev))
+		err = tegra_i2c_runtime_suspend(dev);
+
+	return err;
 }
 
 static int __maybe_unused tegra_i2c_resume(struct device *dev)
@@ -1732,6 +1736,10 @@ static int __maybe_unused tegra_i2c_resume(struct device *dev)
 	struct tegra_i2c_dev *i2c_dev = dev_get_drvdata(dev);
 	int err;
 
+	/*
+	 * We need to ensure that clocks are enabled so that registers can be
+	 * restored in tegra_i2c_init().
+	 */
 	err = tegra_i2c_runtime_resume(dev);
 	if (err)
 		return err;
@@ -1740,9 +1748,16 @@ static int __maybe_unused tegra_i2c_resume(struct device *dev)
 	if (err)
 		return err;
 
-	err = tegra_i2c_runtime_suspend(dev);
-	if (err)
-		return err;
+	/*
+	 * In case we are runtime suspended, disable clocks again so that we
+	 * don't unbalance the clock reference counts during the next runtime
+	 * resume transition.
+	 */
+	if (pm_runtime_status_suspended(dev)) {
+		err = tegra_i2c_runtime_suspend(dev);
+		if (err)
+			return err;
+	}
 
 	i2c_mark_adapter_resumed(&i2c_dev->adapter);
 
Signature · 1 line
2.25.1
author maintainer
#244 lore raw

PATCH 244/388 dpaa2-eth: fix error return code in setup_dpni()

In reply to Greg Kroah-Hartman

From: Wei Yongjun <[email protected]>

[ Upstream commit 97fff7c8de1e54e5326dfeb66085796864bceb64 ]

Fix to return negative error code -ENOMEM from the error handling case instead of 0, as done elsewhere in this function.

---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +3 -1
index 7a248cc1055a3..7af7cc7c8669a 100644
@@ -2654,8 +2654,10 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
-	if (!priv->cls_rules)
+	if (!priv->cls_rules) {
+		err = -ENOMEM;
 		goto close;
+	}
 
 	return 0;
 
Signature · 1 line
2.25.1
author maintainer
#262 lore raw

PATCH 262/388 powerpc/traps: Make unrecoverable NMIs die instead of panic

In reply to Greg Kroah-Hartman

From: Nicholas Piggin <[email protected]>

[ Upstream commit 265d6e588d87194c2fe2d6c240247f0264e0c19b ]

System Reset and Machine Check interrupts that are not recoverable due to being nested or interrupting when RI=0 currently panic. This is not necessary, and can often just kill the current context and recover.

---
 arch/powerpc/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
arch/powerpc/kernel/traps.c +3 -3
index 014ff0701f245..9432fc6af28a5 100644
@@ -510,11 +510,11 @@ out:
 #ifdef CONFIG_PPC_BOOK3S_64
 	BUG_ON(get_paca()->in_nmi == 0);
 	if (get_paca()->in_nmi > 1)
-		nmi_panic(regs, "Unrecoverable nested System Reset");
+		die("Unrecoverable nested System Reset", regs, SIGABRT);
 #endif
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable System Reset");
+		die("Unrecoverable System Reset", regs, SIGABRT);
 
 	if (saved_hsrrs) {
 		mtspr(SPRN_HSRR0, hsrr0);
@@ -858,7 +858,7 @@ void machine_check_exception(struct pt_regs *regs)
 
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
-		nmi_panic(regs, "Unrecoverable Machine check");
+		die("Unrecoverable Machine check", regs, SIGBUS);
 
 	return;
 
Signature · 1 line
2.25.1
author maintainer
#264 lore raw

PATCH 264/388 fuse: dont check refcount after stealing page

In reply to Greg Kroah-Hartman

From: Miklos Szeredi <[email protected]>

[ Upstream commit 32f98877c57bee6bc27f443a96f49678a2cd6a50 ]

page_count() is unstable. Unless there has been an RCU grace period between when the page was removed from the page cache and now, a speculative reference may exist from the page cache.

---
 fs/fuse/dev.c | 1 -
 1 file changed, 1 deletion(-)
fs/fuse/dev.c +0 -1
index 06dd38e76c62a..f9022b7028754 100644
@@ -764,7 +764,6 @@ static int fuse_check_page(struct page *page)
 {
 	if (page_mapcount(page) ||
 	    page->mapping != NULL ||
-	    page_count(page) != 1 ||
 	    (page->flags & PAGE_FLAGS_CHECK_AT_PREP &
 	     ~(1 << PG_locked |
 	       1 << PG_referenced |
Signature · 1 line
2.25.1
author maintainer
#278 lore raw

PATCH 278/388 btrfs: dont force read-only after error in drop snapshot

In reply to Greg Kroah-Hartman

From: David Sterba <[email protected]>

[ Upstream commit 7c09c03091ac562ddca2b393e5d65c1d37da79f1 ]

Deleting a subvolume on a full filesystem leads to ENOSPC followed by a forced read-only. This is not a transaction abort and the filesystem is otherwise ok, so the error should be just propagated to the callers.

This is caused by unnecessary call to btrfs_handle_fs_error for all errors, except EAGAIN. This does not make sense as the standard transaction abort mechanism is in btrfs_drop_snapshot so all relevant failures are handled.

Originally in commit cb1b69f4508a ("Btrfs: forced readonly when btrfs_drop_snapshot() fails") there was no return value at all, so the btrfs_std_error made some sense but once the error handling and propagation has been implemented we don't need it anymore.

---
 fs/btrfs/extent-tree.c | 2 --
 1 file changed, 2 deletions(-)
fs/btrfs/extent-tree.c +0 -2
index 31c1ed554d26d..7658f3193175b 100644
@@ -5428,8 +5428,6 @@ out:
 	 */
 	if (!for_reloc && !root_dropped)
 		btrfs_add_dead_root(root);
-	if (err && err != -EAGAIN)
-		btrfs_handle_fs_error(fs_info, err, NULL);
 	return err;
 }
 
Signature · 1 line
2.25.1
author maintainer
#280 lore raw

PATCH 280/388 gpio: rcar: Fix runtime PM imbalance on error

In reply to Greg Kroah-Hartman

From: Dinghao Liu <[email protected]>

[ Upstream commit 6f8cd246411575703d9312888b70705c396b53a9 ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/gpio/gpio-rcar.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpio/gpio-rcar.c +3 -1
index 187984d26f47a..f0b6c68e848e3 100644
@@ -250,8 +250,10 @@ static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset)
 	int error;
 
 	error = pm_runtime_get_sync(p->dev);
-	if (error < 0)
+	if (error < 0) {
+		pm_runtime_put(p->dev);
 		return error;
+	}
 
 	error = pinctrl_gpio_request(chip->base + offset);
 	if (error)
Signature · 1 line
2.25.1
author maintainer
#279 lore raw

PATCH 279/388 btrfs: fix double __endio_write_update_ordered in direct I/O

In reply to Greg Kroah-Hartman

From: Omar Sandoval <[email protected]>

[ Upstream commit c36cac28cb94e58f7e21ff43bdc6064346dab32c ]

In btrfs_submit_direct(), if we fail to allocate the btrfs_dio_private, we complete the ordered extent range. However, we don't mark that the range doesn't need to be cleaned up from btrfs_direct_IO() until later. Therefore, if we fail to allocate the btrfs_dio_private, we complete the ordered extent range twice. We could fix this by updating unsubmitted_oe_range earlier, but it's cleaner to reorganize the code so that creating the btrfs_dio_private and submitting the bios are separate, and once the btrfs_dio_private is created, cleanup always happens through the btrfs_dio_private.

The logic around unsubmitted_oe_range_end and unsubmitted_oe_range_start is really subtle. We have the following:

1. btrfs_direct_IO sets those two to the same value.

2. When we call __blockdev_direct_IO unless btrfs_get_blocks_direct->btrfs_get_blocks_direct_write is called to modify unsubmitted_oe_range_start so that start < end. Cleanup won't happen.

3. We come into btrfs_submit_direct - if it dip allocation fails we'd return with oe_range_end now modified so cleanup will happen.

4. If we manage to allocate the dip we reset the unsubmitted range members to be equal so that cleanup happens from btrfs_endio_direct_write.

This 4-step logic is not really obvious, especially given it's scattered across 3 functions.

Fixes f28a49287817 ("Btrfs: fix leaking of ordered extents after direct IO write error")
[ add range start/end logic explanation from Nikolay ]
---
 fs/btrfs/inode.c | 178 +++++++++++++++++++----------------------------
 1 file changed, 70 insertions(+), 108 deletions(-)
fs/btrfs/inode.c +70 -108
index 9ac40991a6405..e9787b7b943a2 100644
@@ -8586,14 +8586,64 @@ err:
 	return ret;
 }
 
-static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
+/*
+ * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked
+ * or ordered extents whether or not we submit any bios.
+ */
+static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
+							  struct inode *inode,
+							  loff_t file_offset)
 {
-	struct inode *inode = dip->inode;
+	const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
+	struct btrfs_dio_private *dip;
+	struct bio *bio;
+
+	dip = kzalloc(sizeof(*dip), GFP_NOFS);
+	if (!dip)
+		return NULL;
+
+	bio = btrfs_bio_clone(dio_bio);
+	bio->bi_private = dip;
+	btrfs_io_bio(bio)->logical = file_offset;
+
+	dip->private = dio_bio->bi_private;
+	dip->inode = inode;
+	dip->logical_offset = file_offset;
+	dip->bytes = dio_bio->bi_iter.bi_size;
+	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
+	dip->orig_bio = bio;
+	dip->dio_bio = dio_bio;
+	atomic_set(&dip->pending_bios, 1);
+
+	if (write) {
+		struct btrfs_dio_data *dio_data = current->journal_info;
+
+		/*
+		 * Setting range start and end to the same value means that
+		 * no cleanup will happen in btrfs_direct_IO
+		 */
+		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
+			dip->bytes;
+		dio_data->unsubmitted_oe_range_start =
+			dio_data->unsubmitted_oe_range_end;
+
+		bio->bi_end_io = btrfs_endio_direct_write;
+	} else {
+		bio->bi_end_io = btrfs_endio_direct_read;
+		dip->subio_endio = btrfs_subio_endio_read;
+	}
+	return dip;
+}
+
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+				loff_t file_offset)
+{
+	const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_dio_private *dip;
 	struct bio *bio;
-	struct bio *orig_bio = dip->orig_bio;
-	u64 start_sector = orig_bio->bi_iter.bi_sector;
-	u64 file_offset = dip->logical_offset;
+	struct bio *orig_bio;
+	u64 start_sector;
 	int async_submit = 0;
 	u64 submit_len;
 	int clone_offset = 0;
@@ -8602,11 +8652,24 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 	blk_status_t status;
 	struct btrfs_io_geometry geom;
 
+	dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
+	if (!dip) {
+		if (!write) {
+			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+				file_offset + dio_bio->bi_iter.bi_size - 1);
+		}
+		dio_bio->bi_status = BLK_STS_RESOURCE;
+		dio_end_io(dio_bio);
+		return;
+	}
+
+	orig_bio = dip->orig_bio;
+	start_sector = orig_bio->bi_iter.bi_sector;
 	submit_len = orig_bio->bi_iter.bi_size;
 	ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio),
 				    start_sector << 9, submit_len, &geom);
 	if (ret)
-		return -EIO;
+		goto out_err;
 
 	if (geom.len >= submit_len) {
 		bio = orig_bio;
@@ -8669,7 +8732,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
 submit:
 	status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
 	if (!status)
-		return 0;
+		return;
 
 	if (bio != orig_bio)
 		bio_put(bio);
@@ -8683,107 +8746,6 @@ out_err:
 	 */
 	if (atomic_dec_and_test(&dip->pending_bios))
 		bio_io_error(dip->orig_bio);
-
-	/* bio_end_io() will handle error, so we needn't return it */
-	return 0;
-}
-
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
-				loff_t file_offset)
-{
-	struct btrfs_dio_private *dip = NULL;
-	struct bio *bio = NULL;
-	struct btrfs_io_bio *io_bio;
-	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
-	int ret = 0;
-
-	bio = btrfs_bio_clone(dio_bio);
-
-	dip = kzalloc(sizeof(*dip), GFP_NOFS);
-	if (!dip) {
-		ret = -ENOMEM;
-		goto free_ordered;
-	}
-
-	dip->private = dio_bio->bi_private;
-	dip->inode = inode;
-	dip->logical_offset = file_offset;
-	dip->bytes = dio_bio->bi_iter.bi_size;
-	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
-	bio->bi_private = dip;
-	dip->orig_bio = bio;
-	dip->dio_bio = dio_bio;
-	atomic_set(&dip->pending_bios, 1);
-	io_bio = btrfs_io_bio(bio);
-	io_bio->logical = file_offset;
-
-	if (write) {
-		bio->bi_end_io = btrfs_endio_direct_write;
-	} else {
-		bio->bi_end_io = btrfs_endio_direct_read;
-		dip->subio_endio = btrfs_subio_endio_read;
-	}
-
-	/*
-	 * Reset the range for unsubmitted ordered extents (to a 0 length range)
-	 * even if we fail to submit a bio, because in such case we do the
-	 * corresponding error handling below and it must not be done a second
-	 * time by btrfs_direct_IO().
-	 */
-	if (write) {
-		struct btrfs_dio_data *dio_data = current->journal_info;
-
-		dio_data->unsubmitted_oe_range_end = dip->logical_offset +
-			dip->bytes;
-		dio_data->unsubmitted_oe_range_start =
-			dio_data->unsubmitted_oe_range_end;
-	}
-
-	ret = btrfs_submit_direct_hook(dip);
-	if (!ret)
-		return;
-
-	btrfs_io_bio_free_csum(io_bio);
-
-free_ordered:
-	/*
-	 * If we arrived here it means either we failed to submit the dip
-	 * or we either failed to clone the dio_bio or failed to allocate the
-	 * dip. If we cloned the dio_bio and allocated the dip, we can just
-	 * call bio_endio against our io_bio so that we get proper resource
-	 * cleanup if we fail to submit the dip, otherwise, we must do the
-	 * same as btrfs_endio_direct_[write|read] because we can't call these
-	 * callbacks - they require an allocated dip and a clone of dio_bio.
-	 */
-	if (bio && dip) {
-		bio_io_error(bio);
-		/*
-		 * The end io callbacks free our dip, do the final put on bio
-		 * and all the cleanup and final put for dio_bio (through
-		 * dio_end_io()).
-		 */
-		dip = NULL;
-		bio = NULL;
-	} else {
-		if (write)
-			__endio_write_update_ordered(inode,
-						file_offset,
-						dio_bio->bi_iter.bi_size,
-						false);
-		else
-			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
-			      file_offset + dio_bio->bi_iter.bi_size - 1);
-
-		dio_bio->bi_status = BLK_STS_IOERR;
-		/*
-		 * Releases and cleans up our dio_bio, no need to bio_put()
-		 * nor bio_endio()/bio_io_error() against dio_bio.
-		 */
-		dio_end_io(dio_bio);
-	}
-	if (bio)
-		bio_put(bio);
-	kfree(dip);
 }
 
 static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
Signature · 1 line
2.25.1
author maintainer
#277 lore raw

PATCH 277/388 usb: dwc3: Increase timeout for CmdAct cleared by device controller

In reply to Greg Kroah-Hartman

From: Yu Chen <[email protected]>

[ Upstream commit 1c0e69ae1b9f9004fd72978612ae3463791edc56 ]

If the SS PHY is in P3, there is no pipe_clk, HW may use suspend_clk for function, as suspend_clk is slow so EP command need more time to complete, e.g, imx8M suspend_clk is 32K, set ep configuration will take about 380us per below trace time stamp(44.286278 - 44.285897 = 0.000381):

configfs_acm.sh-822 [000] d..1 44.285896: dwc3_writel: addr
000000006d59aae1 value 00000401
configfs_acm.sh-822 [000] d..1 44.285897: dwc3_readl: addr
000000006d59aae1 value 00000401
... ...
configfs_acm.sh-822 [000] d..1 44.286278: dwc3_readl: addr
000000006d59aae1 value 00000001
configfs_acm.sh-822 [000] d..1 44.286279: dwc3_gadget_ep_cmd:
ep0out: cmd 'Set Endpoint Configuration' [401] params 00001000 00000500 00000000 --> status: Successful

This was originally found on Hisilicon Kirin Soc that need more time for the device controller to clear the CmdAct of DEPCMD.

---
 drivers/usb/dwc3/gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/dwc3/gadget.c +1 -1
index 4225544342519..809103254fc64 100644
@@ -270,7 +270,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned cmd,
 {
 	const struct usb_endpoint_descriptor *desc = dep->endpoint.desc;
 	struct dwc3		*dwc = dep->dwc;
-	u32			timeout = 1000;
+	u32			timeout = 5000;
 	u32			saved_config = 0;
 	u32			reg;
 
Signature · 1 line
2.25.1
author maintainer
#249 lore raw

PATCH 249/388 perf mem2node: Avoid double free related to realloc

In reply to Greg Kroah-Hartman

From: Ian Rogers <[email protected]>

[ Upstream commit 266150c94c69429cf6d18e130237224a047f5061 ]

Realloc of size zero is a free not an error, avoid this causing a double free. Caught by clang's address sanitizer:

==2634==ERROR: AddressSanitizer: attempting double-free on 0x6020000015f0 in thread T0:

    #0 0x5649659297fd in free llvm/llvm-project/compiler-rt/lib/asan/asan_malloc_linux.cpp:123:3
    #1 0x5649659e9251 in __zfree tools/lib/zalloc.c:13:2
    #2 0x564965c0f92c in mem2node__exit tools/perf/util/mem2node.c:114:2
    #3 0x564965a08b4c in perf_c2c__report tools/perf/builtin-c2c.c:2867:2
    #4 0x564965a0616a in cmd_c2c tools/perf/builtin-c2c.c:2989:10
    #5 0x564965944348 in run_builtin tools/perf/perf.c:312:11
    #6 0x564965943235 in handle_internal_command tools/perf/perf.c:364:8
    #7 0x5649659440c4 in run_argv tools/perf/perf.c:408:2
    #8 0x564965942e41 in main tools/perf/perf.c:538:3

0x6020000015f0 is located 0 bytes inside of 1-byte region [0x6020000015f0,0x6020000015f1) freed by thread T0 here:

    #0 0x564965929da3 in realloc third_party/llvm/llvm-project/compiler-rt/lib/asan/asan_malloc_linux.cpp:164:3
    #1 0x564965c0f55e in mem2node__init tools/perf/util/mem2node.c:97:16
    #2 0x564965a08956 in perf_c2c__report tools/perf/builtin-c2c.c:2803:8
    #3 0x564965a0616a in cmd_c2c tools/perf/builtin-c2c.c:2989:10
    #4 0x564965944348 in run_builtin tools/perf/perf.c:312:11
    #5 0x564965943235 in handle_internal_command tools/perf/perf.c:364:8
    #6 0x5649659440c4 in run_argv tools/perf/perf.c:408:2
    #7 0x564965942e41 in main tools/perf/perf.c:538:3

previously allocated by thread T0 here:

    #0 0x564965929c42 in calloc third_party/llvm/llvm-project/compiler-rt/lib/asan/asan_malloc_linux.cpp:154:3
    #1 0x5649659e9220 in zalloc tools/lib/zalloc.c:8:9
    #2 0x564965c0f32d in mem2node__init tools/perf/util/mem2node.c:61:12
    #3 0x564965a08956 in perf_c2c__report tools/perf/builtin-c2c.c:2803:8
    #4 0x564965a0616a in cmd_c2c tools/perf/builtin-c2c.c:2989:10
    #5 0x564965944348 in run_builtin tools/perf/perf.c:312:11
    #6 0x564965943235 in handle_internal_command tools/perf/perf.c:364:8
    #7 0x5649659440c4 in run_argv tools/perf/perf.c:408:2
    #8 0x564965942e41 in main tools/perf/perf.c:538:3

v2: add a WARN_ON_ONCE when the free condition arises.

