May 2022 - Linux-stable-mirror

FAILED: patch "[PATCH] perf symbol: Remove arch__symbols__fixup_end()" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From a5d20d42a2f2dc2b2f9e9361912062732414090d Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:48 -0700 Subject: [PATCH] perf symbol: Remove arch__symbols__fixup_end() Now the generic code can handle kallsyms fixup properly so no need to keep the arch-functions anymore. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d2ce31e28cd7..41c1596e5207 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -8,27 +8,6 @@ #include "callchain.h" #include "record.h" -/* On arm64, kernel text segment starts at high memory address, - * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory - * address, like 0xffff 0000 00ax xxxx. When only small amount of - * memory is used by modules, gap between end of module's text segment - * and start of kernel text segment may reach 2G. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -#define SYMBOL_LIMIT (1 << 12) /* 4K */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || - (strchr(p->name, '[') == NULL && strchr(c->name, '['))) - /* Limit range of last symbol in module and kernel */ - p->end += SYMBOL_LIMIT; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} - void arch__add_leaf_frame_record_opts(struct record_opts *opts) { opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 8a79c4126e5b..0115f3166568 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c deleted file mode 100644 index e652a1aa8132..000000000000 --- a/tools/perf/arch/powerpc/util/machine.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include <internal/lib.h> // page_size -#include "debug.h" -#include "symbol.h" - -/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 - * whereas the modules are located at very high memory addresses, - * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very high. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Limit the range of last kernel symbol */ - p->end += page_size; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 7644a4f6d4a4..98bc3f39d5f3 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } - -/* On s390 kernel text segment start is located at very low memory addresses, - * for example 0x10000. Modules are located at very high memory addresses, - * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very big. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Last kernel symbol mapped to end of page */ - p->end = roundup(p->end, page_size); - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 623094e866fd..f72baf636724 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str) return tail - str; } -void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - p->end = c->start; -} - const char * __weak arch__normalize_symbol_name(const char *name) { return name; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 5fcdd1f94c56..0b893dcc8ea6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n);

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Update symbols__fixup_end()" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8799ebce84d672aae1dc3170510f6a3e66f96b11 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:47 -0700 Subject: [PATCH] perf symbol: Update symbols__fixup_end() Now arch-specific functions all do the same thing. When it fixes the symbol address it needs to check the boundary between the kernel image and modules. For the last symbol in the previous region, it cannot know the exact size as it's discarded already. Thus it just uses a small page size (4096) and rounds it up like the last symbol. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1b85cc1422a9..623094e866fd 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,8 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols, - bool is_kallsyms __maybe_unused) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -232,8 +232,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols, prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Update symbols__fixup_end()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8799ebce84d672aae1dc3170510f6a3e66f96b11 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:47 -0700 Subject: [PATCH] perf symbol: Update symbols__fixup_end() Now arch-specific functions all do the same thing. When it fixes the symbol address it needs to check the boundary between the kernel image and modules. For the last symbol in the previous region, it cannot know the exact size as it's discarded already. Thus it just uses a small page size (4096) and rounds it up like the last symbol. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1b85cc1422a9..623094e866fd 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,8 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols, - bool is_kallsyms __maybe_unused) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -232,8 +232,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols, prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Update symbols__fixup_end()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 8799ebce84d672aae1dc3170510f6a3e66f96b11 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:47 -0700 Subject: [PATCH] perf symbol: Update symbols__fixup_end() Now arch-specific functions all do the same thing. When it fixes the symbol address it needs to check the boundary between the kernel image and modules. For the last symbol in the previous region, it cannot know the exact size as it's discarded already. Thus it just uses a small page size (4096) and rounds it up like the last symbol. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-3-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 1b85cc1422a9..623094e866fd 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,8 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols, - bool is_kallsyms __maybe_unused) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -232,8 +232,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols, prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end()" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 838425f2defe5262906b698752d28fd2fca1aac2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:46 -0700 Subject: [PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end() The symbol fixup is necessary for symbols in kallsyms since they don't have size info. So we use the next symbol's address to calculate the size. Now it's also used for user binaries because sometimes they miss size for hand-written asm functions. There's a arch-specific function to handle kallsyms differently but currently it cannot distinguish kallsyms from others. Pass this information explicitly to handle it properly. Note that those arch functions will be moved to the generic function so I didn't added it to the arch-functions. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..1b85cc1422a9 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,7 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols) +void symbols__fixup_end(struct rb_root_cached *symbols, + bool is_kallsyms __maybe_unused) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -1467,7 +1468,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1660,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..5fcdd1f94c56 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end()" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 838425f2defe5262906b698752d28fd2fca1aac2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:46 -0700 Subject: [PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end() The symbol fixup is necessary for symbols in kallsyms since they don't have size info. So we use the next symbol's address to calculate the size. Now it's also used for user binaries because sometimes they miss size for hand-written asm functions. There's a arch-specific function to handle kallsyms differently but currently it cannot distinguish kallsyms from others. Pass this information explicitly to handle it properly. Note that those arch functions will be moved to the generic function so I didn't added it to the arch-functions. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..1b85cc1422a9 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,7 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols) +void symbols__fixup_end(struct rb_root_cached *symbols, + bool is_kallsyms __maybe_unused) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -1467,7 +1468,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1660,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..5fcdd1f94c56 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 838425f2defe5262906b698752d28fd2fca1aac2 Mon Sep 17 00:00:00 2001 From: Namhyung Kim <namhyung(a)kernel.org> Date: Fri, 15 Apr 2022 17:40:46 -0700 Subject: [PATCH] perf symbol: Pass is_kallsyms to symbols__fixup_end() The symbol fixup is necessary for symbols in kallsyms since they don't have size info. So we use the next symbol's address to calculate the size. Now it's also used for user binaries because sometimes they miss size for hand-written asm functions. There's a arch-specific function to handle kallsyms differently but currently it cannot distinguish kallsyms from others. Pass this information explicitly to handle it properly. Note that those arch functions will be moved to the generic function so I didn't added it to the arch-functions. Fixes: 3cf6a32f3f2a4594 ("perf symbols: Fix symbol size calculation condition") Signed-off-by: Namhyung Kim <namhyung(a)kernel.org> Acked-by: Ian Rogers <irogers(a)google.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Ingo Molnar <mingo(a)kernel.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: John Garry <john.garry(a)huawei.com> Cc: Leo Yan <leo.yan(a)linaro.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Poirier <mathieu.poirier(a)linaro.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Michael Petlan <mpetlan(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Song Liu <songliubraving(a)fb.com> Cc: Will Deacon <will(a)kernel.org> Cc: linux-s390(a)vger.kernel.org Cc: linuxppc-dev(a)lists.ozlabs.org Link: https://lore.kernel.org/r/20220416004048.1514900-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..1b85cc1422a9 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -217,7 +217,8 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) } } -void symbols__fixup_end(struct rb_root_cached *symbols) +void symbols__fixup_end(struct rb_root_cached *symbols, + bool is_kallsyms __maybe_unused) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -1467,7 +1468,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1660,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..5fcdd1f94c56 