---
 tools/perf/util/mem2node.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/util/mem2node.c +2 -1
index 797d86a1ab095..c84f5841c7abd 100644
@@ -1,5 +1,6 @@
 #include <errno.h>
 #include <inttypes.h>
+#include <asm/bug.h>
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
@@ -95,7 +96,7 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
 
 	/* Cut unused entries, due to merging. */
 	tmp_entries = realloc(entries, sizeof(*entries) * j);
-	if (tmp_entries)
+	if (tmp_entries || WARN_ON_ONCE(j == 0))
 		entries = tmp_entries;
 
 	for (i = 0; i < j; i++) {
Signature · 1 line
2.25.1
author maintainer
#256 lore raw

PATCH 256/388 KVM: x86: handle wrap around 32-bit address space

In reply to Greg Kroah-Hartman

From: Paolo Bonzini <[email protected]>

[ Upstream commit fede8076aab4c2280c673492f8f7a2e87712e8b4 ]

KVM is not handling the case where EIP wraps around the 32-bit address space (that is, outside long mode). This is needed both in vmx.c and in emulate.c. SVM with NRIPS is okay, but it can still print an error to dmesg due to integer overflow.

---
 arch/x86/kvm/emulate.c |  2 ++
 arch/x86/kvm/svm.c     |  3 ---
 arch/x86/kvm/vmx/vmx.c | 15 ++++++++++++---
 3 files changed, 14 insertions(+), 6 deletions(-)
arch/x86/kvm/emulate.c +2 -0
index 128d3ad46e965..cc7823e7ef96c 100644
@@ -5836,6 +5836,8 @@ writeback:
 	}
 
 	ctxt->eip = ctxt->_eip;
+	if (ctxt->mode != X86EMUL_MODE_PROT64)
+		ctxt->eip = (u32)ctxt->_eip;
 
 done:
 	if (rc == X86EMUL_PROPAGATE_FAULT) {
arch/x86/kvm/svm.c +0 -3
index 3243a80ea32c0..802b5f9ab7446 100644
@@ -787,9 +787,6 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
 			return 0;
 	} else {
-		if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
-			pr_err("%s: ip 0x%lx next 0x%llx\n",
-			       __func__, kvm_rip_read(vcpu), svm->next_rip);
 		kvm_rip_write(vcpu, svm->next_rip);
 	}
 	svm_set_interrupt_shadow(vcpu, 0);
arch/x86/kvm/vmx/vmx.c +12 -3
index d4a364db27ee8..2a1ed3aae100e 100644
@@ -1541,7 +1541,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
 
 static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
-	unsigned long rip;
+	unsigned long rip, orig_rip;
 
 	/*
 	 * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on
@@ -1553,8 +1553,17 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	 */
 	if (!static_cpu_has(X86_FEATURE_HYPERVISOR) ||
 	    to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) {
-		rip = kvm_rip_read(vcpu);
-		rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		orig_rip = kvm_rip_read(vcpu);
+		rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+#ifdef CONFIG_X86_64
+		/*
+		 * We need to mask out the high 32 bits of RIP if not in 64-bit
+		 * mode, but just finding out that we are in 64-bit mode is
+		 * quite expensive.  Only do it if there was a carry.
+		 */
+		if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu))
+			rip = (u32)rip;
+#endif
 		kvm_rip_write(vcpu, rip);
 	} else {
 		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
Signature · 1 line
2.25.1
author maintainer
#258 lore raw

PATCH 258/388 tty: serial: samsung: Correct clock selection logic

In reply to Greg Kroah-Hartman

From: Jonathan Bakker <[email protected]>

[ Upstream commit 7d31676a8d91dd18e08853efd1cb26961a38c6a6 ]

Some variants of the samsung tty driver can pick which clock to use for their baud rate generation. In the DT conversion, a default clock was selected to be used if a specific one wasn't assigned and then a comparison of which clock rate worked better was done. Unfortunately, the comparison was implemented in such a way that only the default clock was ever actually compared. Fix this by iterating through all possible clocks, except when a specific clock has already been picked via clk_sel (which is only possible via board files).

---
 drivers/tty/serial/samsung.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/tty/serial/samsung.c +4 -4
index 71f99e9217592..c7683beb3412a 100644
@@ -1187,14 +1187,14 @@ static unsigned int s3c24xx_serial_getclk(struct s3c24xx_uart_port *ourport,
 	struct s3c24xx_uart_info *info = ourport->info;
 	struct clk *clk;
 	unsigned long rate;
-	unsigned int cnt, baud, quot, clk_sel, best_quot = 0;
+	unsigned int cnt, baud, quot, best_quot = 0;
 	char clkname[MAX_CLK_NAME_LENGTH];
 	int calc_deviation, deviation = (1 << 30) - 1;
 
-	clk_sel = (ourport->cfg->clk_sel) ? ourport->cfg->clk_sel :
-			ourport->info->def_clk_sel;
 	for (cnt = 0; cnt < info->num_clks; cnt++) {
-		if (!(clk_sel & (1 << cnt)))
+		/* Keep selected clock if provided */
+		if (ourport->cfg->clk_sel &&
+			!(ourport->cfg->clk_sel & (1 << cnt)))
 			continue;
 
 		sprintf(clkname, "clk_uart_baud%d", cnt);
Signature · 1 line
2.25.1
author maintainer
#257 lore raw

PATCH 257/388 tipc: fix memory leak in service subscripting

In reply to Greg Kroah-Hartman

From: Tuong Lien <[email protected]>

[ Upstream commit 0771d7df819284d46cf5cfb57698621b503ec17f ]

Upon receipt of a service subscription request from user via a topology connection, one 'sub' object will be allocated in kernel, so it will be able to send an event of the service if any to the user correspondingly then. Also, in case of any failure, the connection will be shutdown and all the pertaining 'sub' objects will be freed.

However, there is a race condition as follows resulting in memory leak:

       receive-work       connection        send-work
              |                |                |
        sub-1 |<------//-------|                |
        sub-2 |<------//-------|                |
              |                |<---------------| evt for sub-x
        sub-3 |<------//-------|                |
              :                :                :
              :                :                :
              |       /--------|                |
              |       |        * peer closed    |
              |       |        |                |
              |       |        |<-------X-------| evt for sub-y
              |       |        |<===============|
        sub-n |<------/        X    shutdown    |
    -> orphan |                                 |

That is, the 'receive-work' may get the last subscription request while the 'send-work' is shutting down the connection due to peer close.

We had a 'lock' on the connection, so the two actions cannot be carried out simultaneously. If the last subscription is allocated e.g. 'sub-n', before the 'send-work' closes the connection, there will be no issue at all, the 'sub' objects will be freed. In contrast the last subscription will become orphan since the connection was closed, and we released all references.

This commit fixes the issue by simply adding one test if the connection remains in 'connected' state right after we obtain the connection lock, then a subscription object can be created as usual, otherwise we ignore it.

---
 net/tipc/topsrv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
net/tipc/topsrv.c +3 -1
index 73dbed0c4b6b8..931c426673c02 100644
@@ -400,7 +400,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 		return -EWOULDBLOCK;
 	if (ret == sizeof(s)) {
 		read_lock_bh(&sk->sk_callback_lock);
-		ret = tipc_conn_rcv_sub(srv, con, &s);
+		/* RACE: the connection can be closed in the meantime */
+		if (likely(connected(con)))
+			ret = tipc_conn_rcv_sub(srv, con, &s);
 		read_unlock_bh(&sk->sk_callback_lock);
 		if (!ret)
 			return 0;
Signature · 1 line
2.25.1
author maintainer
#294 lore raw

PATCH 294/388 mtd: rawnand: omap_elm: Fix runtime PM imbalance on error

In reply to Greg Kroah-Hartman

From: Dinghao Liu <[email protected]>

[ Upstream commit 37f7212148cf1d796135cdf8d0c7fee13067674b ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/mtd/nand/raw/omap_elm.c | 1 +
 1 file changed, 1 insertion(+)
drivers/mtd/nand/raw/omap_elm.c +1 -0
index 5502ffbdd1e6d..6e0e31eab7cce 100644
@@ -411,6 +411,7 @@ static int elm_probe(struct platform_device *pdev)
 	pm_runtime_enable(&pdev->dev);
 	if (pm_runtime_get_sync(&pdev->dev) < 0) {
 		ret = -EINVAL;
+		pm_runtime_put_sync(&pdev->dev);
 		pm_runtime_disable(&pdev->dev);
 		dev_err(&pdev->dev, "can't enable clock\n");
 		return ret;
Signature · 1 line
2.25.1
author maintainer
#296 lore raw

PATCH 296/388 ceph: fix potential race in ceph_check_caps

In reply to Greg Kroah-Hartman

From: Jeff Layton <[email protected]>

[ Upstream commit dc3da0461cc4b76f2d0c5b12247fcb3b520edbbf ]

Nothing ensures that session will still be valid by the time we dereference the pointer. Take and put a reference.

In principle, we should always be able to get a reference here, but throw a warning if that's ever not the case.

---
 fs/ceph/caps.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)
fs/ceph/caps.c +13 -1
index b2695919435e8..af563d73d252c 100644
@@ -2013,12 +2013,24 @@ ack:
 			if (mutex_trylock(&session->s_mutex) == 0) {
 				dout("inverting session/ino locks on %p\n",
 				     session);
+				session = ceph_get_mds_session(session);
 				spin_unlock(&ci->i_ceph_lock);
 				if (took_snap_rwsem) {
 					up_read(&mdsc->snap_rwsem);
 					took_snap_rwsem = 0;
 				}
-				mutex_lock(&session->s_mutex);
+				if (session) {
+					mutex_lock(&session->s_mutex);
+					ceph_put_mds_session(session);
+				} else {
+					/*
+					 * Because we take the reference while
+					 * holding the i_ceph_lock, it should
+					 * never be NULL. Throw a warning if it
+					 * ever is.
+					 */
+					WARN_ON_ONCE(true);
+				}
 				goto retry;
 			}
 		}
Signature · 1 line
2.25.1
author maintainer
#297 lore raw

PATCH 297/388 mm/swap_state: fix a data race in swapin_nr_pages

In reply to Greg Kroah-Hartman

From: Qian Cai <[email protected]>

[ Upstream commit d6c1f098f2a7ba62627c9bc17cda28f534ef9e4a ]

"prev_offset" is a static variable in swapin_nr_pages() that can be accessed concurrently with only mmap_sem held in read mode as noticed by KCSAN,

 BUG: KCSAN: data-race in swap_cluster_readahead / swap_cluster_readahead

write to 0xffffffff92763830 of 8 bytes by task 14795 on cpu 17:

  swap_cluster_readahead+0x2a6/0x5e0
  swapin_readahead+0x92/0x8dc
  do_swap_page+0x49b/0xf20
  __handle_mm_fault+0xcfb/0xd70
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x715
  page_fault+0x34/0x40

1 lock held by (dnf)/14795:
#0: ffff897bd2e98858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715 do_user_addr_fault at arch/x86/mm/fault.c:1405
(inlined by) do_page_fault at arch/x86/mm/fault.c:1535

 irq event stamp: 83493
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x365/0x589
 irq_exit+0xa2/0xc0

read to 0xffffffff92763830 of 8 bytes by task 1 on cpu 22:

  swap_cluster_readahead+0xfd/0x5e0
  swapin_readahead+0x92/0x8dc
  do_swap_page+0x49b/0xf20
  __handle_mm_fault+0xcfb/0xd70
  handle_mm_fault+0xfc/0x2f0
  do_page_fault+0x263/0x715
  page_fault+0x34/0x40

1 lock held by systemd/1:
#0: ffff897c38f14858 (&mm->mmap_sem#2){++++}-{3:3}, at: do_page_fault+0x143/0x715

 irq event stamp: 43530289
 count_memcg_event_mm+0x1a6/0x270
 count_memcg_event_mm+0x119/0x270
 __do_softirq+0x365/0x589
 irq_exit+0xa2/0xc0
---
 mm/swap_state.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
mm/swap_state.c +3 -2
index 4ce014dc4571a..7c434fcfff0dd 100644
@@ -511,10 +511,11 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 		return 1;
 
 	hits = atomic_xchg(&swapin_readahead_hits, 0);
-	pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages,
+	pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits,
+				  max_pages,
 				  atomic_read(&last_readahead_pages));
 	if (!hits)
-		prev_offset = offset;
+		WRITE_ONCE(prev_offset, offset);
 	atomic_set(&last_readahead_pages, pages);
 
 	return pages;
Signature · 1 line
2.25.1
author maintainer
#295 lore raw

PATCH 295/388 PCI: tegra: Fix runtime PM imbalance on error

In reply to Greg Kroah-Hartman

From: Dinghao Liu <[email protected]>

[ Upstream commit fcee90cdf6f3a3a371add04d41528d5ba9c3b411 ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

Also, call pm_runtime_disable() when pm_runtime_get_sync() returns an error code.

---
 drivers/pci/controller/pci-tegra.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/pci/controller/pci-tegra.c +1 -2
index b71e753419c2d..cfa3c83d6cc74 100644
@@ -2768,7 +2768,7 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 	err = pm_runtime_get_sync(pcie->dev);
 	if (err < 0) {
 		dev_err(dev, "fail to enable pcie controller: %d\n", err);
-		goto teardown_msi;
+		goto pm_runtime_put;
 	}
 
 	err = tegra_pcie_request_resources(pcie);
@@ -2808,7 +2808,6 @@ free_resources:
 pm_runtime_put:
 	pm_runtime_put_sync(pcie->dev);
 	pm_runtime_disable(pcie->dev);
-teardown_msi:
 	tegra_pcie_msi_teardown(pcie);
 put_resources:
 	tegra_pcie_put_resources(pcie);
Signature · 1 line
2.25.1
author maintainer
#299 lore raw

PATCH 299/388 rapidio: avoid data race between file operation callbacks and mport_cdev_add().

In reply to Greg Kroah-Hartman

From: Madhuparna Bhowmik <[email protected]>

[ Upstream commit e1c3cdb26ab881b77486dc50370356a349077c74 ]

Fields of md(mport_dev) are set after cdev_device_add(). However, the file operation callbacks can be called after cdev_device_add() and therefore accesses to fields of md in the callbacks can race with the rest of the mport_cdev_add() function.

One such example is INIT_LIST_HEAD(&md->portwrites) in mport_cdev_add(), the list is initialised after cdev_device_add(). This can race with list_add_tail(&pw_filter->md_node,&md->portwrites) in rio_mport_add_pw_filter() which is called by unlocked_ioctl.

To avoid such data races use cdev_device_add() after initializing md.

Found by Linux Driver Verification project (linuxtesting.org).

---
 drivers/rapidio/devices/rio_mport_cdev.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/rapidio/devices/rio_mport_cdev.c +7 -7
index 10af330153b5e..0b85a80ae7ef6 100644
@@ -2384,13 +2384,6 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 	cdev_init(&md->cdev, &mport_fops);
 	md->cdev.owner = THIS_MODULE;
 
-	ret = cdev_device_add(&md->cdev, &md->dev);
-	if (ret) {
-		rmcd_error("Failed to register mport %d (err=%d)",
-		       mport->id, ret);
-		goto err_cdev;
-	}
-
 	INIT_LIST_HEAD(&md->doorbells);
 	spin_lock_init(&md->db_lock);
 	INIT_LIST_HEAD(&md->portwrites);
@@ -2410,6 +2403,13 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport)
 #else
 	md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER;
 #endif
+
+	ret = cdev_device_add(&md->cdev, &md->dev);
+	if (ret) {
+		rmcd_error("Failed to register mport %d (err=%d)",
+		       mport->id, ret);
+		goto err_cdev;
+	}
 	ret = rio_query_mport(mport, &attr);
 	if (!ret) {
 		md->properties.flags = attr.flags;
Signature · 1 line
2.25.1
author maintainer
#301 lore raw

PATCH 301/388 x86/speculation/mds: Mark mds_user_clear_cpu_buffers() __always_inline

In reply to Greg Kroah-Hartman

From: Thomas Gleixner <[email protected]>

[ Upstream commit a7ef9ba986b5fae9d80f8a7b31db0423687efe4e ]

Prevent the compiler from uninlining and creating traceable/probable functions as this is invoked _after_ context tracking switched to CONTEXT_USER and rcu idle.

---
 arch/x86/include/asm/nospec-branch.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/include/asm/nospec-branch.h +2 -2
index 5c24a7b351665..b222a35959467 100644
@@ -320,7 +320,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
  * combination with microcode which triggers a CPU buffer flush when the
  * instruction is executed.
  */
-static inline void mds_clear_cpu_buffers(void)
+static __always_inline void mds_clear_cpu_buffers(void)
 {
 	static const u16 ds = __KERNEL_DS;
 
@@ -341,7 +341,7 @@ static inline void mds_clear_cpu_buffers(void)
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static inline void mds_user_clear_cpu_buffers(void)
+static __always_inline void mds_user_clear_cpu_buffers(void)
 {
 	if (static_branch_likely(&mds_user_clear))
 		mds_clear_cpu_buffers();
Signature · 1 line
2.25.1
author maintainer
#270 lore raw

PATCH 270/388 arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register

In reply to Greg Kroah-Hartman

From: Anshuman Khandual <[email protected]>

[ Upstream commit 1ed1b90a0594c8c9d31e8bb8be25a2b37717dc9e ]

ID_DFR0 based TraceFilt feature should not be exposed to guests. Hence lets drop it.

Cc Catalin Marinas <[email protected]>
Cc Will Deacon <[email protected]>
Cc Marc Zyngier <[email protected]>
Cc Mark Rutland <[email protected]>
Cc James Morse <[email protected]>
Cc Suzuki K Poulose <[email protected]>
---
 arch/arm64/kernel/cpufeature.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/kernel/cpufeature.c +1 -1
index 1df57ffc9314d..f2ec845404149 100644
@@ -319,7 +319,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
+	/* [31:28] TraceFilt */
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0),
Signature · 9 lines
2.25.1




_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
author maintainer
#303 lore raw

PATCH 303/388 vfio/pci: Clear error and request eventfd ctx after releasing

In reply to Greg Kroah-Hartman

From: Alex Williamson <[email protected]>

[ Upstream commit 5c5866c593bbd444d0339ede6a8fb5f14ff66d72 ]

The next use of the device will generate an underflow from the stale reference.

Cc Qian Cai <[email protected]>
Fixes 1518ac272e78 ("vfio/pci: fix memory leaks of eventfd ctx")
---
 drivers/vfio/pci/vfio_pci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/vfio/pci/vfio_pci.c +6 -2
index 12f7691e8b6ca..b669be5a20066 100644
@@ -474,10 +474,14 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
-		if (vdev->err_trigger)
+		if (vdev->err_trigger) {
 			eventfd_ctx_put(vdev->err_trigger);
-		if (vdev->req_trigger)
+			vdev->err_trigger = NULL;
+		}
+		if (vdev->req_trigger) {
 			eventfd_ctx_put(vdev->req_trigger);
+			vdev->req_trigger = NULL;
+		}
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
Signature · 1 line
2.25.1
author maintainer
#302 lore raw

PATCH 302/388 NFS: nfs_xdr_status should record the procedure name

In reply to Greg Kroah-Hartman

From: Chuck Lever <[email protected]>

[ Upstream commit 5be5945864ea143fda628e8179c8474457af1f43 ]

When sunrpc trace points are not enabled, the recorded task ID information alone is not helpful.

---
 fs/nfs/nfstrace.h | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)
fs/nfs/nfstrace.h +13 -2
index 361cc10d6f95d..c8081d2b4166a 100644
@@ -1147,7 +1147,12 @@ TRACE_EVENT(nfs_xdr_status,
 			__field(unsigned int, task_id)
 			__field(unsigned int, client_id)
 			__field(u32, xid)
+			__field(int, version)
 			__field(unsigned long, error)
+			__string(program,
+				 xdr->rqst->rq_task->tk_client->cl_program->name)
+			__string(procedure,
+				 xdr->rqst->rq_task->tk_msg.rpc_proc->p_name)
 		),
 
 		TP_fast_assign(
@@ -1157,13 +1162,19 @@ TRACE_EVENT(nfs_xdr_status,
 			__entry->task_id = task->tk_pid;
 			__entry->client_id = task->tk_client->cl_clid;
 			__entry->xid = be32_to_cpu(rqstp->rq_xid);
+			__entry->version = task->tk_client->cl_vers;
 			__entry->error = error;
+			__assign_str(program,
+				     task->tk_client->cl_program->name)
+			__assign_str(procedure, task->tk_msg.rpc_proc->p_name)
 		),
 
 		TP_printk(
-			"task:%u@%d xid=0x%08x error=%ld (%s)",
+			"task:%u@%d xid=0x%08x %sv%d %s error=%ld (%s)",
 			__entry->task_id, __entry->client_id, __entry->xid,
-			-__entry->error, nfs_show_status(__entry->error)
+			__get_str(program), __entry->version,
+			__get_str(procedure), -__entry->error,
+			nfs_show_status(__entry->error)
 		)
 );
 
Signature · 1 line
2.25.1
author maintainer
#283 lore raw

PATCH 283/388 perf evsel: Fix 2 memory leaks

In reply to Greg Kroah-Hartman

From: Ian Rogers <[email protected]>

[ Upstream commit 3efc899d9afb3d03604f191a0be9669eabbfc4aa ]

If allocated, perf_pkg_mask and metric_events need freeing.

---
 tools/perf/util/evsel.c | 2 ++
 1 file changed, 2 insertions(+)
tools/perf/util/evsel.c +2 -0
index 12b1755b136d3..9dd9e3f4ef591 100644
@@ -1255,6 +1255,8 @@ void perf_evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
+	zfree(&evsel->per_pkg_mask);
+	zfree(&evsel->metric_events);
 	perf_evsel__object.fini(evsel);
 }
 
Signature · 1 line
2.25.1
author maintainer
#300 lore raw

PATCH 300/388 mtd: parser: cmdline: Support MTD names containing one or more colons

In reply to Greg Kroah-Hartman

From: Boris Brezillon <[email protected]>

[ Upstream commit eb13fa0227417e84aecc3bd9c029d376e33474d3 ]

Looks like some drivers define MTD names with a colon in it, thus making mtdpart= parsing impossible. Let's fix the parser to gracefully handle that case: the last ':' in a partition definition sequence is considered instead of the first one.

---
 drivers/mtd/parsers/cmdlinepart.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
drivers/mtd/parsers/cmdlinepart.c +20 -3
index c86f2db8c882d..0625b25620ca7 100644
@@ -218,12 +218,29 @@ static int mtdpart_setup_real(char *s)
 		struct cmdline_mtd_partition *this_mtd;
 		struct mtd_partition *parts;
 		int mtd_id_len, num_parts;
-		char *p, *mtd_id;
+		char *p, *mtd_id, *semicol;
+
+		/*
+		 * Replace the first ';' by a NULL char so strrchr can work
+		 * properly.
+		 */
+		semicol = strchr(s, ';');
+		if (semicol)
+			*semicol = '\0';
 
 		mtd_id = s;
 
-		/* fetch <mtd-id> */
-		p = strchr(s, ':');
+		/*
+		 * fetch <mtd-id>. We use strrchr to ignore all ':' that could
+		 * be present in the MTD name, only the last one is interpreted
+		 * as an <mtd-id>/<part-definition> separator.
+		 */
+		p = strrchr(s, ':');
+
+		/* Restore the ';' now. */
+		if (semicol)
+			*semicol = ';';
+
 		if (!p) {
 			pr_err("no mtd-id\n");
 			return -EINVAL;
Signature · 1 line
2.25.1
author maintainer
#311 lore raw

PATCH 311/388 btrfs: qgroup: fix data leak caused by race between writeback and truncate

In reply to Greg Kroah-Hartman

From: Qu Wenruo <[email protected]>

[ Upstream commit fa91e4aa1716004ea8096d5185ec0451e206aea0 ]

[BUG]
When running tests like generic/013 on test device with btrfs quota enabled, it can normally lead to data leak, detected at unmount time:

BTRFS warning (device dm-3): qgroup 0/5 has unreleased space, type 0 rsv 4096

  ------------[ cut here ]------------
  WARNING: CPU: 11 PID: 16386 at fs/btrfs/disk-io.c:4142 close_ctree+0x1dc/0x323 [btrfs]
  RIP: 0010:close_ctree+0x1dc/0x323 [btrfs]
  Call Trace:
   btrfs_put_super+0x15/0x17 [btrfs]
   generic_shutdown_super+0x72/0x110
   kill_anon_super+0x18/0x30
   btrfs_kill_super+0x17/0x30 [btrfs]
   deactivate_locked_super+0x3b/0xa0
   deactivate_super+0x40/0x50
   cleanup_mnt+0x135/0x190
   __cleanup_mnt+0x12/0x20
   task_work_run+0x64/0xb0
   __prepare_exit_to_usermode+0x1bc/0x1c0
   __syscall_return_slowpath+0x47/0x230
   do_syscall_64+0x64/0xb0
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  ---[ end trace caf08beafeca2392 ]---
  BTRFS error (device dm-3): qgroup reserved space leaked

[CAUSE]
In the offending case, the offending operations are:
2/6: writev f2X[269 1 0 0 0 0] [1006997,67,288] 0 2/7: truncate f2X[269 1 0 0 48 1026293] 18388 0

The following sequence of events could happen after the writev():

	CPU1 (writeback)		|		CPU2 (truncate)
-----------------------------------------------------------------
btrfs_writepages()			|
|- extent_write_cache_pages()		|
   |- Got page for 1003520		|
   |  1003520 is Dirty, no writeback	|
   |  So (!clear_page_dirty_for_io())   |
   |  gets called for it		|
   |- Now page 1003520 is Clean.	|
   |					| btrfs_setattr()
   |					| |- btrfs_setsize()
   |					|    |- truncate_setsize()
   |					|       New i_size is 18388
   |- __extent_writepage()		|
   |  |- page_offset() > i_size		|
      |- btrfs_invalidatepage()		|
	 |- Page is clean, so no qgroup |

callback executed

This means, the qgroup reserved data space is not properly released in btrfs_invalidatepage() as the page is Clean.

[FIX]
Instead of checking the dirty bit of a page, call btrfs_qgroup_free_data() unconditionally in btrfs_invalidatepage().

As qgroup rsv are completely bound to the QGROUP_RESERVED bit of io_tree, not bound to page status, thus we won't cause double freeing anyway.

Fixes 0b34c261e235 ("btrfs: qgroup: Prevent qgroup->reserved from going subzero")
---
 fs/btrfs/inode.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)
fs/btrfs/inode.c +10 -13
index e9787b7b943a2..182e93a5b11d5 100644
@@ -9044,20 +9044,17 @@ again:
 	/*
 	 * Qgroup reserved space handler
 	 * Page here will be either
-	 * 1) Already written to disk
-	 *    In this case, its reserved space is released from data rsv map
-	 *    and will be freed by delayed_ref handler finally.
-	 *    So even we call qgroup_free_data(), it won't decrease reserved
-	 *    space.
-	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here. However,
-	 *    if a truncate invalidates the page (by clearing PageDirty)
-	 *    and the page is accounted for while allocating extent
-	 *    in btrfs_check_data_free_space() we let delayed_ref to
-	 *    free the entire extent.
+	 * 1) Already written to disk or ordered extent already submitted
+	 *    Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+	 *    Qgroup will be handled by its qgroup_record then.
+	 *    btrfs_qgroup_free_data() call will do nothing here.
+	 *
+	 * 2) Not written to disk yet
+	 *    Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+	 *    bit of its io_tree, and free the qgroup reserved data space.
+	 *    Since the IO will never happen for this page.
 	 */
-	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED |
 				 EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
Signature · 1 line
2.25.1
author maintainer
#284 lore raw

PATCH 284/388 perf trace: Fix the selection for architectures to generate the errno name tables

In reply to Greg Kroah-Hartman

From: Ian Rogers <[email protected]>

[ Upstream commit 7597ce89b3ed239f7a3408b930d2a6c7a4c938a1 ]

Make the architecture test directory agree with the code comment.

Committer notes:

This was split from a larger patch.

The code was assuming the developer always worked from tools/perf/, so make sure we do the test -d having $toolsdir/perf/arch/$arch, to match the intent expressed in the comment, just above that loop.

Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Alexios Zavras <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Greg Kroah-Hartman <[email protected]>
Cc Igor Lubashev <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Kan Liang <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Mathieu Poirier <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Nick Desaulniers <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Stephane Eranian <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Wei Li <[email protected]>
---
 tools/perf/trace/beauty/arch_errno_names.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/trace/beauty/arch_errno_names.sh +1 -1
index 22c9fc900c847..f8c44a85650be 100755
@@ -91,7 +91,7 @@ EoHEADER
 # in tools/perf/arch
 archlist=""
 for arch in $(find $toolsdir/arch -maxdepth 1 -mindepth 1 -type d -printf "%f\n" | grep -v x86 | sort); do
-	test -d arch/$arch && archlist="$archlist $arch"
+	test -d $toolsdir/perf/arch/$arch && archlist="$archlist $arch"
 done
 
 for arch in x86 $archlist generic; do
Signature · 1 line
2.25.1
author maintainer
#287 lore raw

PATCH 287/388 perf metricgroup: Free metric_events on error

In reply to Greg Kroah-Hartman

From: Ian Rogers <[email protected]>

[ Upstream commit a159e2fe89b4d1f9fb54b0ae418b961e239bf617 ]

Avoid a simple memory leak.

Cc Alexander Shishkin <[email protected]>
Cc Alexei Starovoitov <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Andrii Nakryiko <[email protected]>
Cc Cong Wang <[email protected]>
Cc Daniel Borkmann <[email protected]>
Cc Jin Yao <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc John Fastabend <[email protected]>
Cc John Garry <[email protected]>
Cc Kajol Jain <[email protected]>
Cc Kan Liang <[email protected]>
Cc Kim Phillips <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Martin KaFai Lau <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Song Liu <[email protected]>
Cc Stephane Eranian <[email protected]>
Cc Vince Weaver <[email protected]>
Cc Yonghong Song <[email protected]>
Cc kp singh <[email protected]>
---
 tools/perf/util/metricgroup.c | 3 +++
 1 file changed, 3 insertions(+)
tools/perf/util/metricgroup.c +3 -0
index 940a6e7a68549..7753c3091478a 100644
@@ -174,6 +174,7 @@ static int metricgroup__setup_events(struct list_head *groups,
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
+			free(metric_events);
 			continue;
 		}
 		for (i = 0; i < eg->idnum; i++)
@@ -181,11 +182,13 @@ static int metricgroup__setup_events(struct list_head *groups,
 		me = metricgroup__lookup(metric_events_list, evsel, true);
 		if (!me) {
 			ret = -ENOMEM;
+			free(metric_events);
 			break;
 		}
 		expr = malloc(sizeof(struct metric_expr));
 		if (!expr) {
 			ret = -ENOMEM;
+			free(metric_events);
 			break;
 		}
 		expr->metric_expr = eg->metric_expr;
Signature · 1 line
2.25.1
author maintainer
#315 lore raw

PATCH 315/388 mt76: fix LED link time failure

In reply to Greg Kroah-Hartman

From: Arnd Bergmann <[email protected]>

[ Upstream commit d68f4e43a46ff1f772ff73085f96d44eb4163e9d ]

The mt76_led_cleanup() function is called unconditionally, which leads to a link error when CONFIG_LEDS is a loadable module or disabled but mt76 is built-in:

drivers/net/wireless/mediatek/mt76/mac80211.o: In function `mt76_unregister_device':
mac80211.c:(.text+0x2ac): undefined reference to `led_classdev_unregister'

Use the same trick that is guarding the registration, using an IS_ENABLED() check for the CONFIG_MT76_LEDS symbol that indicates whether LEDs can be used or not.

Fixes 36f7e2b2bb1d ("mt76: do not use devm API for led classdev")
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/mediatek/mt76/mac80211.c +2 -1
index 7be5806a1c398..8bd191347b9fb 100644
@@ -368,7 +368,8 @@ void mt76_unregister_device(struct mt76_dev *dev)
 {
 	struct ieee80211_hw *hw = dev->hw;
 
-	mt76_led_cleanup(dev);
+	if (IS_ENABLED(CONFIG_MT76_LEDS))
+		mt76_led_cleanup(dev);
 	mt76_tx_status_check(dev, NULL, true);
 	ieee80211_unregister_hw(hw);
 }
Signature · 1 line
2.25.1
author maintainer
#289 lore raw

PATCH 289/388 PCI: tegra194: Fix runtime PM imbalance on error

In reply to Greg Kroah-Hartman

From: Dinghao Liu <[email protected]>

[ Upstream commit 1c1dbb2c02623db18a50c61b175f19aead800b4e ]

pm_runtime_get_sync() increments the runtime PM usage counter even when it returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 drivers/pci/controller/dwc/pcie-tegra194.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/pci/controller/dwc/pcie-tegra194.c +2 -3
index f89f5acee72d4..c06b05ab9f787 100644
@@ -1395,7 +1395,7 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 	ret = pinctrl_pm_select_default_state(dev);
 	if (ret < 0) {
 		dev_err(dev, "Failed to configure sideband pins: %d\n", ret);
-		goto fail_pinctrl;
+		goto fail_pm_get_sync;
 	}
 
 	tegra_pcie_init_controller(pcie);
@@ -1422,9 +1422,8 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 
 fail_host_init:
 	tegra_pcie_deinit_controller(pcie);
-fail_pinctrl:
-	pm_runtime_put_sync(dev);
 fail_pm_get_sync:
+	pm_runtime_put_sync(dev);
 	pm_runtime_disable(dev);
 	return ret;
 }
Signature · 1 line
2.25.1
author maintainer
#290 lore raw

PATCH 290/388 ASoC: img-i2s-out: Fix runtime PM imbalance on error

In reply to Greg Kroah-Hartman

From: Dinghao Liu <[email protected]>

[ Upstream commit 65bd91dd6957390c42a0491b9622cf31a2cdb140 ]

pm_runtime_get_sync() increments the runtime PM usage counter even the call returns an error code. Thus a pairing decrement is needed on the error handling path to keep the counter balanced.

---
 sound/soc/img/img-i2s-out.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
sound/soc/img/img-i2s-out.c +6 -2
index 4b18534096336..9c4212f2f7269 100644
@@ -347,8 +347,10 @@ static int img_i2s_out_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	chan_control_mask = IMG_I2S_OUT_CHAN_CTL_CLKT_MASK;
 
 	ret = pm_runtime_get_sync(i2s->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(i2s->dev);
 		return ret;
+	}
 
 	img_i2s_out_disable(i2s);
 
@@ -488,8 +490,10 @@ static int img_i2s_out_probe(struct platform_device *pdev)
 			goto err_pm_disable;
 	}
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto err_suspend;
+	}
 
 	reg = IMG_I2S_OUT_CTL_FRM_SIZE_MASK;
 	img_i2s_out_writel(i2s, reg, IMG_I2S_OUT_CTL);
Signature · 1 line
2.25.1
author maintainer
#281 lore raw

PATCH 281/388 vfio/pci: fix memory leaks of eventfd ctx

In reply to Greg Kroah-Hartman

From: Qian Cai <[email protected]>

[ Upstream commit 1518ac272e789cae8c555d69951b032a275b7602 ]

Finished a qemu-kvm (-device vfio-pci,host=0001:01:00.0) triggers a few memory leaks after a while because vfio_pci_set_ctx_trigger_single() calls eventfd_ctx_fdget() without the matching eventfd_ctx_put() later. Fix it by calling eventfd_ctx_put() for those memory in vfio_pci_release() before vfio_device_release().

unreferenced object 0xebff008981cc2b00 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994816 (age 9796.310s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:

    [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
    [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
    [<000000005fcec025>] do_eventfd+0x54/0x1ac
    [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
    [<00000000b819758c>] do_el0_svc+0x128/0x1dc
    [<00000000b244e810>] el0_sync_handler+0xd0/0x268
    [<00000000d495ef94>] el0_sync+0x164/0x180

unreferenced object 0x29ff008981cc4180 (size 128):
comm "qemu-kvm", pid 4043, jiffies 4294994818 (age 9796.290s) hex dump (first 32 bytes):
01 00 00 00 6b 6b 6b 6b 00 00 00 00 ad 4e ad de ....kkkk.....N.. ff ff ff ff 6b 6b 6b 6b ff ff ff ff ff ff ff ff ....kkkk........
backtrace:

    [<00000000917e8f8d>] slab_post_alloc_hook+0x74/0x9c
    [<00000000df0f2aa2>] kmem_cache_alloc_trace+0x2b4/0x3d4
    [<000000005fcec025>] do_eventfd+0x54/0x1ac
    [<0000000082791a69>] __arm64_sys_eventfd2+0x34/0x44
    [<00000000b819758c>] do_el0_svc+0x128/0x1dc
    [<00000000b244e810>] el0_sync_handler+0xd0/0x268
    [<00000000d495ef94>] el0_sync+0x164/0x180
---
 drivers/vfio/pci/vfio_pci.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/vfio/pci/vfio_pci.c +4 -0
index 0d16f9806655f..12f7691e8b6ca 100644
@@ -474,6 +474,10 @@ static void vfio_pci_release(void *device_data)
 	if (!(--vdev->refcnt)) {
 		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+		if (vdev->err_trigger)
+			eventfd_ctx_put(vdev->err_trigger);
+		if (vdev->req_trigger)
+			eventfd_ctx_put(vdev->req_trigger);
 	}
 
 	mutex_unlock(&vdev->reflck->lock);
Signature · 1 line
2.25.1
author maintainer
#288 lore raw

PATCH 288/388 perf kcore_copy: Fix module map when there are no modules loaded

In reply to Greg Kroah-Hartman

From: Adrian Hunter <[email protected]>

[ Upstream commit 61f82e3fb697a8e85f22fdec786528af73dc36d1 ]

In the absence of any modules, no "modules" map is created, but there are other executable pages to map, due to eBPF JIT, kprobe or ftrace. Map them by recognizing that the first "module" symbol is not necessarily from a module, and adjust the map accordingly.

Cc Alexander Shishkin <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc H. Peter Anvin <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Leo Yan <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Mathieu Poirier <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Steven Rostedt (VMware) <[email protected]>
---
 tools/perf/util/symbol-elf.c | 7 +++++++
 1 file changed, 7 insertions(+)
tools/perf/util/symbol-elf.c +7 -0
index 66f4be1df573e..2ec0a32da5793 100644
@@ -1449,6 +1449,7 @@ struct kcore_copy_info {
 	u64 first_symbol;
 	u64 last_symbol;
 	u64 first_module;
+	u64 first_module_symbol;
 	u64 last_module_symbol;
 	size_t phnum;
 	struct list_head phdrs;
@@ -1525,6 +1526,8 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 
 	if (strchr(name, '[')) {
+		if (!kci->first_module_symbol || start < kci->first_module_symbol)
+			kci->first_module_symbol = start;
 		if (start > kci->last_module_symbol)
 			kci->last_module_symbol = start;
 		return 0;
@@ -1722,6 +1725,10 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 		kci->etext += page_size;
 	}
 
+	if (kci->first_module_symbol &&
+	    (!kci->first_module || kci->first_module_symbol < kci->first_module))
+		kci->first_module = kci->first_module_symbol;
+
 	kci->first_module = round_down(kci->first_module, page_size);
 
 	if (kci->last_module_symbol) {
Signature · 1 line
2.25.1
author maintainer
#286 lore raw

PATCH 286/388 perf util: Fix memory leak of prefix_if_not_in

In reply to Greg Kroah-Hartman

From: Xie XiuQi <[email protected]>

[ Upstream commit 07e9a6f538cbeecaf5c55b6f2991416f873cdcbd ]

Need to free "str" before return when asprintf() failed to avoid memory leak.