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 86931ff7207bc045fa5439ef97b31859613dc303 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <seanjc(a)google.com> Date: Thu, 28 Apr 2022 23:34:16 +0000 Subject: [PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed host.MAXPHYADDR Disallow memslots and MMIO SPTEs whose gpa range would exceed the host's MAXPHYADDR, i.e. don't create SPTEs for gfns that exceed host.MAXPHYADDR. The TDP MMU bounds its zapping based on host.MAXPHYADDR, and so if the guest, possibly with help from userspace, manages to coerce KVM into creating a SPTE for an "impossible" gfn, KVM will leak the associated shadow pages (page tables): WARNING: CPU: 10 PID: 1122 at arch/x86/kvm/mmu/tdp_mmu.c:57 kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Modules linked in: kvm_intel kvm irqbypass CPU: 10 PID: 1122 Comm: set_memory_regi Tainted: G W 5.18.0-rc1+ #293 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2d0 [kvm] kvm_vm_release+0x1d/0x30 [kvm] __fput+0x82/0x240 task_work_run+0x5b/0x90 exit_to_user_mode_prepare+0xd2/0xe0 syscall_exit_to_user_mode+0x1d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> On bare metal, encountering an impossible gpa in the page fault path is well and truly impossible, barring CPU bugs, as the CPU will signal #PF during the gva=>gpa translation (or a similar failure when stuffing a physical address into e.g. the VMCS/VMCB). But if KVM is running as a VM itself, the MAXPHYADDR enumerated to KVM may not be the actual MAXPHYADDR of the underlying hardware, in which case the hardware will not fault on the illegal-from-KVM's-perspective gpa. Alternatively, KVM could continue allowing the dodgy behavior and simply zap the max possible range. But, for hosts with MAXPHYADDR < 52, that's a (minor) waste of cycles, and more importantly, KVM can't reasonably support impossible memslots when running on bare metal (or with an accurate MAXPHYADDR as a VM). Note, limiting the overhead by checking if KVM is running as a guest is not a safe option as the host isn't required to announce itself to the guest in any way, e.g. doesn't need to set the HYPERVISOR CPUID bit. A second alternative to disallowing the memslot behavior would be to disallow creating a VM with guest.MAXPHYADDR > host.MAXPHYADDR. That restriction is undesirable as there are legitimate use cases for doing so, e.g. using the highest host.MAXPHYADDR out of a pool of heterogeneous systems so that VMs can be migrated between hosts with different MAXPHYADDRs without running afoul of the allow_smaller_maxphyaddr mess. Note that any guest.MAXPHYADDR is valid with shadow paging, and it is even useful in order to test KVM with MAXPHYADDR=52 (i.e. without any reserved physical address bits). The now common kvm_mmu_max_gfn() is inclusive instead of exclusive. The memslot and TDP MMU code want an exclusive value, but the name implies the returned value is inclusive, and the MMIO path needs an inclusive check. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Fixes: 524a1e4e381f ("KVM: x86/mmu: Don't leak non-leaf SPTEs when zapping all SPTEs") Cc: stable(a)vger.kernel.org Cc: Maxim Levitsky <mlevitsk(a)redhat.com> Cc: Ben Gardon <bgardon(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Signed-off-by: Sean Christopherson <seanjc(a)google.com> Message-Id: <20220428233416.2446833-1-seanjc(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f9080ee50ffa..5f6225c384e6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2992,9 +2992,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..e4abeb5df1b1 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c472769e0300..edc68538819b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -815,14 +815,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +831,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +924,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 547ba00ef64f..43174a8d9497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11995,8 +11995,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch));

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 86931ff7207bc045fa5439ef97b31859613dc303 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <seanjc(a)google.com> Date: Thu, 28 Apr 2022 23:34:16 +0000 Subject: [PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed host.MAXPHYADDR Disallow memslots and MMIO SPTEs whose gpa range would exceed the host's MAXPHYADDR, i.e. don't create SPTEs for gfns that exceed host.MAXPHYADDR. The TDP MMU bounds its zapping based on host.MAXPHYADDR, and so if the guest, possibly with help from userspace, manages to coerce KVM into creating a SPTE for an "impossible" gfn, KVM will leak the associated shadow pages (page tables): WARNING: CPU: 10 PID: 1122 at arch/x86/kvm/mmu/tdp_mmu.c:57 kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Modules linked in: kvm_intel kvm irqbypass CPU: 10 PID: 1122 Comm: set_memory_regi Tainted: G W 5.18.0-rc1+ #293 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2d0 [kvm] kvm_vm_release+0x1d/0x30 [kvm] __fput+0x82/0x240 task_work_run+0x5b/0x90 exit_to_user_mode_prepare+0xd2/0xe0 syscall_exit_to_user_mode+0x1d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> On bare metal, encountering an impossible gpa in the page fault path is well and truly impossible, barring CPU bugs, as the CPU will signal #PF during the gva=>gpa