---
 tools/perf/util/sort.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/sort.c +1 -1
index 43d1d410854a3..4027906fd3e38 100644
@@ -2788,7 +2788,7 @@ static char *prefix_if_not_in(const char *pre, char *str)
 		return str;
 
 	if (asprintf(&n, "%s,%s", pre, str) < 0)
-		return NULL;
+		n = NULL;
 
 	free(str);
 	return n;
Signature · 1 line
2.25.1
author maintainer
#332 lore raw

PATCH 332/388 drm/amdkfd: fix a memory leak issue

In reply to Greg Kroah-Hartman

From: Dennis Li <[email protected]>

[ Upstream commit 087d764159996ae378b08c0fdd557537adfd6899 ]

In the resume stage of GPU recovery, start_cpsch will call pm_init which set pm->allocated as false, cause the next pm_release_ib has no chance to release ib memory.

Add pm_release_ib in stop_cpsch which will be called in the suspend stage of GPU recovery.

---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +2 -0
index a2ed9c257cb0d..e9a2784400792 100644
@@ -1075,6 +1075,8 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	dqm_unlock(dqm);
 
+	pm_release_ib(&dqm->packets);
+
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
 
Signature · 1 line
2.25.1
author maintainer
#335 lore raw

PATCH 335/388 i2c: core: Call i2c_acpi_install_space_handler() before i2c_acpi_register_devices()

In reply to Greg Kroah-Hartman

From: Hans de Goede <[email protected]>

[ Upstream commit 21653a4181ff292480599dad996a2b759ccf050f ]

Some ACPI i2c-devices _STA method (which is used to detect if the device is present) use autodetection code which probes which device is present over i2c. This requires the I2C ACPI OpRegion handler to be registered before we enumerate i2c-clients under the i2c-adapter.

This fixes the i2c touchpad on the Lenovo ThinkBook 14-IIL and ThinkBook 15 IIL not getting an i2c-client instantiated and thus not working.

---
 drivers/i2c/i2c-core-base.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/i2c/i2c-core-base.c +1 -1
index def62d5b42ca7..2dfe2ffcf8825 100644
@@ -1385,8 +1385,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 
 	/* create pre-declared device nodes */
 	of_i2c_register_devices(adap);
-	i2c_acpi_register_devices(adap);
 	i2c_acpi_install_space_handler(adap);
+	i2c_acpi_register_devices(adap);
 
 	if (adap->nr < __i2c_first_dynamic_bus_num)
 		i2c_scan_static_board_info(adap);
Signature · 1 line
2.25.1
author maintainer
#337 lore raw

PATCH 337/388 ieee802154: fix one possible memleak in ca8210_dev_com_init

In reply to Greg Kroah-Hartman

From: Liu Jian <[email protected]>

[ Upstream commit 88f46b3fe2ac41c381770ebad9f2ee49346b57a2 ]

We should call destroy_workqueue to destroy mlme_workqueue in error branch.

Fixes ded845a781a5 ("ieee802154: Add CA8210 IEEE 802.15.4 device driver")
---
 drivers/net/ieee802154/ca8210.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/ieee802154/ca8210.c +1 -0
index 430c937861534..25dbea302fb6d 100644
@@ -2924,6 +2924,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv)
 	);
 	if (!priv->irq_workqueue) {
 		dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n");
+		destroy_workqueue(priv->mlme_workqueue);
 		return -ENOMEM;
 	}
 
Signature · 1 line
2.25.1
author maintainer
#336 lore raw

PATCH 336/388 objtool: Fix noreturn detection for ignored functions

In reply to Greg Kroah-Hartman

From: Josh Poimboeuf <[email protected]>

[ Upstream commit db6c6a0df840e3f52c84cc302cc1a08ba11a4416 ]

When a function is annotated with STACK_FRAME_NON_STANDARD, objtool doesn't validate its code paths. It also skips sibling call detection within the function.

But sibling call detection is actually needed for the case where the ignored function doesn't have any return instructions. Otherwise objtool naively marks the function as implicit static noreturn, which affects the reachability of its callers, resulting in "unreachable instruction" warnings.

Fix it by just enabling sibling call detection for ignored functions. The 'insn->ignore' check in add_jump_destinations() is no longer needed after

e6da9567959e ("objtool: Don't use ignore flag for fake jumps").

Fixes the following warning:

arch/x86/kvm/vmx/vmx.o: warning: objtool: vmx_handle_exit_irqoff()+0x142: unreachable instruction

which triggers on an allmodconfig with CONFIG_GCOV_KERNEL unset.

---
 tools/objtool/check.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/objtool/check.c +1 -1
index 48b234d8f251e..1b7e748170e54 100644
@@ -556,7 +556,7 @@ static int add_jump_destinations(struct objtool_file *file)
 		    insn->type != INSN_JUMP_UNCONDITIONAL)
 			continue;
 
-		if (insn->ignore || insn->offset == FAKE_JUMP_OFFSET)
+		if (insn->offset == FAKE_JUMP_OFFSET)
 			continue;
 
 		rela = find_rela_by_dest_range(insn->sec, insn->offset,
Signature · 1 line
2.25.1
author maintainer
#339 lore raw

PATCH 339/388 clocksource/drivers/h8300_timer8: Fix wrong return value in h8300_8timer_init()

In reply to Greg Kroah-Hartman

From: Tianjia Zhang <[email protected]>

[ Upstream commit 400d033f5a599120089b5f0c54d14d198499af5a ]

In the init function, if the call to of_iomap() fails, the return value is ENXIO instead of -ENXIO.

Change to the right negative errno.

Fixes 691f8f878290f ("clocksource/drivers/h8300_timer8: Convert init function to return error")
Cc Daniel Lezcano <[email protected]>
---
 drivers/clocksource/h8300_timer8.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/clocksource/h8300_timer8.c +1 -1
index 1d740a8c42ab3..47114c2a7cb54 100644
@@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node)
 		return PTR_ERR(clk);
 	}
 
-	ret = ENXIO;
+	ret = -ENXIO;
 	base = of_iomap(node, 0);
 	if (!base) {
 		pr_err("failed to map registers for clockevent\n");
Signature · 1 line
2.25.1
author maintainer
#338 lore raw

PATCH 338/388 ieee802154/adf7242: check status of adf7242_read_reg

In reply to Greg Kroah-Hartman

From: Tom Rix <[email protected]>

[ Upstream commit e3914ed6cf44bfe1f169e26241f8314556fd1ac1 ]

Clang static analysis reports this error

adf7242.c:887:6: warning: Assigned value is garbage or undefined

        len = len_u8;
            ^ ~~~~~~

len_u8 is set in

       adf7242_read_reg(lp, 0, &len_u8);

When this call fails, len_u8 is not set.

So check the return code.

Fixes 7302b9d90117 ("ieee802154/adf7242: Driver for ADF7242 MAC IEEE802154")
---
 drivers/net/ieee802154/adf7242.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ieee802154/adf7242.c +3 -1
index 8dbccec6ac866..5945ac5f38eea 100644
@@ -882,7 +882,9 @@ static int adf7242_rx(struct adf7242_local *lp)
 	int ret;
 	u8 lqi, len_u8, *data;
 
-	adf7242_read_reg(lp, 0, &len_u8);
+	ret = adf7242_read_reg(lp, 0, &len_u8);
+	if (ret)
+		return ret;
 
 	len = len_u8;
 
Signature · 1 line
2.25.1
author maintainer
#340 lore raw

PATCH 340/388 mwifiex: Increase AES key storage size to 256 bits

In reply to Greg Kroah-Hartman

From: Maximilian Luz <[email protected]>

[ Upstream commit 4afc850e2e9e781976fb2c7852ce7bac374af938 ]

Following commit e18696786548 ("mwifiex: Prevent memory corruption handling keys") the mwifiex driver fails to authenticate with certain networks, specifically networks with 256 bit keys, and repeatedly asks for the password. The kernel log repeats the following lines (id and bssid redacted):

mwifiex_pcie 0000:01:00.0: info: trying to associate to '<id>' bssid <bssid> mwifiex_pcie 0000:01:00.0: info: associated to bssid <bssid> successfully mwifiex_pcie 0000:01:00.0: crypto keys added
mwifiex_pcie 0000:01:00.0: info: successfully disconnected from <bssid>: reason code 3

Tracking down this problem lead to the overflow check introduced by the aforementioned commit into mwifiex_ret_802_11_key_material_v2(). This check fails on networks with 256 bit keys due to the current storage size for AES keys in struct mwifiex_aes_param being only 128 bit.

To fix this issue, increase the storage size for AES keys to 256 bit.

---
 drivers/net/wireless/marvell/mwifiex/fw.h          | 2 +-
 drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)
drivers/net/wireless/marvell/mwifiex/fw.h +1 -1
index 1fb76d2f5d3fd..8b9d0809daf62 100644
@@ -953,7 +953,7 @@ struct mwifiex_tkip_param {
 struct mwifiex_aes_param {
 	u8 pn[WPA_PN_SIZE];
 	__le16 key_len;
-	u8 key[WLAN_KEY_LEN_CCMP];
+	u8 key[WLAN_KEY_LEN_CCMP_256];
 } __packed;
 
 struct mwifiex_wapi_param {
drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +2 -2
index 7ae2c34f65db2..4eaa493e33253 100644
@@ -619,7 +619,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 	key_v2 = &resp->params.key_material_v2;
 
 	len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len);
-	if (len > WLAN_KEY_LEN_CCMP)
+	if (len > sizeof(key_v2->key_param_set.key_params.aes.key))
 		return -EINVAL;
 
 	if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) {
@@ -635,7 +635,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv,
 		return 0;
 
 	memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0,
-	       WLAN_KEY_LEN_CCMP);
+	       sizeof(key_v2->key_param_set.key_params.aes.key));
 	priv->aes_key_v2.key_param_set.key_params.aes.key_len =
 				cpu_to_le16(len);
 	memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key,
Signature · 1 line
2.25.1
author maintainer
#344 lore raw

PATCH 344/388 netfilter: conntrack: nf_conncount_init is failing with IPv6 disabled

In reply to Greg Kroah-Hartman

From: Eelco Chaudron <[email protected]>

[ Upstream commit 526e81b990e53e31ba40ba304a2285ffd098721f ]

The openvswitch module fails initialization when used in a kernel without IPv6 enabled. nf_conncount_init() fails because the ct code unconditionally tries to initialize the netns IPv6 related bit, regardless of the build option. The change below ignores the IPv6 part if not enabled.

Note that the corresponding _put() function already has this IPv6 configuration check.

Fixes 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
---
 net/netfilter/nf_conntrack_proto.c | 2 ++
 1 file changed, 2 insertions(+)
net/netfilter/nf_conntrack_proto.c +2 -0
index a0560d175a7ff..aaf4293ddd459 100644
@@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net)
 	int err;
 
 	err = nf_ct_netns_do_get(net, NFPROTO_IPV4);
+#if IS_ENABLED(CONFIG_IPV6)
 	if (err < 0)
 		goto err1;
 	err = nf_ct_netns_do_get(net, NFPROTO_IPV6);
@@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net)
 err2:
 	nf_ct_netns_put(net, NFPROTO_IPV4);
 err1:
+#endif
 	return err;
 }
 
Signature · 1 line
2.25.1
author maintainer
#317 lore raw

PATCH 317/388 perf parse-events: Use strcmp() to compare the PMU name

In reply to Greg Kroah-Hartman

From: Jin Yao <[email protected]>

[ Upstream commit 8510895bafdbf7c4dd24c22946d925691135c2b2 ]

A big uncore event group is split into multiple small groups which only include the uncore events from the same PMU. This has been supported in the commit 3cdc5c2cb924a ("perf parse-events: Handle uncore event aliases in small groups properly").

If the event's PMU name starts to repeat, it must be a new event. That can be used to distinguish the leader from other members. But now it only compares the pointer of pmu_name (leader->pmu_name == evsel->pmu_name).

If we use "perf stat -M LLC_MISSES.PCIE_WRITE -a" on cascadelakex, the event list is:

evsel->name evsel->pmu_name
---------------------------------------------------------------
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_4 (as leader)
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_2
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_0
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_5
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_3
unc_iio_data_req_of_cpu.mem_write.part0 uncore_iio_1
unc_iio_data_req_of_cpu.mem_write.part1 uncore_iio_4
......

For the event "unc_iio_data_req_of_cpu.mem_write.part1" with "uncore_iio_4", it should be the event from PMU "uncore_iio_4". It's not a new leader for this PMU.

But if we use "(leader->pmu_name == evsel->pmu_name)", the check would be failed and the event is stored to leaders[] as a new PMU leader.

So this patch uses strcmp to compare the PMU name between events.

Fixes d4953f7ef1a2 ("perf parse-events: Fix 3 use after frees found with clang ASAN")
Cc Alexander Shishkin <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Jin Yao <[email protected]>
Cc Kan Liang <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 tools/perf/util/parse-events.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
tools/perf/util/parse-events.c +2 -3
@@ -1505,12 +1505,11 @@ parse_events__set_leader_for_uncore_alia
 		 * event. That can be used to distinguish the leader from
 		 * other members, even they have the same event name.
 		 */
-		if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+		if ((leader != evsel) &&
+		    !strcmp(leader->pmu_name, evsel->pmu_name)) {
 			is_leader = false;
 			continue;
 		}
-		/* The name is always alias name */
-		WARN_ON(strcmp(leader->name, evsel->name));
 
 		/* Store the leader event for each PMU */
 		leaders[nr_pmu++] = (uintptr_t) evsel;
author maintainer
#319 lore raw

PATCH 319/388 ALSA: hda: Workaround for spurious wakeups on some Intel platforms

In reply to Greg Kroah-Hartman

From: Takashi Iwai <[email protected]>

[ Upstream commit a6630529aecb5a3e84370c376ed658e892e6261e ]

We've received a regression report on Intel HD-audio controller that wakes up immediately after S3 suspend. The bisection leads to the commit c4c8dd6ef807 ("ALSA: hda: Skip controller resume if not needed"). This commit replaces the system-suspend to use pm_runtime_force_suspend() instead of the direct call of __azx_runtime_suspend(). However, by some really mysterious reason, pm_runtime_force_suspend() causes a spurious wakeup (although it calls the same __azx_runtime_suspend() internally).

As an ugly workaround for now, revert the behavior to call __azx_runtime_suspend() and __azx_runtime_resume() for those old Intel platforms that may exhibit such a problem, while keeping the new standard pm_runtime_force_suspend() and pm_runtime_force_resume() pair for the remaining chips.

---
 sound/pci/hda/hda_controller.h |  2 +-
 sound/pci/hda/hda_intel.c      | 17 ++++++++++++++---
 2 files changed, 15 insertions(+), 4 deletions(-)
sound/pci/hda/hda_controller.h +1 -1
index 82e26442724ba..a356fb0e57738 100644
@@ -41,7 +41,7 @@
 /* 24 unused */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
-/* 27 unused */
+#define AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP (1 << 27) /* Workaround for spurious wakeups after suspend */
 #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 #define AZX_DCAPS_NO_MSI64      (1 << 29)	/* Stick to 32-bit MSIs */
 #define AZX_DCAPS_SEPARATE_STREAM_TAG	(1 << 30) /* capture and playback use separate stream tag */
sound/pci/hda/hda_intel.c +14 -3
index 754e4d1a86b57..590ea262f2e20 100644
@@ -295,7 +295,8 @@ enum {
 /* PCH for HSW/BDW; with runtime PM */
 /* no i915 binding for this as HSW/BDW has another controller for HDMI */
 #define AZX_DCAPS_INTEL_PCH \
-	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME)
+	(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
+	 AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
 
 /* HSW HDMI */
 #define AZX_DCAPS_INTEL_HASWELL \
@@ -1026,7 +1027,14 @@ static int azx_suspend(struct device *dev)
 	chip = card->private_data;
 	bus = azx_bus(chip);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
-	pm_runtime_force_suspend(dev);
+	/* An ugly workaround: direct call of __azx_runtime_suspend() and
+	 * __azx_runtime_resume() for old Intel platforms that suffer from
+	 * spurious wakeups after S3 suspend
+	 */
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_suspend(chip);
+	else
+		pm_runtime_force_suspend(dev);
 	if (bus->irq >= 0) {
 		free_irq(bus->irq, chip);
 		bus->irq = -1;
@@ -1054,7 +1062,10 @@ static int azx_resume(struct device *dev)
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	pm_runtime_force_resume(dev);
+	if (chip->driver_caps & AZX_DCAPS_SUSPEND_SPURIOUS_WAKEUP)
+		__azx_runtime_resume(chip, false);
+	else
+		pm_runtime_force_resume(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);
Signature · 1 line
2.25.1
author maintainer
#318 lore raw

PATCH 318/388 ALSA: hda: Always use jackpoll helper for jack update after resume

In reply to Greg Kroah-Hartman

From: Takashi Iwai <[email protected]>

[ Upstream commit 8d6762af302d69f76fa788a277a56a9d9cd275d5 ]

HD-audio codec driver applies a tricky procedure to forcibly perform the runtime resume by mimicking the usage count even if the device has been runtime-suspended beforehand. This was needed to assure to trigger the jack detection update after the system resume.

And recently we also applied the similar logic to the HD-audio controller side. However this seems leading to some inconsistency, and eventually PCI controller gets screwed up.

This patch is an attempt to fix and clean up those behavior: instead of the tricky runtime resume procedure, the existing jackpoll work is scheduled when such a forced codec resume is required. The jackpoll work will power up the codec, and this alone should suffice for the jack status update in usual cases. If the extra polling is requested (by checking codec->jackpoll_interval), the manual update is invoked after that, and the codec is powered down again.

Also, we filter the spurious wake up of the codec from the controller runtime resume by checking codec->relaxed_resume flag. If this flag is set, basically we don't need to wake up explicitly, but it's supposed to be done via the audio component notifier.

Fixes c4c8dd6ef807 ("ALSA: hda: Skip controller resume if not needed")
---
 sound/pci/hda/hda_codec.c | 28 +++++++++++++++++-----------
 sound/pci/hda/hda_intel.c | 17 ++---------------
 2 files changed, 19 insertions(+), 26 deletions(-)
sound/pci/hda/hda_codec.c +17 -11
index 12da263fb02ba..6da296def283e 100644
@@ -641,8 +641,18 @@ static void hda_jackpoll_work(struct work_struct *work)
 	struct hda_codec *codec =
 		container_of(work, struct hda_codec, jackpoll_work.work);
 
-	snd_hda_jack_set_dirty_all(codec);
-	snd_hda_jack_poll_all(codec);
+	/* for non-polling trigger: we need nothing if already powered on */
+	if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core))
+		return;
+
+	/* the power-up/down sequence triggers the runtime resume */
+	snd_hda_power_up_pm(codec);
+	/* update jacks manually if polling is required, too */
+	if (codec->jackpoll_interval) {
+		snd_hda_jack_set_dirty_all(codec);
+		snd_hda_jack_poll_all(codec);
+	}
+	snd_hda_power_down_pm(codec);
 
 	if (!codec->jackpoll_interval)
 		return;
@@ -2958,18 +2968,14 @@ static int hda_codec_runtime_resume(struct device *dev)
 static int hda_codec_force_resume(struct device *dev)
 {
 	struct hda_codec *codec = dev_to_hda_codec(dev);
-	bool forced_resume = hda_codec_need_resume(codec);
 	int ret;
 
-	/* The get/put pair below enforces the runtime resume even if the
-	 * device hasn't been used at suspend time.  This trick is needed to
-	 * update the jack state change during the sleep.
-	 */
-	if (forced_resume)
-		pm_runtime_get_noresume(dev);
 	ret = pm_runtime_force_resume(dev);
-	if (forced_resume)
-		pm_runtime_put(dev);
+	/* schedule jackpoll work for jack detection update */
+	if (codec->jackpoll_interval ||
+	    (pm_runtime_suspended(dev) && hda_codec_need_resume(codec)))
+		schedule_delayed_work(&codec->jackpoll_work,
+				      codec->jackpoll_interval);
 	return ret;
 }
 
sound/pci/hda/hda_intel.c +2 -15
index a6e8aaa091c7d..754e4d1a86b57 100644
@@ -1002,7 +1002,8 @@ static void __azx_runtime_resume(struct azx *chip, bool from_rt)
 
 	if (status && from_rt) {
 		list_for_each_codec(codec, &chip->bus)
-			if (status & (1 << codec->addr))
+			if (!codec->relaxed_resume &&
+			    (status & (1 << codec->addr)))
 				schedule_delayed_work(&codec->jackpoll_work,
 						      codec->jackpoll_interval);
 	}
@@ -1041,9 +1042,7 @@ static int azx_suspend(struct device *dev)
 static int azx_resume(struct device *dev)
 {
 	struct snd_card *card = dev_get_drvdata(dev);
-	struct hda_codec *codec;
 	struct azx *chip;
-	bool forced_resume = false;
 
 	if (!azx_is_pm_ready(card))
 		return 0;
@@ -1055,19 +1054,7 @@ static int azx_resume(struct device *dev)
 	if (azx_acquire_irq(chip, 1) < 0)
 		return -EIO;
 
-	/* check for the forced resume */
-	list_for_each_codec(codec, &chip->bus) {
-		if (hda_codec_need_resume(codec)) {
-			forced_resume = true;
-			break;
-		}
-	}
-
-	if (forced_resume)
-		pm_runtime_get_noresume(dev);
 	pm_runtime_force_resume(dev);
-	if (forced_resume)
-		pm_runtime_put(dev);
 	snd_power_change_state(card, SNDRV_CTL_POWER_D0);
 
 	trace_azx_resume(chip);
Signature · 1 line
2.25.1
author maintainer
#320 lore raw

PATCH 320/388 net: openvswitch: use div_u64() for 64-by-32 divisions

In reply to Greg Kroah-Hartman

From: Tonghao Zhang <[email protected]>

[ Upstream commit 659d4587fe7233bfdff303744b20d6f41ad04362 ]

Compile the kernel for arm 32 platform, the build warning found. To fix that, should use div_u64() for divisions.
| net/openvswitch/meter.c:396: undefined reference to `__udivdi3'

[add more commit msg, change reported tag, and use div_u64 instead of do_div by Tonghao]

Fixes e57358873bb5d6ca ("net: openvswitch: use u64 for meter bucket")
---
 net/openvswitch/meter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/openvswitch/meter.c +1 -1
index b10734f18bbd6..541eea74ef7a6 100644
@@ -252,7 +252,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 		 * Start with a full bucket.
 		 */
 		band->bucket = (band->burst_size + band->rate) * 1000ULL;
-		band_max_delta_t = band->bucket / band->rate;
+		band_max_delta_t = div_u64(band->bucket, band->rate);
 		if (band_max_delta_t > meter->max_delta_t)
 			meter->max_delta_t = band_max_delta_t;
 		band++;
Signature · 1 line
2.25.1
author maintainer
#322 lore raw

PATCH 322/388 device_cgroup: Fix RCU list debugging warning

In reply to Greg Kroah-Hartman

From: Amol Grover <[email protected]>

[ Upstream commit bc62d68e2a0a69fcdcf28aca8edb01abf306b698 ]

exceptions may be traversed using list_for_each_entry_rcu() outside of an RCU read side critical section BUT under the protection of decgroup_mutex. Hence add the corresponding lockdep expression to fix the following false-positive warning:

[    2.304417] =============================
[    2.304418] WARNING: suspicious RCU usage
[    2.304420] 5.5.4-stable #17 Tainted: G            E
[    2.304422] -----------------------------
[    2.304424] security/device_cgroup.c:355 RCU-list traversed in non-reader section!!
---
 security/device_cgroup.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
security/device_cgroup.c +2 -1
index 725674f3276d3..5d7bb91c64876 100644
@@ -352,7 +352,8 @@ static bool match_exception_partial(struct list_head *exceptions, short type,
 {
 	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, exceptions, list) {
+	list_for_each_entry_rcu(ex, exceptions, list,
+				lockdep_is_held(&devcgroup_mutex)) {
 		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
 			continue;
 		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
Signature · 1 line
2.25.1
author maintainer
#321 lore raw

PATCH 321/388 nvme: explicitly update mpath disk capacity on revalidation

In reply to Greg Kroah-Hartman

From: Anthony Iliopoulos <[email protected]>

[ Upstream commit 05b29021fba5e725dd385151ef00b6340229b500 ]

Commit 3b4b19721ec652 ("nvme: fix possible deadlock when I/O is blocked") reverted multipath head disk revalidation due to deadlocks caused by holding the bd_mutex during revalidate.

Updating the multipath disk blockdev size is still required though for userspace to be able to observe any resizing while the device is mounted. Directly update the bdev inode size to avoid unnecessarily holding the bdev->bd_mutex.

Fixes 3b4b19721ec652 ("nvme: fix possible deadlock when I/O is

blocked")

---
 drivers/nvme/host/core.c |  1 +
 drivers/nvme/host/nvme.h | 13 +++++++++++++
 2 files changed, 14 insertions(+)
drivers/nvme/host/core.c +1 -0
index 5702bc59c569c..2cd32901d95c7 100644
@@ -1864,6 +1864,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+		nvme_mpath_update_disk_size(ns->head->disk);
 	}
 #endif
 }
drivers/nvme/host/nvme.h +13 -0
index 5eb9500c89392..b7117fb09dd0f 100644
@@ -561,6 +561,16 @@ static inline void nvme_trace_bio_complete(struct request *req,
 					 req->bio, status);
 }
 
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+	struct block_device *bdev = bdget_disk(disk, 0);
+
+	if (bdev) {
+		bd_set_size(bdev, get_capacity(disk) << SECTOR_SHIFT);
+		bdput(bdev);
+	}
+}
+
 extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
 extern struct device_attribute subsys_attr_iopolicy;
@@ -636,6 +646,9 @@ static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
 static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 {
 }
+static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
Signature · 1 line
2.25.1
author maintainer
#348 lore raw

PATCH 348/388 net: qed: Disable aRFS for NPAR and 100G

In reply to Greg Kroah-Hartman

From: Dmitry Bogdanov <[email protected]>

[ Upstream commit 2d2fe8433796603091ac8ea235b9165ac5a85f9a ]

In CMT and NPAR the PF is unknown when the GFS block processes the packet. Therefore cannot use searcher as it has a per PF database, and thus ARFS must be disabled.

Fixes d51e4af5c209 ("qed: aRFS infrastructure support")
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c  | 11 ++++++++++-
 drivers/net/ethernet/qlogic/qed/qed_l2.c   |  3 +++
 drivers/net/ethernet/qlogic/qed/qed_main.c |  2 ++
 include/linux/qed/qed_if.h                 |  1 +
 4 files changed, 16 insertions(+), 1 deletion(-)
drivers/net/ethernet/qlogic/qed/qed_dev.c +10 -1
index 4456ce5325a74..a923c65532702 100644
@@ -4142,7 +4142,8 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 			cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
 					BIT(QED_MF_LLH_PROTO_CLSS) |
 					BIT(QED_MF_LL2_NON_UNICAST) |
-					BIT(QED_MF_INTER_PF_SWITCH);
+					BIT(QED_MF_INTER_PF_SWITCH) |
+					BIT(QED_MF_DISABLE_ARFS);
 			break;
 		case NVM_CFG1_GLOB_MF_MODE_DEFAULT:
 			cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) |
@@ -4155,6 +4156,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 
 		DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
 			cdev->mf_bits);
+
+		/* In CMT the PF is unknown when the GFS block processes the
+		 * packet. Therefore cannot use searcher as it has a per PF
+		 * database, and thus ARFS must be disabled.
+		 *
+		 */
+		if (QED_IS_CMT(cdev))
+			cdev->mf_bits |= BIT(QED_MF_DISABLE_ARFS);
 	}
 
 	DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n",
drivers/net/ethernet/qlogic/qed/qed_l2.c +3 -0
index 1a5fc2ae351c4..8a73482cb7a88 100644
@@ -2001,6 +2001,9 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn,
 			     struct qed_ptt *p_ptt,
 			     struct qed_arfs_config_params *p_cfg_params)
 {
+	if (test_bit(QED_MF_DISABLE_ARFS, &p_hwfn->cdev->mf_bits))
+		return;
+
 	if (p_cfg_params->mode != QED_FILTER_CONFIG_MODE_DISABLE) {
 		qed_gft_config(p_hwfn, p_ptt, p_hwfn->rel_pf_id,
 			       p_cfg_params->tcp,
drivers/net/ethernet/qlogic/qed/qed_main.c +2 -0
index e72f9f1d2e94d..bc1f5b36b5bf2 100644
@@ -280,6 +280,8 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 		dev_info->fw_eng = FW_ENGINEERING_VERSION;
 		dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH,
 						       &cdev->mf_bits);
+		if (!test_bit(QED_MF_DISABLE_ARFS, &cdev->mf_bits))
+			dev_info->b_arfs_capable = true;
 		dev_info->tx_switching = true;
 
 		if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME)
include/linux/qed/qed_if.h +1 -0
index b5db1ee96d789..65a7355ed07b3 100644
@@ -637,6 +637,7 @@ struct qed_dev_info {
 #define QED_MFW_VERSION_3_OFFSET	24
 
 	u32		flash_size;
+	bool		b_arfs_capable;
 	bool		b_inter_pf_switch;
 	bool		tx_switching;
 	bool		rdma_supported;
Signature · 1 line
2.25.1
author maintainer
#360 lore raw

PATCH 360/388 regmap: fix page selection for noinc reads

In reply to Greg Kroah-Hartman

From: Dmitry Baryshkov <[email protected]>

[ Upstream commit 4003324856311faebb46cbd56a1616bd3f3b67c2 ]

Non-incrementing reads can fail if register + length crosses page border. However for non-incrementing reads we should not check for page border crossing. Fix this by passing additional flag to _regmap_raw_read and passing length to _regmap_select_page basing on the flag.

Fixes 74fe7b551f33 ("regmap: Add regmap_noinc_read API")
---
 drivers/base/regmap/regmap.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
drivers/base/regmap/regmap.c +6 -6
index 927ebde1607be..7244319dd2d52 100644
@@ -2454,7 +2454,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 EXPORT_SYMBOL_GPL(regmap_raw_write_async);
 
 static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
-			    unsigned int val_len)
+			    unsigned int val_len, bool noinc)
 {
 	struct regmap_range_node *range;
 	int ret;
@@ -2467,7 +2467,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 	range = _regmap_range_lookup(map, reg);
 	if (range) {
 		ret = _regmap_select_page(map, &reg, range,
-					  val_len / map->format.val_bytes);
+					  noinc ? 1 : val_len / map->format.val_bytes);
 		if (ret != 0)
 			return ret;
 	}
@@ -2505,7 +2505,7 @@ static int _regmap_bus_read(void *context, unsigned int reg,
 	if (!map->format.parse_val)
 		return -EINVAL;
 
-	ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes);
+	ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false);
 	if (ret == 0)
 		*val = map->format.parse_val(work_val);
 
@@ -2621,7 +2621,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 
 		/* Read bytes that fit into whole chunks */
 		for (i = 0; i < chunk_count; i++) {
-			ret = _regmap_raw_read(map, reg, val, chunk_bytes);
+			ret = _regmap_raw_read(map, reg, val, chunk_bytes, false);
 			if (ret != 0)
 				goto out;
 
@@ -2632,7 +2632,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 
 		/* Read remaining bytes */
 		if (val_len) {
-			ret = _regmap_raw_read(map, reg, val, val_len);
+			ret = _regmap_raw_read(map, reg, val, val_len, false);
 			if (ret != 0)
 				goto out;
 		}
@@ -2707,7 +2707,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg,
 			read_len = map->max_raw_read;
 		else
 			read_len = val_len;
-		ret = _regmap_raw_read(map, reg, val, read_len);
+		ret = _regmap_raw_read(map, reg, val, read_len, true);
 		if (ret)
 			goto out_unlock;
 		val = ((u8 *)val) + read_len;
Signature · 1 line
2.25.1
author maintainer
#358 lore raw

PATCH 358/388 lib80211: fix unmet direct dependendices config warning when !CRYPTO

In reply to Greg Kroah-Hartman

From: Necip Fazil Yildiran <[email protected]>

[ Upstream commit b959ba9f468b1c581f40e92661ad58b093abaa03 ]

When LIB80211_CRYPT_CCMP is enabled and CRYPTO is disabled, it results in unmet direct dependencies config warning. The reason is that LIB80211_CRYPT_CCMP selects CRYPTO_AES and CRYPTO_CCM, which are subordinate to CRYPTO. This is reproducible with CRYPTO disabled and R8188EU enabled, where R8188EU selects LIB80211_CRYPT_CCMP but does not select or depend on CRYPTO.

Honor the kconfig menu hierarchy to remove kconfig dependency warnings.

Fixes a11e2f85481c ("lib80211: use crypto API ccm(aes) transform for CCMP processing")
---
 net/wireless/Kconfig | 1 +
 1 file changed, 1 insertion(+)
net/wireless/Kconfig +1 -0
index 63cf7131f601c..211007c091d59 100644
@@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP
 
 config LIB80211_CRYPT_CCMP
 	tristate
+	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_CCM
 
Signature · 1 line
2.25.1
author maintainer
#359 lore raw

PATCH 359/388 ALSA: asihpi: fix iounmap in error handler

In reply to Greg Kroah-Hartman

From: Tom Rix <[email protected]>

[ Upstream commit 472eb39103e885f302fd8fd6eff104fcf5503f1b ]

clang static analysis flags this problem hpioctl.c:513:7: warning: Branch condition evaluates to
a garbage value

                if (pci.ap_mem_base[idx]) {
                    ^~~~~~~~~~~~~~~~~~~~

If there is a failure in the middle of the memory space loop, only some of the memory spaces need to be cleaned up.

At the error handler, idx holds the number of successful memory spaces mapped. So rework the handler loop to use the old idx.

There is a second problem, the memory space loop conditionally iomaps()/sets the mem_base so it is necessay to initize pci.

Fixes 719f82d3987a ("ALSA: Add support of AudioScience ASI boards")
---
 sound/pci/asihpi/hpioctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
sound/pci/asihpi/hpioctl.c +2 -2
index 496dcde9715d6..9790f5108a166 100644
@@ -343,7 +343,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
 	struct hpi_message hm;
 	struct hpi_response hr;
 	struct hpi_adapter adapter;
-	struct hpi_pci pci;
+	struct hpi_pci pci = { 0 };
 
 	memset(&adapter, 0, sizeof(adapter));
 
@@ -499,7 +499,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev,
 	return 0;
 
 err:
-	for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) {
+	while (--idx >= 0) {
 		if (pci.ap_mem_base[idx]) {
 			iounmap(pci.ap_mem_base[idx]);
 			pci.ap_mem_base[idx] = NULL;
Signature · 1 line
2.25.1
author maintainer
#364 lore raw

PATCH 364/388 KVM: x86: Reset MMU context if guest toggles CR4.SMAP or CR4.PKE

In reply to Greg Kroah-Hartman

From: Sean Christopherson <[email protected]>

[ Upstream commit 8d214c481611b29458a57913bd786f0ac06f0605 ]

Reset the MMU context during kvm_set_cr4() if SMAP or PKE is toggled. Recent commits to (correctly) not reload PDPTRs when SMAP/PKE are toggled inadvertantly skipped the MMU context reset due to the mask of bits that triggers PDPTR loads also being used to trigger MMU context resets.

Fixes 427890aff855 ("kvm: x86: Toggling CR4.SMAP does not load PDPTEs in PAE mode")
Fixes cb957adb4ea4 ("kvm: x86: Toggling CR4.PKE does not load PDPTEs in PAE mode")
Cc Jim Mattson <[email protected]>
Cc Peter Shier <[email protected]>
Cc Oliver Upton <[email protected]>

Message-Id: <[email protected]>

---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/x86.c +2 -1
index 67ad417a29ca4..12e83297ea020 100644
@@ -973,6 +973,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
 				   X86_CR4_SMEP;
+	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -1000,7 +1001,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (kvm_x86_ops->set_cr4(vcpu, cr4))
 		return 1;
 
-	if (((cr4 ^ old_cr4) & pdptr_bits) ||
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
Signature · 1 line
2.25.1
author maintainer
#349 lore raw

PATCH 349/388 net: qede: Disable aRFS for NPAR and 100G

In reply to Greg Kroah-Hartman

From: Dmitry Bogdanov <[email protected]>

[ Upstream commit 0367f05885b9f21d062447bd2ba1302ba3cc7392 ]

In some configurations ARFS cannot be used, so disable it if device is not capable.

---
 drivers/net/ethernet/qlogic/qede/qede_filter.c |  3 +++
 drivers/net/ethernet/qlogic/qede/qede_main.c   | 11 +++++------
 2 files changed, 8 insertions(+), 6 deletions(-)
drivers/net/ethernet/qlogic/qede/qede_filter.c +3 -0
index c8bdbf057d5a2..5041994bf03fb 100644
@@ -336,6 +336,9 @@ int qede_alloc_arfs(struct qede_dev *edev)
 {
 	int i;
 
+	if (!edev->dev_info.common.b_arfs_capable)
+		return -EINVAL;
+
 	edev->arfs = vzalloc(sizeof(*edev->arfs));
 	if (!edev->arfs)
 		return -ENOMEM;
drivers/net/ethernet/qlogic/qede/qede_main.c +5 -6
index 2c3d654c84543..ce3e62e73e4cd 100644
@@ -770,7 +770,7 @@ static void qede_init_ndev(struct qede_dev *edev)
 		      NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		      NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC;
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1)
+	if (edev->dev_info.common.b_arfs_capable)
 		hw_features |= NETIF_F_NTUPLE;
 
 	if (edev->dev_info.common.vxlan_enable ||
@@ -2211,7 +2211,7 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	qede_vlan_mark_nonconfigured(edev);
 	edev->ops->fastpath_stop(edev->cdev);
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
+	if (edev->dev_info.common.b_arfs_capable) {
 		qede_poll_for_freeing_arfs_filters(edev);
 		qede_free_arfs(edev);
 	}
@@ -2278,10 +2278,9 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	if (rc)
 		goto err2;
 
-	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) {
-		rc = qede_alloc_arfs(edev);
-		if (rc)
-			DP_NOTICE(edev, "aRFS memory allocation failed\n");
+	if (qede_alloc_arfs(edev)) {
+		edev->ndev->features &= ~NETIF_F_NTUPLE;
+		edev->dev_info.common.b_arfs_capable = false;
 	}
 
 	qede_napi_add_enable(edev);
Signature · 1 line
2.25.1
author maintainer
#369 lore raw

PATCH 369/388 scsi: lpfc: Fix initial FLOGI failure due to BBSCN not supported

In reply to Greg Kroah-Hartman

From: James Smart <[email protected]>

commit 7f04839ec4483563f38062b4dd90253e45447198 upstream.

Initial FLOGIs are failing with the following message:

lpfc 0000:13:00.1: 1:(0):0820 FLOGI Failed (x300). BBCredit Not Supported

In a prior patch, the READ_SPARAM command was re-ordered to post after CONFIG_LINK as the driver is expected to update the driver's copy of the service parameters for the FLOGI payload. If the bb-credit recovery feature is enabled, this is fine. But on adapters were bb-credit recovery isn't enabled, it would cause the FLOGI to fail.

Fix by restoring the original command order (READ_SPARAM before CONFIG_LINK), and after issuing CONFIG_LINK, detect bb-credit recovery support and reissuing READ_SPARAM to obtain the updated service parameters (effectively adding in the fix command order).