translation (or a similar failure when stuffing a physical address into e.g. the VMCS/VMCB). But if KVM is running as a VM itself, the MAXPHYADDR enumerated to KVM may not be the actual MAXPHYADDR of the underlying hardware, in which case the hardware will not fault on the illegal-from-KVM's-perspective gpa. Alternatively, KVM could continue allowing the dodgy behavior and simply zap the max possible range. But, for hosts with MAXPHYADDR < 52, that's a (minor) waste of cycles, and more importantly, KVM can't reasonably support impossible memslots when running on bare metal (or with an accurate MAXPHYADDR as a VM). Note, limiting the overhead by checking if KVM is running as a guest is not a safe option as the host isn't required to announce itself to the guest in any way, e.g. doesn't need to set the HYPERVISOR CPUID bit. A second alternative to disallowing the memslot behavior would be to disallow creating a VM with guest.MAXPHYADDR > host.MAXPHYADDR. That restriction is undesirable as there are legitimate use cases for doing so, e.g. using the highest host.MAXPHYADDR out of a pool of heterogeneous systems so that VMs can be migrated between hosts with different MAXPHYADDRs without running afoul of the allow_smaller_maxphyaddr mess. Note that any guest.MAXPHYADDR is valid with shadow paging, and it is even useful in order to test KVM with MAXPHYADDR=52 (i.e. without any reserved physical address bits). The now common kvm_mmu_max_gfn() is inclusive instead of exclusive. The memslot and TDP MMU code want an exclusive value, but the name implies the returned value is inclusive, and the MMIO path needs an inclusive check. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Fixes: 524a1e4e381f ("KVM: x86/mmu: Don't leak non-leaf SPTEs when zapping all SPTEs") Cc: stable(a)vger.kernel.org Cc: Maxim Levitsky <mlevitsk(a)redhat.com> Cc: Ben Gardon <bgardon(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Signed-off-by: Sean Christopherson <seanjc(a)google.com> Message-Id: <20220428233416.2446833-1-seanjc(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f9080ee50ffa..5f6225c384e6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2992,9 +2992,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..e4abeb5df1b1 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c472769e0300..edc68538819b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -815,14 +815,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +831,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +924,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 547ba00ef64f..43174a8d9497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11995,8 +11995,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch));

2 years, 7 months

1
0
0 0

FAILED: patch "[PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed" failed to apply to 5.17-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.17-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 86931ff7207bc045fa5439ef97b31859613dc303 Mon Sep 17 00:00:00 2001 From: Sean Christopherson <seanjc(a)google.com> Date: Thu, 28 Apr 2022 23:34:16 +0000 Subject: [PATCH] KVM: x86/mmu: Do not create SPTEs for GFNs that exceed host.MAXPHYADDR Disallow memslots and MMIO SPTEs whose gpa range would exceed the host's MAXPHYADDR, i.e. don't create SPTEs for gfns that exceed host.MAXPHYADDR. The TDP MMU bounds its zapping based on host.MAXPHYADDR, and so if the guest, possibly with help from userspace, manages to coerce KVM into creating a SPTE for an "impossible" gfn, KVM will leak the associated shadow pages (page tables): WARNING: CPU: 10 PID: 1122 at arch/x86/kvm/mmu/tdp_mmu.c:57 kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Modules linked in: kvm_intel kvm irqbypass CPU: 10 PID: 1122 Comm: set_memory_regi Tainted: G W 5.18.0-rc1+ #293 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:kvm_mmu_uninit_tdp_mmu+0x4b/0x60 [kvm] Call Trace: <TASK> kvm_arch_destroy_vm+0x130/0x1b0 [kvm] kvm_destroy_vm+0x162/0x2d0 [kvm] kvm_vm_release+0x1d/0x30 [kvm] __fput+0x82/0x240 task_work_run+0x5b/0x90 exit_to_user_mode_prepare+0xd2/0xe0 syscall_exit_to_user_mode+0x1d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> On bare metal, encountering an impossible gpa in the page fault path is well and truly impossible, barring CPU bugs, as the CPU will signal #PF during the gva=>gpa translation (or a similar failure when stuffing a physical address into e.g. the VMCS/VMCB). But if KVM is running as a VM itself, the MAXPHYADDR enumerated to KVM may not be the actual MAXPHYADDR of the underlying hardware, in which case the hardware will not fault on the illegal-from-KVM's-perspective gpa. Alternatively, KVM could continue allowing the dodgy behavior and simply zap the max possible range. But, for hosts with MAXPHYADDR < 52, that's a (minor) waste of cycles, and more importantly, KVM can't reasonably support impossible memslots when running on bare metal (or with an accurate MAXPHYADDR as a VM). Note, limiting the overhead by checking if KVM is running as a guest is not a safe option as the host isn't required to announce itself to the guest in any way, e.g. doesn't need to set the HYPERVISOR CPUID bit. A second alternative to disallowing the memslot behavior would be to disallow creating a VM with guest.MAXPHYADDR > host.MAXPHYADDR. That restriction is undesirable as there