[mkp: corrected SHA]

Fixes 835214f5d5f5 ("scsi: lpfc: Fix broken Credit Recovery after driver load")
CC <[email protected]> # v5.7+
---
 drivers/scsi/lpfc/lpfc_hbadisc.c |   76 ++++++++++++++++++++++++++-------------
 1 file changed, 52 insertions(+), 24 deletions(-)
drivers/scsi/lpfc/lpfc_hbadisc.c +52 -24
@@ -73,6 +73,7 @@ static void lpfc_disc_timeout_handler(st
 static void lpfc_disc_flush_list(struct lpfc_vport *vport);
 static void lpfc_unregister_fcfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
 static int lpfc_fcf_inuse(struct lpfc_hba *);
+static void lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *, LPFC_MBOXQ_t *);
 
 void
 lpfc_terminate_rport_io(struct fc_rport *rport)
@@ -1134,11 +1135,13 @@ out:
 	return;
 }
 
-
 void
 lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 {
 	struct lpfc_vport *vport = pmb->vport;
+	LPFC_MBOXQ_t *sparam_mb;
+	struct lpfc_dmabuf *sparam_mp;
+	int rc;
 
 	if (pmb->u.mb.mbxStatus)
 		goto out;
@@ -1163,12 +1166,42 @@ lpfc_mbx_cmpl_local_config_link(struct l
 	}
 
 	/* Start discovery by sending a FLOGI. port_state is identically
-	 * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending
-	 * the FLOGI is being deferred till after MBX_READ_SPARAM completes.
+	 * LPFC_FLOGI while waiting for FLOGI cmpl.
 	 */
 	if (vport->port_state != LPFC_FLOGI) {
-		if (!(phba->hba_flag & HBA_DEFER_FLOGI))
+		/* Issue MBX_READ_SPARAM to update CSPs before FLOGI if
+		 * bb-credit recovery is in place.
+		 */
+		if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
+		    !(phba->link_flag & LS_LOOPBACK_MODE)) {
+			sparam_mb = mempool_alloc(phba->mbox_mem_pool,
+						  GFP_KERNEL);
+			if (!sparam_mb)
+				goto sparam_out;
+
+			rc = lpfc_read_sparam(phba, sparam_mb, 0);
+			if (rc) {
+				mempool_free(sparam_mb, phba->mbox_mem_pool);
+				goto sparam_out;
+			}
+			sparam_mb->vport = vport;
+			sparam_mb->mbox_cmpl = lpfc_mbx_cmpl_read_sparam;
+			rc = lpfc_sli_issue_mbox(phba, sparam_mb, MBX_NOWAIT);
+			if (rc == MBX_NOT_FINISHED) {
+				sparam_mp = (struct lpfc_dmabuf *)
+						sparam_mb->ctx_buf;
+				lpfc_mbuf_free(phba, sparam_mp->virt,
+					       sparam_mp->phys);
+				kfree(sparam_mp);
+				sparam_mb->ctx_buf = NULL;
+				mempool_free(sparam_mb, phba->mbox_mem_pool);
+				goto sparam_out;
+			}
+
+			phba->hba_flag |= HBA_DEFER_FLOGI;
+		}  else {
 			lpfc_initial_flogi(vport);
+		}
 	} else {
 		if (vport->fc_flag & FC_PT2PT)
 			lpfc_disc_start(vport);
@@ -1180,6 +1213,7 @@ out:
 			 "0306 CONFIG_LINK mbxStatus error x%x "
 			 "HBA state x%x\n",
 			 pmb->u.mb.mbxStatus, vport->port_state);
+sparam_out:
 	mempool_free(pmb, phba->mbox_mem_pool);
 
 	lpfc_linkdown(phba);
@@ -3237,21 +3271,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba
 	lpfc_linkup(phba);
 	sparam_mbox = NULL;
 
-	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
-		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
-		if (!cfglink_mbox)
-			goto out;
-		vport->port_state = LPFC_LOCAL_CFG_LINK;
-		lpfc_config_link(phba, cfglink_mbox);
-		cfglink_mbox->vport = vport;
-		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
-		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
-		if (rc == MBX_NOT_FINISHED) {
-			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
-			goto out;
-		}
-	}
-
 	sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
 	if (!sparam_mbox)
 		goto out;
@@ -3272,7 +3291,20 @@ lpfc_mbx_process_link_up(struct lpfc_hba
 		goto out;
 	}
 
-	if (phba->hba_flag & HBA_FCOE_MODE) {
+	if (!(phba->hba_flag & HBA_FCOE_MODE)) {
+		cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!cfglink_mbox)
+			goto out;
+		vport->port_state = LPFC_LOCAL_CFG_LINK;
+		lpfc_config_link(phba, cfglink_mbox);
+		cfglink_mbox->vport = vport;
+		cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link;
+		rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT);
+		if (rc == MBX_NOT_FINISHED) {
+			mempool_free(cfglink_mbox, phba->mbox_mem_pool);
+			goto out;
+		}
+	} else {
 		vport->port_state = LPFC_VPORT_UNKNOWN;
 		/*
 		 * Add the driver's default FCF record at FCF index 0 now. This
@@ -3329,10 +3361,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba
 		}
 		/* Reset FCF roundrobin bmask for new discovery */
 		lpfc_sli4_clear_fcf_rr_bmask(phba);
-	} else {
-		if (phba->bbcredit_support && phba->cfg_enable_bbcr &&
-		    !(phba->link_flag & LS_LOOPBACK_MODE))
-			phba->hba_flag |= HBA_DEFER_FLOGI;
 	}
 
 	/* Prepare for LINK up registrations */
author maintainer
#371 lore raw

PATCH 371/388 ALSA: hda/realtek - Couldnt detect Mic if booting with headset plugged

In reply to Greg Kroah-Hartman

From: Hui Wang <[email protected]>

commit 3f74249057827c5f6676c41c18f6be12ce1469ce upstream.

We found a Mic detection issue on many Lenovo laptops, those laptops belong to differnt models and they have different audio design like internal mic connects to the codec or PCH, they all have this problem, the problem is if plugging a headset before powerup/reboot the machine, after booting up, the headphone could be detected but Mic couldn't. If we plug out and plug in the headset, both headphone and Mic could be detected then.

Through debugging we found the codec on those laptops are same, it is alc257, and if we don't disable the 3k pulldown in alc256_shutup(), the issue will be fixed. So far there is no pop noise or power consumption regression on those laptops after this change.

---
 sound/pci/hda/patch_realtek.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
sound/pci/hda/patch_realtek.c +5 -1
@@ -3418,7 +3418,11 @@ static void alc256_shutup(struct hda_cod
 
 	/* 3k pull low control for Headset jack. */
 	/* NOTE: call this before clearing the pin, otherwise codec stalls */
-	alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
+	/* If disable 3k pulldown control for alc257, the Mic detection will not work correctly
+	 * when booting with headset plugged. So skip setting it for the codec alc257
+	 */
+	if (codec->core.vendor_id != 0x10ec0257)
+		alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
 
 	if (!spec->no_shutup_pins)
 		snd_hda_codec_write(codec, hp_pin, 0,
author maintainer
#372 lore raw

PATCH 372/388 ALSA: hda/realtek: Enable front panel headset LED on Lenovo ThinkStation P520

In reply to Greg Kroah-Hartman

From: Kai-Heng Feng <[email protected]>

commit f73bbf639b32acb6b409e188fdde5644b301978f upstream.

On Lenovo P520, the front panel headset LED isn't lit up right now.

Realtek states that the LED needs to be enabled by ALC233's GPIO2, so let's do it accordingly to light the LED up.

---
 sound/pci/hda/patch_realtek.c |    7 +++++++
 1 file changed, 7 insertions(+)
sound/pci/hda/patch_realtek.c +7 -0
@@ -6036,6 +6036,7 @@ static void alc_fixup_thinkpad_acpi(stru
 #include "hp_x360_helper.c"
 
 enum {
+	ALC269_FIXUP_GPIO2,
 	ALC269_FIXUP_SONY_VAIO,
 	ALC275_FIXUP_SONY_VAIO_GPIO2,
 	ALC269_FIXUP_DELL_M101Z,
@@ -6217,6 +6218,10 @@ enum {
 };
 
 static const struct hda_fixup alc269_fixups[] = {
+	[ALC269_FIXUP_GPIO2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio2,
+	},
 	[ALC269_FIXUP_SONY_VAIO] = {
 		.type = HDA_FIXUP_PINCTLS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -7036,6 +7041,8 @@ static const struct hda_fixup alc269_fix
 	[ALC233_FIXUP_LENOVO_MULTI_CODECS] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_alc662_fixup_lenovo_dual_codecs,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_GPIO2
 	},
 	[ALC233_FIXUP_ACER_HEADSET_MIC] = {
 		.type = HDA_FIXUP_VERBS,
author maintainer
#375 lore raw

PATCH 375/388 s390/dasd: Fix zero write for FBA devices

In reply to Greg Kroah-Hartman

From: Jan Höppner <[email protected]>

commit 709192d531e5b0a91f20aa14abfe2fc27ddd47af upstream.

A discard request that writes zeros using the global kernel internal ZERO_PAGE will fail for machines with more than 2GB of memory due to the location of the ZERO_PAGE.

Fix this by using a driver owned global zero page allocated with GFP_DMA flag set.

Fixes 28b841b3a7cb ("s390/dasd: Add discard support for FBA devices")
Cc <[email protected]> # 4.14+
---
 drivers/s390/block/dasd_fba.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/s390/block/dasd_fba.c +8 -1
@@ -40,6 +40,7 @@
 MODULE_LICENSE("GPL");
 
 static struct dasd_discipline dasd_fba_discipline;
+static void *dasd_fba_zero_page;
 
 struct dasd_fba_private {
 	struct dasd_fba_characteristics rdc_data;
@@ -270,7 +271,7 @@ static void ccw_write_zero(struct ccw1 *
 	ccw->cmd_code = DASD_FBA_CCW_WRITE;
 	ccw->flags |= CCW_FLAG_SLI;
 	ccw->count = count;
-	ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0));
+	ccw->cda = (__u32) (addr_t) dasd_fba_zero_page;
 }
 
 /*
@@ -830,6 +831,11 @@ dasd_fba_init(void)
 	int ret;
 
 	ASCEBC(dasd_fba_discipline.ebcname, 4);
+
+	dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA);
+	if (!dasd_fba_zero_page)
+		return -ENOMEM;
+
 	ret = ccw_driver_register(&dasd_fba_driver);
 	if (!ret)
 		wait_for_device_probe();
@@ -841,6 +847,7 @@ static void __exit
 dasd_fba_cleanup(void)
 {
 	ccw_driver_unregister(&dasd_fba_driver);
+	free_page((unsigned long)dasd_fba_zero_page);
 }
 
 module_init(dasd_fba_init);
author maintainer
#374 lore raw

PATCH 374/388 tracing: fix double free

In reply to Greg Kroah-Hartman

From: Tom Rix <[email protected]>

commit 46bbe5c671e06f070428b9be142cc4ee5cedebac upstream.

clang static analyzer reports this problem

trace_events_hist.c:3824:3: warning: Attempt to free
released memory

    kfree(hist_data->attrs->var_defs.name[i]);

In parse_var_defs() if there is a problem allocating var_defs.expr, the earlier var_defs.name is freed. This free is duplicated by free_var_defs() which frees the rest of the list.

Because free_var_defs() has to run anyway, remove the second free fom parse_var_defs().

Fixes 30350d65ac56 ("tracing: Add variable support to hist triggers")
---
 kernel/trace/trace_events_hist.c |    1 -
 1 file changed, 1 deletion(-)
kernel/trace/trace_events_hist.c +0 -1
@@ -4770,7 +4770,6 @@ static int parse_var_defs(struct hist_tr
 
 			s = kstrdup(field_str, GFP_KERNEL);
 			if (!s) {
-				kfree(hist_data->attrs->var_defs.name[n_vars]);
 				ret = -ENOMEM;
 				goto free;
 			}
author maintainer
#373 lore raw

PATCH 373/388 lib/string.c: implement stpcpy

In reply to Greg Kroah-Hartman

From: Nick Desaulniers <[email protected]>

commit 1e1b6d63d6340764e00356873e5794225a2a03ea upstream.

LLVM implemented a recent "libcall optimization" that lowers calls to sprintf(dest, "%s", str) where the return value is used to stpcpy(dest, str) - dest.

This generally avoids the machinery involved in parsing format strings. stpcpy is just like strcpy except it returns the pointer to the new tail of dest. This optimization was introduced into clang-12.

Implement this so that we don't observe linkage failures due to missing symbol definitions for stpcpy.

Similar to last year's fire drill with: commit 5f074f3e192f ("lib/string.c: implement a basic bcmp")

The kernel is somewhere between a "freestanding" environment (no full libc) and "hosted" environment (many symbols from libc exist with the same type, function signature, and semantics).

As Peter Anvin notes, there's not really a great way to inform the compiler that you're targeting a freestanding environment but would like to opt-in to some libcall optimizations (see pr/47280 below), rather than opt-out.

Arvind notes, -fno-builtin-* behaves slightly differently between GCC and Clang, and Clang is missing many __builtin_* definitions, which I consider a bug in Clang and am working on fixing.

Masahiro summarizes the subtle distinction between compilers justly:
To prevent transformation from foo() into bar(), there are two ways in Clang to do that; -fno-builtin-foo, and -fno-builtin-bar. There is only one in GCC; -fno-buitin-foo.

(Any difference in that behavior in Clang is likely a bug from a missing __builtin_* definition.)

Masahiro also notes:
We want to disable optimization from foo() to bar(),
but we may still benefit from the optimization from foo() into something else. If GCC implements the same transform, we would run into a problem because it is not -fno-builtin-bar, but -fno-builtin-foo that disables that optimization.

In this regard, -fno-builtin-foo would be more future-proof than -fno-built-bar, but -fno-builtin-foo is still potentially overkill. We may want to prevent calls from foo() being optimized into calls to bar(), but we still may want other optimization on calls to foo().

It seems that compilers today don't quite provide the fine grain control over which libcall optimizations pseudo-freestanding environments would prefer.

Finally, Kees notes that this interface is unsafe, so we should not encourage its use. As such, I've removed the declaration from any header, but it still needs to be exported to avoid linkage errors in modules.

---
 lib/string.c |   24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
lib/string.c +24 -0
@@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const ch
 }
 EXPORT_SYMBOL(strscpy_pad);
 
+/**
+ * stpcpy - copy a string from src to dest returning a pointer to the new end
+ *          of dest, including src's %NUL-terminator. May overrun dest.
+ * @dest: pointer to end of string being copied into. Must be large enough
+ *        to receive copy.
+ * @src: pointer to the beginning of string being copied from. Must not overlap
+ *       dest.
+ *
+ * stpcpy differs from strcpy in a key way: the return value is a pointer
+ * to the new %NUL-terminating character in @dest. (For strcpy, the return
+ * value is a pointer to the start of @dest). This interface is considered
+ * unsafe as it doesn't perform bounds checking of the inputs. As such it's
+ * not recommended for usage. Instead, its definition is provided in case
+ * the compiler lowers other libcalls to stpcpy.
+ */
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src);
+char *stpcpy(char *__restrict__ dest, const char *__restrict__ src)
+{
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return --dest;
+}
+EXPORT_SYMBOL(stpcpy);
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
author maintainer
#352 lore raw

PATCH 352/388 batman-adv: Add missing include for in_interrupt()

In reply to Greg Kroah-Hartman

From: Sven Eckelmann <[email protected]>

[ Upstream commit 4bba9dab86b6ac15ca560ef1f2b5aa4529cbf784 ]

The fix for receiving (internally generated) bla packets outside the interrupt context introduced the usage of in_interrupt(). But this functionality is only defined in linux/preempt.h which was not included with the same patch.

Fixes 279e89b2281a ("batman-adv: bla: use netif_rx_ni when not in interrupt context")
---
 net/batman-adv/bridge_loop_avoidance.c | 1 +
 1 file changed, 1 insertion(+)
net/batman-adv/bridge_loop_avoidance.c +1 -0
index 62d2e766dd392..fe406c17b2c0a 100644
@@ -25,6 +25,7 @@
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
+#include <linux/preempt.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/seq_file.h>
Signature · 1 line
2.25.1
author maintainer
#353 lore raw

PATCH 353/388 nvme-tcp: fix kconfig dependency warning when !CRYPTO

In reply to Greg Kroah-Hartman

From: Necip Fazil Yildiran <[email protected]>

[ Upstream commit af5ad17854f96a6d3c9775e776bd01ab262672a1 ]

When NVME_TCP is enabled and CRYPTO is disabled, it results in the following Kbuild warning:

WARNING: unmet direct dependencies detected for CRYPTO_CRC32C
Depends on [n]: CRYPTO [=n]
Selected by [y]:
- NVME_TCP [=y] && INET [=y] && BLK_DEV_NVME [=y]

The reason is that NVME_TCP selects CRYPTO_CRC32C without depending on or selecting CRYPTO while CRYPTO_CRC32C is subordinate to CRYPTO.

Honor the kconfig menu hierarchy to remove kconfig dependency warnings.

Fixes 79fd751d61aa ("nvme: tcp: selects CRYPTO_CRC32C for nvme-tcp")
---
 drivers/nvme/host/Kconfig | 1 +
 1 file changed, 1 insertion(+)
drivers/nvme/host/Kconfig +1 -0
index 2b36f052bfb91..7b3f6555e67ba 100644
@@ -64,6 +64,7 @@ config NVME_TCP
 	depends on INET
 	depends on BLK_DEV_NVME
 	select NVME_FABRICS
+	select CRYPTO
 	select CRYPTO_CRC32C
 	help
 	  This provides support for the NVMe over Fabrics protocol using
Signature · 1 line
2.25.1
author maintainer
#378 lore raw

PATCH 378/388 btrfs: fix overflow when copying corrupt csums for a message

In reply to Greg Kroah-Hartman

From: Johannes Thumshirn <[email protected]>

commit 35be8851d172c6e3db836c0f28c19087b10c9e00 upstream.

Syzkaller reported a buffer overflow in btree_readpage_end_io_hook() when loop mounting a crafted image:

detected buffer overflow in memcpy

  ------------[ cut here ]------------
  kernel BUG at lib/string.c:1129!
  invalid opcode: 0000 [#1] PREEMPT SMP KASAN
  CPU: 1 PID: 26 Comm: kworker/u4:2 Not tainted 5.9.0-rc4-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
  Workqueue: btrfs-endio-meta btrfs_work_helper
  RIP: 0010:fortify_panic+0xf/0x20 lib/string.c:1129
  RSP: 0018:ffffc90000e27980 EFLAGS: 00010286
  RAX: 0000000000000022 RBX: ffff8880a80dca64 RCX: 0000000000000000
  RDX: ffff8880a90860c0 RSI: ffffffff815dba07 RDI: fffff520001c4f22
  RBP: ffff8880a80dca00 R08: 0000000000000022 R09: ffff8880ae7318e7
  R10: 0000000000000000 R11: 0000000000077578 R12: 00000000ffffff6e
  R13: 0000000000000008 R14: ffffc90000e27a40 R15: 1ffff920001c4f3c
  FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000557335f440d0 CR3: 000000009647d000 CR4: 00000000001506e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   memcpy include/linux/string.h:405 [inline]
   btree_readpage_end_io_hook.cold+0x206/0x221 fs/btrfs/disk-io.c:642
   end_bio_extent_readpage+0x4de/0x10c0 fs/btrfs/extent_io.c:2854
   bio_endio+0x3cf/0x7f0 block/bio.c:1449
   end_workqueue_fn+0x114/0x170 fs/btrfs/disk-io.c:1695
   btrfs_work_helper+0x221/0xe20 fs/btrfs/async-thread.c:318
   process_one_work+0x94c/0x1670 kernel/workqueue.c:2269
   worker_thread+0x64c/0x1120 kernel/workqueue.c:2415
   kthread+0x3b5/0x4a0 kernel/kthread.c:292
   ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:294
  Modules linked in:
  ---[ end trace b68924293169feef ]---
  RIP: 0010:fortify_panic+0xf/0x20 lib/string.c:1129
  RSP: 0018:ffffc90000e27980 EFLAGS: 00010286
  RAX: 0000000000000022 RBX: ffff8880a80dca64 RCX: 0000000000000000
  RDX: ffff8880a90860c0 RSI: ffffffff815dba07 RDI: fffff520001c4f22
  RBP: ffff8880a80dca00 R08: 0000000000000022 R09: ffff8880ae7318e7
  R10: 0000000000000000 R11: 0000000000077578 R12: 00000000ffffff6e
  R13: 0000000000000008 R14: ffffc90000e27a40 R15: 1ffff920001c4f3c
  FS:  0000000000000000(0000) GS:ffff8880ae700000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f95b7c4d008 CR3: 000000009647d000 CR4: 00000000001506e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

The overflow happens, because in btree_readpage_end_io_hook() we assume that we have found a 4 byte checksum instead of the real possible 32 bytes we have for the checksums.