are legitimate use cases for doing so, e.g. using the highest host.MAXPHYADDR out of a pool of heterogeneous systems so that VMs can be migrated between hosts with different MAXPHYADDRs without running afoul of the allow_smaller_maxphyaddr mess. Note that any guest.MAXPHYADDR is valid with shadow paging, and it is even useful in order to test KVM with MAXPHYADDR=52 (i.e. without any reserved physical address bits). The now common kvm_mmu_max_gfn() is inclusive instead of exclusive. The memslot and TDP MMU code want an exclusive value, but the name implies the returned value is inclusive, and the MMIO path needs an inclusive check. Fixes: faaf05b00aec ("kvm: x86/mmu: Support zapping SPTEs in the TDP MMU") Fixes: 524a1e4e381f ("KVM: x86/mmu: Don't leak non-leaf SPTEs when zapping all SPTEs") Cc: stable(a)vger.kernel.org Cc: Maxim Levitsky <mlevitsk(a)redhat.com> Cc: Ben Gardon <bgardon(a)google.com> Cc: David Matlack <dmatlack(a)google.com> Signed-off-by: Sean Christopherson <seanjc(a)google.com> Message-Id: <20220428233416.2446833-1-seanjc(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e6cae6f22683..a335e7f1f69e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -65,6 +65,30 @@ static __always_inline u64 rsvd_bits(int s, int e) return ((2ULL << (e - s)) - 1) << s; } +/* + * The number of non-reserved physical address bits irrespective of features + * that repurpose legal bits, e.g. MKTME. + */ +extern u8 __read_mostly shadow_phys_bits; + +static inline gfn_t kvm_mmu_max_gfn(void) +{ + /* + * Note that this uses the host MAXPHYADDR, not the guest's. + * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; + * assuming KVM is running on bare metal, guest accesses beyond + * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit + * (either EPT Violation/Misconfig or #NPF), and so KVM will never + * install a SPTE for such addresses. If KVM is running as a VM + * itself, on the other hand, it might see a MAXPHYADDR that is less + * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR + * disallows such SPTEs entirely and simplifies the TDP MMU. + */ + int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; + + return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; +} + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f9080ee50ffa..5f6225c384e6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2992,9 +2992,15 @@ static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fa /* * If MMIO caching is disabled, emulate immediately without * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. + * MMIO SPTE will just be an expensive nop. Do not cache MMIO + * whose gfn is greater than host.MAXPHYADDR, any guest that + * generates such gfns is running nested and is being tricked + * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if + * and only if L1's MAXPHYADDR is inaccurate with respect to + * the hardware's). */ - if (unlikely(!shadow_mmio_value)) { + if (unlikely(!shadow_mmio_value) || + unlikely(fault->gfn > kvm_mmu_max_gfn())) { *ret_val = RET_PF_EMULATE; return true; } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 73f12615416f..e4abeb5df1b1 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -201,12 +201,6 @@ static inline bool is_removed_spte(u64 spte) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; -/* - * The number of non-reserved physical address bits irrespective of features - * that repurpose legal bits, e.g. MKTME. - */ -extern u8 __read_mostly shadow_phys_bits; - static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index c472769e0300..edc68538819b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -815,14 +815,15 @@ static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm, return iter->yielded; } -static inline gfn_t tdp_mmu_max_gfn_host(void) +static inline gfn_t tdp_mmu_max_gfn_exclusive(void) { /* - * Bound TDP MMU walks at host.MAXPHYADDR, guest accesses beyond that - * will hit a #PF(RSVD) and never hit an EPT Violation/Misconfig / #NPF, - * and so KVM will never install a SPTE for such addresses. + * Bound TDP MMU walks at host.MAXPHYADDR. KVM disallows memslots with + * a gpa range that would exceed the max gfn, and KVM does not create + * MMIO SPTEs for "impossible" gfns, instead sending such accesses down + * the slow emulation path every time. */ - return 1ULL << (shadow_phys_bits - PAGE_SHIFT); + return kvm_mmu_max_gfn() + 1; } static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, @@ -830,7 +831,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_host(); + gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { @@ -923,7 +924,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - end = min(end, tdp_mmu_max_gfn_host()); + end = min(end, tdp_mmu_max_gfn_exclusive()); lockdep_assert_held_write(&kvm->mmu_lock); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 547ba00ef64f..43174a8d9497 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11995,8 +11995,12 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *new, enum kvm_mr_change change) { - if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) + if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) { + if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); + } if (change == KVM_MR_FLAGS_ONLY) memcpy(&new->arch, &old->arch, sizeof(old->arch));

2 years, 7 months

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2022