With the fix applied:

[   35.726623] BTRFS: device fsid 815caf9a-dc43-4d2a-ac54-764b8333d765 devid 1 transid 5 /dev/loop0 scanned by syz-repro (215)
[   35.738994] BTRFS info (device loop0): disk space caching is enabled
[   35.738998] BTRFS info (device loop0): has skinny extents
[   35.743337] BTRFS warning (device loop0): loop0 checksum verify failed on 1052672 wanted 0xf9c035fc8d239a54 found 0x67a25c14b7eabcf9 level 0
[   35.743420] BTRFS error (device loop0): failed to read chunk root
[   35.745899] BTRFS error (device loop0): open_ctree failed
Reported-by [email protected]
Fixes d5178578bcd4 ("btrfs: directly call into crypto framework for checksumming")
---
 fs/btrfs/disk-io.c |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)
fs/btrfs/disk-io.c +5 -6
@@ -649,16 +649,15 @@ static int btree_readpage_end_io_hook(st
 		goto err;
 
 	if (memcmp_extent_buffer(eb, result, 0, csum_size)) {
-		u32 val;
-		u32 found = 0;
-
-		memcpy(&found, result, csum_size);
+		u8 val[BTRFS_CSUM_SIZE] = { 0 };
 
 		read_extent_buffer(eb, &val, 0, csum_size);
 		btrfs_warn_rl(fs_info,
-		"%s checksum verify failed on %llu wanted %x found %x level %d",
+	"%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d",
 			      fs_info->sb->s_id, eb->start,
-			      val, found, btrfs_header_level(eb));
+			      CSUM_FMT_VALUE(csum_size, val),
+			      CSUM_FMT_VALUE(csum_size, result),
+			      btrfs_header_level(eb));
 		ret = -EUCLEAN;
 		goto err;
 	}
author maintainer
#351 lore raw

PATCH 351/388 drm/sun4i: sun8i-csc: Secondary CSC register correction

In reply to Greg Kroah-Hartman

From: Martin Cerveny <[email protected]>

[ Upstream commit cab4c03b4ba54c8d9378298cacb8bc0fd74ceece ]

"Allwinner V3s" has secondary video layer (VI). Decoded video is displayed in wrong colors until secondary CSC registers are programmed correctly.

---
 drivers/gpu/drm/sun4i/sun8i_csc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/sun4i/sun8i_csc.h +1 -1
index f42441b1b14dd..a55a38ad849c1 100644
@@ -12,7 +12,7 @@ struct sun8i_mixer;
 
 /* VI channel CSC units offsets */
 #define CCSC00_OFFSET 0xAA050
-#define CCSC01_OFFSET 0xFA000
+#define CCSC01_OFFSET 0xFA050
 #define CCSC10_OFFSET 0xA0000
 #define CCSC11_OFFSET 0xF0000
 
Signature · 1 line
2.25.1
author maintainer
#382 lore raw

PATCH 382/388 s390/zcrypt: Fix ZCRYPT_PERDEV_REQCNT ioctl

In reply to Greg Kroah-Hartman

From: Christian Borntraeger <[email protected]>

commit f7e80983f0cf470bb82036e73bff4d5a7daf8fc2 upstream.

reqcnt is an u32 pointer but we do copy sizeof(reqcnt) which is the size of the pointer. This means we only copy 8 byte. Let us copy the full monty.

Cc Harald Freudenberger <[email protected]>
Fixes af4a72276d49 ("s390/zcrypt: Support up to 256 crypto adapters.")
---
 drivers/s390/crypto/zcrypt_api.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/s390/crypto/zcrypt_api.c +2 -1
@@ -1419,7 +1419,8 @@ static long zcrypt_unlocked_ioctl(struct
 		if (!reqcnt)
 			return -ENOMEM;
 		zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES);
-		if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt)))
+		if (copy_to_user((int __user *) arg, reqcnt,
+				 sizeof(u32) * AP_DEVICES))
 			rc = -EFAULT;
 		kfree(reqcnt);
 		return rc;
author maintainer
#384 lore raw

PATCH 384/388 dm: fix bio splitting and its bio completion order for regular IO

In reply to Greg Kroah-Hartman

From: Mike Snitzer <[email protected]>

commit ee1dfad5325ff1cfb2239e564cd411b3bfe8667a upstream.

dm_queue_split() is removed because __split_and_process_bio() _must_ handle splitting bios to ensure proper bio submission and completion ordering as a bio is split.

Otherwise, multiple recursive calls to ->submit_bio will cause multiple split bios to be allocated from the same ->bio_split mempool at the same time. This would result in deadlock in low memory conditions because no progress could be made (only one bio is available in ->bio_split mempool).

This fix has been verified to still fix the loss of performance, due to excess splitting, that commit 120c9257f5f1 provided.

Fixes 120c9257f5f1 ("Revert "dm: always call blk_queue_split() in dm_process_bio()"")
Cc [email protected] # 5.0+, requires custom backport due to 5.9 changes
---
 drivers/md/dm.c |   23 ++---------------------
 1 file changed, 2 insertions(+), 21 deletions(-)
drivers/md/dm.c +2 -21
@@ -1720,23 +1720,6 @@ out:
 	return ret;
 }
 
-static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struct bio **bio)
-{
-	unsigned len, sector_count;
-
-	sector_count = bio_sectors(*bio);
-	len = min_t(sector_t, max_io_len((*bio)->bi_iter.bi_sector, ti), sector_count);
-
-	if (sector_count > len) {
-		struct bio *split = bio_split(*bio, len, GFP_NOIO, &md->queue->bio_split);
-
-		bio_chain(split, *bio);
-		trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector);
-		generic_make_request(*bio);
-		*bio = split;
-	}
-}
-
 static blk_qc_t dm_process_bio(struct mapped_device *md,
 			       struct dm_table *map, struct bio *bio)
 {
@@ -1764,14 +1747,12 @@ static blk_qc_t dm_process_bio(struct ma
 	if (current->bio_list) {
 		if (is_abnormal_io(bio))
 			blk_queue_split(md->queue, &bio);
-		else
-			dm_queue_split(md, ti, &bio);
+		/* regular IO is split by __split_and_process_bio */
 	}
 
 	if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
 		return __process_bio(md, map, bio, ti);
-	else
-		return __split_and_process_bio(md, map, bio);
+	return __split_and_process_bio(md, map, bio);
 }
 
 static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
author maintainer
#377 lore raw

PATCH 377/388 kprobes: tracing/kprobes: Fix to kill kprobes on initmem after boot

In reply to Greg Kroah-Hartman

From: Masami Hiramatsu <[email protected]>

commit 82d083ab60c3693201c6f5c7a5f23a6ed422098d upstream.

Since kprobe_event= cmdline option allows user to put kprobes on the functions in initmem, kprobe has to make such probes gone after boot. Currently the probes on the init functions in modules will be handled by module callback, but the kernel init text isn't handled. Without this, kprobes may access non-exist text area to disable or remove it.

Fixes 970988e19eb0 ("tracing/kprobe: Add kprobe_event= boot parameter")
Cc Jonathan Corbet <[email protected]>
Cc Shuah Khan <[email protected]>
Cc Randy Dunlap <[email protected]>
Cc Ingo Molnar <[email protected]>
---
 include/linux/kprobes.h |    5 +++++
 init/main.c             |    2 ++
 kernel/kprobes.c        |   22 ++++++++++++++++++++++
 3 files changed, 29 insertions(+)
include/linux/kprobes.h +5 -0
@@ -369,6 +369,8 @@ void unregister_kretprobes(struct kretpr
 void kprobe_flush_task(struct task_struct *tk);
 void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
+void kprobe_free_init_mem(void);
+
 int disable_kprobe(struct kprobe *kp);
 int enable_kprobe(struct kprobe *kp);
 
@@ -426,6 +428,9 @@ static inline void unregister_kretprobes
 static inline void kprobe_flush_task(struct task_struct *tk)
 {
 }
+static inline void kprobe_free_init_mem(void)
+{
+}
 static inline int disable_kprobe(struct kprobe *kp)
 {
 	return -ENOSYS;
init/main.c +2 -0
@@ -32,6 +32,7 @@
 #include <linux/nmi.h>
 #include <linux/percpu.h>
 #include <linux/kmod.h>
+#include <linux/kprobes.h>
 #include <linux/vmalloc.h>
 #include <linux/kernel_stat.h>
 #include <linux/start_kernel.h>
@@ -1111,6 +1112,7 @@ static int __ref kernel_init(void *unuse
 	kernel_init_freeable();
 	/* need to finish all async __init code before freeing the memory */
 	async_synchronize_full();
+	kprobe_free_init_mem();
 	ftrace_free_init_mem();
 	free_initmem();
 	mark_readonly();
kernel/kprobes.c +22 -0
@@ -2309,6 +2309,28 @@ static struct notifier_block kprobe_modu
 extern unsigned long __start_kprobe_blacklist[];
 extern unsigned long __stop_kprobe_blacklist[];
 
+void kprobe_free_init_mem(void)
+{
+	void *start = (void *)(&__init_begin);
+	void *end = (void *)(&__init_end);
+	struct hlist_head *head;
+	struct kprobe *p;
+	int i;
+
+	mutex_lock(&kprobe_mutex);
+
+	/* Kill all kprobes on initmem */
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry(p, head, hlist) {
+			if (start <= (void *)p->addr && (void *)p->addr < end)
+				kill_kprobe(p);
+		}
+	}
+
+	mutex_unlock(&kprobe_mutex);
+}
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
author maintainer
#387 lore raw

PATCH 387/388 ata: make qc_prep return ata_completion_errors

In reply to Greg Kroah-Hartman

From: Jiri Slaby <[email protected]>

commit 95364f36701e62dd50eee91e1303187fd1a9f567 upstream.

In case a driver wants to return an error from qc_prep, return enum ata_completion_errors. sata_mv is one of those drivers -- see the next patch. Other drivers return the newly defined AC_ERR_OK.

[v2] use enum ata_completion_errors and AC_ERR_OK.

---
 Documentation/driver-api/libata.rst |    2 +-
 drivers/ata/acard-ahci.c            |    6 ++++--
 drivers/ata/libahci.c               |    6 ++++--
 drivers/ata/libata-core.c           |    9 +++++++--
 drivers/ata/libata-sff.c            |   12 ++++++++----
 drivers/ata/pata_macio.c            |    6 ++++--
 drivers/ata/pata_pxa.c              |    8 +++++---
 drivers/ata/pdc_adma.c              |    7 ++++---
 drivers/ata/sata_fsl.c              |    4 +++-
 drivers/ata/sata_inic162x.c         |    4 +++-
 drivers/ata/sata_mv.c               |   26 +++++++++++++++-----------
 drivers/ata/sata_nv.c               |   18 +++++++++++-------
 drivers/ata/sata_promise.c          |    6 ++++--
 drivers/ata/sata_qstor.c            |    8 +++++---
 drivers/ata/sata_rcar.c             |    6 ++++--
 drivers/ata/sata_sil.c              |    8 +++++---
 drivers/ata/sata_sil24.c            |    6 ++++--
 drivers/ata/sata_sx4.c              |    6 ++++--
 include/linux/libata.h              |   12 ++++++------
 19 files changed, 101 insertions(+), 59 deletions(-)
Documentation/driver-api/libata.rst +1 -1
@@ -250,7 +250,7 @@ High-level taskfile hooks
 
 ::
 
-    void (*qc_prep) (struct ata_queued_cmd *qc);
+    enum ata_completion_errors (*qc_prep) (struct ata_queued_cmd *qc);
     int (*qc_issue) (struct ata_queued_cmd *qc);
 
 
drivers/ata/acard-ahci.c +4 -2
@@ -56,7 +56,7 @@ struct acard_sg {
 	__le32			size;	 /* bit 31 (EOT) max==0x10000 (64k) */
 };
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc);
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int acard_ahci_port_start(struct ata_port *ap);
 static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -210,7 +210,7 @@ static unsigned int acard_ahci_fill_sg(s
 	return si;
 }
 
-static void acard_ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors acard_ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -248,6 +248,8 @@ static void acard_ahci_qc_prep(struct at
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
drivers/ata/libahci.c +4 -2
@@ -57,7 +57,7 @@ static int ahci_scr_write(struct ata_lin
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int ahci_port_start(struct ata_port *ap);
 static void ahci_port_stop(struct ata_port *ap);
-static void ahci_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc);
 static int ahci_pmp_qc_defer(struct ata_queued_cmd *qc);
 static void ahci_freeze(struct ata_port *ap);
 static void ahci_thaw(struct ata_port *ap);
@@ -1624,7 +1624,7 @@ static int ahci_pmp_qc_defer(struct ata_
 		return sata_pmp_qc_defer_cmd_switch(qc);
 }
 
-static void ahci_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors ahci_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct ahci_port_priv *pp = ap->private_data;
@@ -1660,6 +1660,8 @@ static void ahci_qc_prep(struct ata_queu
 		opts |= AHCI_CMD_ATAPI | AHCI_CMD_PREFETCH;
 
 	ahci_fill_cmd_slot(pp, qc->hw_tag, opts);
+
+	return AC_ERR_OK;
 }
 
 static void ahci_fbs_dec_intr(struct ata_port *ap)
drivers/ata/libata-core.c +7 -2
@@ -4978,7 +4978,10 @@ int ata_std_qc_defer(struct ata_queued_c
 	return ATA_DEFER_LINK;
 }
 
-void ata_noop_qc_prep(struct ata_queued_cmd *qc) { }
+enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc)
+{
+	return AC_ERR_OK;
+}
 
 /**
  *	ata_sg_init - Associate command with scatter-gather table.
@@ -5465,7 +5468,9 @@ void ata_qc_issue(struct ata_queued_cmd
 		return;
 	}
 
-	ap->ops->qc_prep(qc);
+	qc->err_mask |= ap->ops->qc_prep(qc);
+	if (unlikely(qc->err_mask))
+		goto err;
 	trace_ata_qc_issue(qc);
 	qc->err_mask |= ap->ops->qc_issue(qc);
 	if (unlikely(qc->err_mask))
drivers/ata/libata-sff.c +8 -4
@@ -2679,12 +2679,14 @@ static void ata_bmdma_fill_sg_dumb(struc
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
 
@@ -2697,12 +2699,14 @@ EXPORT_SYMBOL_GPL(ata_bmdma_qc_prep);
  *	LOCKING:
  *	spin_lock_irqsave(host lock)
  */
-void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
+enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	ata_bmdma_fill_sg_dumb(qc);
+
+	return AC_ERR_OK;
 }
 EXPORT_SYMBOL_GPL(ata_bmdma_dumb_qc_prep);
 
drivers/ata/pata_macio.c +4 -2
@@ -510,7 +510,7 @@ static int pata_macio_cable_detect(struc
 	return ATA_CBL_PATA40;
 }
 
-static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 {
 	unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE);
 	struct ata_port *ap = qc->ap;
@@ -523,7 +523,7 @@ static void pata_macio_qc_prep(struct at
 		   __func__, qc, qc->flags, write, qc->dev->devno);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	table = (struct dbdma_cmd *) priv->dma_table_cpu;
 
@@ -568,6 +568,8 @@ static void pata_macio_qc_prep(struct at
 	table->command = cpu_to_le16(DBDMA_STOP);
 
 	dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi);
+
+	return AC_ERR_OK;
 }
 
 
drivers/ata/pata_pxa.c +5 -3
@@ -44,25 +44,27 @@ static void pxa_ata_dma_irq(void *d)
 /*
  * Prepare taskfile for submission.
  */
-static void pxa_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pxa_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pata_pxa_data *pd = qc->ap->private_data;
 	struct dma_async_tx_descriptor *tx;
 	enum dma_transfer_direction dir;
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	dir = (qc->dma_dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM);
 	tx = dmaengine_prep_slave_sg(pd->dma_chan, qc->sg, qc->n_elem, dir,
 				     DMA_PREP_INTERRUPT);
 	if (!tx) {
 		ata_dev_err(qc->dev, "prep_slave_sg() failed\n");
-		return;
+		return AC_ERR_OK;
 	}
 	tx->callback = pxa_ata_dma_irq;
 	tx->callback_param = pd;
 	pd->dma_cookie = dmaengine_submit(tx);
+
+	return AC_ERR_OK;
 }
 
 /*
drivers/ata/pdc_adma.c +4 -3
@@ -116,7 +116,7 @@ static int adma_ata_init_one(struct pci_
 				const struct pci_device_id *ent);
 static int adma_port_start(struct ata_port *ap);
 static void adma_port_stop(struct ata_port *ap);
-static void adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int adma_qc_issue(struct ata_queued_cmd *qc);
 static int adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static void adma_freeze(struct ata_port *ap);
@@ -295,7 +295,7 @@ static int adma_fill_sg(struct ata_queue
 	return i;
 }
 
-static void adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct adma_port_priv *pp = qc->ap->private_data;
 	u8  *buf = pp->pkt;
@@ -306,7 +306,7 @@ static void adma_qc_prep(struct ata_queu
 
 	adma_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	buf[i++] = 0;	/* Response flags */
 	buf[i++] = 0;	/* reserved */
@@ -371,6 +371,7 @@ static void adma_qc_prep(struct ata_queu
 			printk("%s\n", obuf);
 	}
 #endif
+	return AC_ERR_OK;
 }
 
 static inline void adma_packet_start(struct ata_queued_cmd *qc)
drivers/ata/sata_fsl.c +3 -1
@@ -502,7 +502,7 @@ static unsigned int sata_fsl_fill_sg(str
 	return num_prde;
 }
 
-static void sata_fsl_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_fsl_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sata_fsl_port_priv *pp = ap->private_data;
@@ -548,6 +548,8 @@ static void sata_fsl_qc_prep(struct ata_
 
 	VPRINTK("SATA FSL : xx_qc_prep, di = 0x%x, ttl = %d, num_prde = %d\n",
 		desc_info, ttl_dwords, num_prde);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sata_fsl_qc_issue(struct ata_queued_cmd *qc)
drivers/ata/sata_inic162x.c +3 -1
@@ -478,7 +478,7 @@ static void inic_fill_sg(struct inic_prd
 	prd[-1].flags |= PRD_END;
 }
 
-static void inic_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors inic_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct inic_port_priv *pp = qc->ap->private_data;
 	struct inic_pkt *pkt = pp->pkt;
@@ -538,6 +538,8 @@ static void inic_qc_prep(struct ata_queu
 		inic_fill_sg(prd, qc);
 
 	pp->cpb_tbl[0] = pp->pkt_dma;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int inic_qc_issue(struct ata_queued_cmd *qc)
drivers/ata/sata_mv.c +15 -11
@@ -592,8 +592,8 @@ static int mv5_scr_write(struct ata_link
 static int mv_port_start(struct ata_port *ap);
 static void mv_port_stop(struct ata_port *ap);
 static int mv_qc_defer(struct ata_queued_cmd *qc);
-static void mv_qc_prep(struct ata_queued_cmd *qc);
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc);
 static unsigned int mv_qc_issue(struct ata_queued_cmd *qc);
 static int mv_hardreset(struct ata_link *link, unsigned int *class,
 			unsigned long deadline);
@@ -2031,7 +2031,7 @@ static void mv_rw_multi_errata_sata24(st
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2043,15 +2043,15 @@ static void mv_qc_prep(struct ata_queued
 	switch (tf->protocol) {
 	case ATA_PROT_DMA:
 		if (tf->command == ATA_CMD_DSM)
-			return;
+			return AC_ERR_OK;
 		/* fall-thru */
 	case ATA_PROT_NCQ:
 		break;	/* continue below */
 	case ATA_PROT_PIO:
 		mv_rw_multi_errata_sata24(qc);
-		return;
+		return AC_ERR_OK;
 	default:
-		return;
+		return AC_ERR_OK;
 	}
 
 	/* Fill in command request block
@@ -2116,8 +2116,10 @@ static void mv_qc_prep(struct ata_queued
 	mv_crqb_pack_cmd(cw++, tf->command, ATA_REG_CMD, 1);	/* last */
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
@@ -2132,7 +2134,7 @@ static void mv_qc_prep(struct ata_queued
  *      LOCKING:
  *      Inherited from caller.
  */
-static void mv_qc_prep_iie(struct ata_queued_cmd *qc)
+static enum ata_completion_errors mv_qc_prep_iie(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct mv_port_priv *pp = ap->private_data;
@@ -2143,9 +2145,9 @@ static void mv_qc_prep_iie(struct ata_qu
 
 	if ((tf->protocol != ATA_PROT_DMA) &&
 	    (tf->protocol != ATA_PROT_NCQ))
-		return;
+		return AC_ERR_OK;
 	if (tf->command == ATA_CMD_DSM)
-		return;  /* use bmdma for this */
+		return AC_ERR_OK;  /* use bmdma for this */
 
 	/* Fill in Gen IIE command request block */
 	if (!(tf->flags & ATA_TFLAG_WRITE))
@@ -2186,8 +2188,10 @@ static void mv_qc_prep_iie(struct ata_qu
 		);
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 	mv_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 /**
drivers/ata/sata_nv.c +11 -7
@@ -297,7 +297,7 @@ static void nv_ck804_freeze(struct ata_p
 static void nv_ck804_thaw(struct ata_port *ap);
 static int nv_adma_slave_config(struct scsi_device *sdev);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
 static irqreturn_t nv_adma_interrupt(int irq, void *dev_instance);
 static void nv_adma_irq_clear(struct ata_port *ap);
@@ -319,7 +319,7 @@ static void nv_mcp55_freeze(struct ata_p
 static void nv_swncq_error_handler(struct ata_port *ap);
 static int nv_swncq_slave_config(struct scsi_device *sdev);
 static int nv_swncq_port_start(struct ata_port *ap);
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc);
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
 static unsigned int nv_swncq_qc_issue(struct ata_queued_cmd *qc);
 static void nv_swncq_irq_clear(struct ata_port *ap, u16 fis);
@@ -1344,7 +1344,7 @@ static int nv_adma_use_reg_mode(struct a
 	return 1;
 }
 
-static void nv_adma_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct nv_adma_port_priv *pp = qc->ap->private_data;
 	struct nv_adma_cpb *cpb = &pp->cpb[qc->hw_tag];
@@ -1356,7 +1356,7 @@ static void nv_adma_qc_prep(struct ata_q
 			(qc->flags & ATA_QCFLAG_DMAMAP));
 		nv_adma_register_mode(qc->ap);
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	cpb->resp_flags = NV_CPB_RESP_DONE;
@@ -1388,6 +1388,8 @@ static void nv_adma_qc_prep(struct ata_q
 	cpb->ctl_flags = ctl_flags;
 	wmb();
 	cpb->resp_flags = 0;
+
+	return AC_ERR_OK;
 }
 
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc)
@@ -1950,17 +1952,19 @@ static int nv_swncq_port_start(struct at
 	return 0;
 }
 
-static void nv_swncq_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (qc->tf.protocol != ATA_PROT_NCQ) {
 		ata_bmdma_qc_prep(qc);
-		return;
+		return AC_ERR_OK;
 	}
 
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	nv_swncq_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc)
drivers/ata/sata_promise.c +4 -2
@@ -139,7 +139,7 @@ static int pdc_sata_scr_write(struct ata
 static int pdc_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int pdc_common_port_start(struct ata_port *ap);
 static int pdc_sata_port_start(struct ata_port *ap);
-static void pdc_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static int pdc_check_atapi_dma(struct ata_queued_cmd *qc);
@@ -633,7 +633,7 @@ static void pdc_fill_sg(struct ata_queue
 	prd[idx - 1].flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void pdc_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct pdc_port_priv *pp = qc->ap->private_data;
 	unsigned int i;
@@ -665,6 +665,8 @@ static void pdc_qc_prep(struct ata_queue
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static int pdc_is_sataii_tx4(unsigned long flags)
drivers/ata/sata_qstor.c +5 -3
@@ -100,7 +100,7 @@ static int qs_scr_write(struct ata_link
 static int qs_ata_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static int qs_port_start(struct ata_port *ap);
 static void qs_host_stop(struct ata_host *host);
-static void qs_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int qs_qc_issue(struct ata_queued_cmd *qc);
 static int qs_check_atapi_dma(struct ata_queued_cmd *qc);
 static void qs_freeze(struct ata_port *ap);
@@ -260,7 +260,7 @@ static unsigned int qs_fill_sg(struct at
 	return si;
 }
 
-static void qs_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors qs_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct qs_port_priv *pp = qc->ap->private_data;
 	u8 dflags = QS_DF_PORD, *buf = pp->pkt;
@@ -272,7 +272,7 @@ static void qs_qc_prep(struct ata_queued
 
 	qs_enter_reg_mode(qc->ap);
 	if (qc->tf.protocol != ATA_PROT_DMA)
-		return;
+		return AC_ERR_OK;
 
 	nelem = qs_fill_sg(qc);
 
@@ -295,6 +295,8 @@ static void qs_qc_prep(struct ata_queued
 
 	/* frame information structure (FIS) */
 	ata_tf_to_fis(&qc->tf, 0, 1, &buf[32]);
+
+	return AC_ERR_OK;
 }
 
 static inline void qs_packet_start(struct ata_queued_cmd *qc)
drivers/ata/sata_rcar.c +4 -2
@@ -550,12 +550,14 @@ static void sata_rcar_bmdma_fill_sg(stru
 	prd[si - 1].addr |= cpu_to_le32(SATA_RCAR_DTEND);
 }
 
-static void sata_rcar_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sata_rcar_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sata_rcar_bmdma_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static void sata_rcar_bmdma_setup(struct ata_queued_cmd *qc)
drivers/ata/sata_sil.c +5 -3
@@ -103,7 +103,7 @@ static void sil_dev_config(struct ata_de
 static int sil_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int sil_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
 static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed);
-static void sil_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc);
 static void sil_bmdma_setup(struct ata_queued_cmd *qc);
 static void sil_bmdma_start(struct ata_queued_cmd *qc);
 static void sil_bmdma_stop(struct ata_queued_cmd *qc);
@@ -317,12 +317,14 @@ static void sil_fill_sg(struct ata_queue
 		last_prd->flags_len |= cpu_to_le32(ATA_PRD_EOT);
 }
 
-static void sil_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil_qc_prep(struct ata_queued_cmd *qc)
 {
 	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
-		return;
+		return AC_ERR_OK;
 
 	sil_fill_sg(qc);
+
+	return AC_ERR_OK;
 }
 
 static unsigned char sil_get_device_cache_line(struct pci_dev *pdev)
drivers/ata/sata_sil24.c +4 -2
@@ -326,7 +326,7 @@ static void sil24_dev_config(struct ata_
 static int sil24_scr_read(struct ata_link *link, unsigned sc_reg, u32 *val);
 static int sil24_scr_write(struct ata_link *link, unsigned sc_reg, u32 val);
 static int sil24_qc_defer(struct ata_queued_cmd *qc);
-static void sil24_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc);
 static bool sil24_qc_fill_rtf(struct ata_queued_cmd *qc);
 static void sil24_pmp_attach(struct ata_port *ap);
@@ -830,7 +830,7 @@ static int sil24_qc_defer(struct ata_que
 	return ata_std_qc_defer(qc);
 }
 
-static void sil24_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct sil24_port_priv *pp = ap->private_data;
@@ -874,6 +874,8 @@ static void sil24_qc_prep(struct ata_que
 
 	if (qc->flags & ATA_QCFLAG_DMAMAP)
 		sil24_fill_sg(qc, sge);
+
+	return AC_ERR_OK;
 }
 
 static unsigned int sil24_qc_issue(struct ata_queued_cmd *qc)
drivers/ata/sata_sx4.c +4 -2
@@ -202,7 +202,7 @@ static void pdc_error_handler(struct ata
 static void pdc_freeze(struct ata_port *ap);
 static void pdc_thaw(struct ata_port *ap);
 static int pdc_port_start(struct ata_port *ap);
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc);
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc);
 static void pdc_tf_load_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static void pdc_exec_command_mmio(struct ata_port *ap, const struct ata_taskfile *tf);
 static unsigned int pdc20621_dimm_init(struct ata_host *host);
@@ -530,7 +530,7 @@ static void pdc20621_nodata_prep(struct
 	VPRINTK("ata pkt buf ofs %u, mmio copied\n", i);
 }
 
-static void pdc20621_qc_prep(struct ata_queued_cmd *qc)
+static enum ata_completion_errors pdc20621_qc_prep(struct ata_queued_cmd *qc)
 {
 	switch (qc->tf.protocol) {
 	case ATA_PROT_DMA:
@@ -542,6 +542,8 @@ static void pdc20621_qc_prep(struct ata_
 	default:
 		break;
 	}
+
+	return AC_ERR_OK;
 }
 
 static void __pdc20621_push_hdma(struct ata_queued_cmd *qc,
include/linux/libata.h +6 -6
@@ -896,9 +896,9 @@ struct ata_port_operations {
 	/*
 	 * Command execution
 	 */
-	int  (*qc_defer)(struct ata_queued_cmd *qc);
-	int  (*check_atapi_dma)(struct ata_queued_cmd *qc);
-	void (*qc_prep)(struct ata_queued_cmd *qc);
+	int (*qc_defer)(struct ata_queued_cmd *qc);
+	int (*check_atapi_dma)(struct ata_queued_cmd *qc);
+	enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc);
 	unsigned int (*qc_issue)(struct ata_queued_cmd *qc);
 	bool (*qc_fill_rtf)(struct ata_queued_cmd *qc);
 
@@ -1166,7 +1166,7 @@ extern int ata_xfer_mode2shift(unsigned
 extern const char *ata_mode_string(unsigned long xfer_mask);
 extern unsigned long ata_id_xfermask(const u16 *id);
 extern int ata_std_qc_defer(struct ata_queued_cmd *qc);
-extern void ata_noop_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc);
 extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
 		 unsigned int n_elem);
 extern unsigned int ata_dev_classify(const struct ata_taskfile *tf);
@@ -1900,9 +1900,9 @@ extern const struct ata_port_operations
 	.sg_tablesize		= LIBATA_MAX_PRD,		\
 	.dma_boundary		= ATA_DMA_BOUNDARY
 
-extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc);
-extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
+extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc);
 extern unsigned int ata_bmdma_port_intr(struct ata_port *ap,
 				      struct ata_queued_cmd *qc);
 extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance);
author maintainer
#379 lore raw

PATCH 379/388 dmabuf: fix NULL pointer dereference in dma_buf_release()

In reply to Greg Kroah-Hartman

From: Charan Teja Reddy <[email protected]>

commit 19a508bd1ad8e444de86873bf2f2b2ab8edd6552 upstream.

NULL pointer dereference is observed while exporting the dmabuf but failed to allocate the 'struct file' which results into the dropping of the allocated dentry corresponding to this file in the dmabuf fs, which is ending up in dma_buf_release() and accessing the uninitialzed dentry->d_fsdata.

Call stack on 5.4 is below:

 dma_buf_release+0x2c/0x254 drivers/dma-buf/dma-buf.c:88
 __dentry_kill+0x294/0x31c fs/dcache.c:584
 dentry_kill fs/dcache.c:673 [inline]
 dput+0x250/0x380 fs/dcache.c:859
 path_put+0x24/0x40 fs/namei.c:485
 alloc_file_pseudo+0x1a4/0x200 fs/file_table.c:235
 dma_buf_getfile drivers/dma-buf/dma-buf.c:473 [inline]
 dma_buf_export+0x25c/0x3ec drivers/dma-buf/dma-buf.c:585

Fix this by checking for the valid pointer in the dentry->d_fsdata.

Fixes 4ab59c3c638c ("dma-buf: Move dma_buf_release() from fops to dentry_ops")
Cc <[email protected]> [5.7+]
---
 drivers/dma-buf/dma-buf.c |    2 ++
 1 file changed, 2 insertions(+)
drivers/dma-buf/dma-buf.c +2 -0
@@ -59,6 +59,8 @@ static void dma_buf_release(struct dentr
 	struct dma_buf *dmabuf;
 
 	dmabuf = dentry->d_fsdata;
+	if (unlikely(!dmabuf))
+		return;
 
 	BUG_ON(dmabuf->vmapping_counter);
 
author maintainer
#388 lore raw

PATCH 388/388 ata: sata_mv, avoid trigerrable BUG_ON

In reply to Greg Kroah-Hartman

From: Jiri Slaby <[email protected]>

commit e9f691d899188679746eeb96e6cb520459eda9b4 upstream.

There are several reports that the BUG_ON on unsupported command in mv_qc_prep can be triggered under some circumstances:
https://bugzilla.suse.com/show_bug.cgi?id=1110252
https://serverfault.com/questions/888897/raid-problems-after-power-outage
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1652185
https://bugs.centos.org/view.php?id=14998

Let sata_mv handle the failure gracefully: warn about that incl. the failed command number and return an AC_ERR_INVALID error. We can do that now thanks to the previous patch.

Remove also the long-standing FIXME.

[v2] use %.2x as commands are defined as hexa.

---
 drivers/ata/sata_mv.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)
drivers/ata/sata_mv.c +3 -5
@@ -2098,12 +2098,10 @@ static enum ata_completion_errors mv_qc_
 		 * non-NCQ mode are: [RW] STREAM DMA and W DMA FUA EXT, none
 		 * of which are defined/used by Linux.  If we get here, this
 		 * driver needs work.
-		 *
-		 * FIXME: modify libata to give qc_prep a return value and
-		 * return error here.
 		 */
-		BUG_ON(tf->command);
-		break;
+		ata_port_err(ap, "%s: unsupported command: %.2x\n", __func__,
+				tf->command);
+		return AC_ERR_INVALID;
 	}
 	mv_crqb_pack_cmd(cw++, tf->nsect, ATA_REG_NSECT, 0);
 	mv_crqb_pack_cmd(cw++, tf->hob_lbal, ATA_REG_LBAL, 0);
author maintainer
#385 lore raw

PATCH 385/388 kprobes: Fix compiler warning for !CONFIG_KPROBES_ON_FTRACE

In reply to Greg Kroah-Hartman

From: Muchun Song <[email protected]>

commit 10de795a5addd1962406796a6e13ba6cc0fc6bee upstream.

Fix compiler warning(as show below) for !CONFIG_KPROBES_ON_FTRACE.

kernel/kprobes.c: In function 'kill_kprobe':
kernel/kprobes.c:1116:33: warning: statement with no effect [-Wunused-value]
1116 | #define disarm_kprobe_ftrace(p) (-ENODEV)
| ^
kernel/kprobes.c:2154:3: note: in expansion of macro 'disarm_kprobe_ftrace'
2154 | disarm_kprobe_ftrace(p);

Fixes 0cb2f1372baa ("kprobes: Fix NULL pointer dereference at kprobe_ftrace_handler")
---
 kernel/kprobes.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
kernel/kprobes.c +14 -3
@@ -1076,9 +1076,20 @@ static int disarm_kprobe_ftrace(struct k
 		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
-#define prepare_kprobe(p)	arch_prepare_kprobe(p)
-#define arm_kprobe_ftrace(p)	(-ENODEV)
-#define disarm_kprobe_ftrace(p)	(-ENODEV)
+static inline int prepare_kprobe(struct kprobe *p)
+{
+	return arch_prepare_kprobe(p);
+}
+
+static inline int arm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
+
+static inline int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	return -ENODEV;
+}
 #endif
 
 /* Arm a kprobe with text_mutex */
author maintainer
#386 lore raw

PATCH 386/388 ata: define AC_ERR_OK

In reply to Greg Kroah-Hartman

From: Jiri Slaby <[email protected]>

commit 25937580a5065d6fbd92d9c8ebd47145ad80052e upstream.

Since we will return enum ata_completion_errors from qc_prep in the next patch, let's define AC_ERR_OK to mark the OK status.

---
 include/linux/libata.h |    1 +
 1 file changed, 1 insertion(+)
include/linux/libata.h +1 -0
@@ -486,6 +486,7 @@ enum hsm_task_states {
 };
 
 enum ata_completion_errors {
+	AC_ERR_OK		= 0,	    /* no error */
 	AC_ERR_DEV		= (1 << 0), /* device reported error */
 	AC_ERR_HSM		= (1 << 1), /* host state machine violation */
 	AC_ERR_TIMEOUT		= (1 << 2), /* timeout */
author maintainer
#383 lore raw

PATCH 383/388 KVM: arm64: Assume write fault on S1PTW permission fault on instruction fetch

In reply to Greg Kroah-Hartman

From: Marc Zyngier <[email protected]>

commit c4ad98e4b72cb5be30ea282fce935248f2300e62 upstream.

KVM currently assumes that an instruction abort can never be a write. This is in general true, except when the abort is triggered by a S1PTW on instruction fetch that tries to update the S1 page tables (to set AF, for example).

This can happen if the page tables have been paged out and brought back in without seeing a direct write to them (they are thus marked read only), and the fault handling code will make the PT executable(!) instead of writable. The guest gets stuck forever.

In these conditions, the permission fault must be considered as a write so that the Stage-1 update can take place. This is essentially the I-side equivalent of the problem fixed by 60e21a0ef54c ("arm64: KVM:
Take S1 walks into account when determining S2 write faults").

Update kvm_is_write_fault() to return true on IABT+S1PTW, and introduce kvm_vcpu_trap_is_exec_fault() that only return true when no faulting on a S1 fault. Additionally, kvm_vcpu_dabt_iss1tw() is renamed to kvm_vcpu_abt_iss1tw(), as the above makes it plain that it isn't specific to data abort.

---
 arch/arm/include/asm/kvm_emulate.h   |   11 ++++++++---
 arch/arm64/include/asm/kvm_emulate.h |   12 ++++++++++--
 arch/arm64/kvm/hyp/switch.c          |    2 +-
 virt/kvm/arm/mmio.c                  |    2 +-
 virt/kvm/arm/mmu.c                   |    2 +-
 5 files changed, 21 insertions(+), 8 deletions(-)
arch/arm/include/asm/kvm_emulate.h +8 -3
@@ -204,7 +204,7 @@ static inline int kvm_vcpu_dabt_get_rd(s
 	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
 }
 
-static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW;
 }
@@ -236,16 +236,21 @@ static inline bool kvm_vcpu_trap_il_is32
 	return kvm_vcpu_get_hsr(vcpu) & HSR_IL;
 }
 
-static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu)
+static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT;
 }
 
-static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
+static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC;
arch/arm64/include/asm/kvm_emulate.h +10 -2
@@ -299,7 +299,7 @@ static inline int kvm_vcpu_dabt_get_rd(c
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW);
 }
@@ -307,7 +307,7 @@ static inline bool kvm_vcpu_dabt_iss1tw(
 static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+		kvm_vcpu_abt_iss1tw(vcpu); /* AF/DBM update */
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -336,6 +336,11 @@ static inline bool kvm_vcpu_trap_is_iabt
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC;
@@ -373,6 +378,9 @@ static inline int kvm_vcpu_sys_get_rt(st
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 
arch/arm64/kvm/hyp/switch.c +1 -1
@@ -496,7 +496,7 @@ static bool __hyp_text fixup_guest_exit(
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_dabt_isextabt(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
+			!kvm_vcpu_abt_iss1tw(vcpu);
 
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
virt/kvm/arm/mmio.c +1 -1
@@ -130,7 +130,7 @@ static int decode_hsr(struct kvm_vcpu *v
 	bool sign_extend;
 	bool sixty_four;
 
-	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+	if (kvm_vcpu_abt_iss1tw(vcpu)) {
 		/* page table accesses IO mem: tell guest to fix its TTBR */
 		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 		return 1;
virt/kvm/arm/mmu.c +1 -1
@@ -1690,7 +1690,7 @@ static int user_mem_abort(struct kvm_vcp
 	unsigned long vma_pagesize, flags = 0;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
 	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {